Revisão Bibliográfica: Learning Vector Quantization 28/04/2003
Download 488.92 Kb.
|
|
....for inference rules and selection of a defuzzification methodology There are a number of fuzzy operators such as multiplication, addition [11] that allows fuzzy relationships to be developed to describe the system. The fuzzy inference rules are called fuzzy associative memories (FAM s) by Kosko [2]. The key part in developing a fuzzy system is to define the fuzzy functions (shape and linguistic label) based on practical experience or the examination of test data. In the past this has been done by a subject matter expert and then tuned based on experimentation. Kosko [2] has suggested that ....
....concern with the inadequacies of the computational model of cognition. As van Gelder and Port point out, there are two main approaches to cognition in continuous temporal contexts, the dynamic (or connectionist) and the computational. The former approach is exemplified by neural nets and Kosko s[21] fuzzy cognitive maps, in which nodes (objects, agents, processes or modules) are connected together by arcs (links, synapses, relationships, channels) which convey continuous time varying real values. The nature of the cognition is determined by the network structure, and the object structure. .... B. Kosko. Neural Networks and Fuzzy Systems. Prentice Hall, 1992. 34
....we demonstrate how robust homing behaviour and docking can also be achieved with TVL robots by adding infra red (IR) sensors to the robot for determining the relative direction of prioritized beacons placed at specific locations in the environment. Note: for a concise description of FAMs, see [15]) In Section 2 we briefly describe the TVL controller used in our previous work. In Section 3 we explain how a TVL robot can effectively navigate indoor environments, negotiate randomly placed obstacles and return to its charging bay by complying with a single instruction ie: follow fast .... B. Kosko. Neural Networks and Fuzzy Systems, Englewood Cliffs, NJ, Prentice Hall, Inc. 1992.
....generating prototype based rules are described, and the fourth section shows that such rules can provide useful explanation of data in cases when logical rules seem to fail. A short discussion concludes this paper. Types of rules Logical rules of several types have been introduced in fuzzy logic [3]. One way to introduce them is by defining predicate functions P i (O j ) for objects O j that are evaluated. In crisp logic these predicate functions may simply check if the object has some property, for example if an attribute has some value A = a k or if the value belongs to some interval. In .... Kosko B, Neural Networks and Fuzzy Systems. Prentice Hall 1992
....mobile robot equipped with a 16 sensor sonar ring. b) Robots trajectory commands (maximum trajectory velocities are shown in brackets) 3. Learning Trajectory Velocities with FAM Matrices Considerable work in fuzzy control uses a matrix representation of fuzzy rules called a FAM matrix (see [Kosko, 1995] for a concise description) A FAM matrix can be described as an N dimensional table where each dimension represents a specific input with size equal to the number of fuzzy sets used to describe that input. So for example, if the input vector is comprised of 6 elements with each input described .... B. Kosko. Neural networks and fuzzy systems, Englewood Cliffs, NJ, Prentice Hall, Inc. 1992.
....T0 T1L T1R T2L T3L T3R T2R (a) b) Figure 8. a) Yamabico mobile robot equipped with a 16 sensor sonar ring. b) Robots trajectory commands with trajectory radii and maximum velocities shown. Previously, Ward and Zelinsky, 1997] we used a single Fuzzy Associative Memory (FAM) matrix (see [Kosko, 1992]) to enable the robot to acquire a mapping between the sonar sensors and 7 trajectories. However this was achieved by grouping the robots sensors into banks of 3, as shown in Figure 9(a) to prevent the FAM matrix from becoming excessively large (as explained in 4 Section 2) The 5 resulting .... ....3 we provide results of experiments showing how the use of multiple FAM matrices can improve the robots perception and behavior. 2. 0 Mapping Sensors to Trajectory Velocities with FAM Matrices Considerable work in fuzzy control uses a matrix representation of fuzzy rules called a FAM matrix (see [Kosko, 1992] for a concise description) A FAM matrix can be described as an N dimensional table where each dimension represents a specific input with size equal to the number of fuzzy sets used to describe that input. Thus a FAM matrix with inputs and fuzzy sets described in Figure 9 would contain 5 4 3 .... B. Kosko. Neural networks and fuzzy systems, Englewood Cliffs, NJ, Prentice Hall, Inc. 1992. 
Application Of Knowledge Based Systems For Supervision.. - Haber, Haber, Alique.. ....system s objectives. Wang and Tyan [108] give a classification of the most useful schemes for fuzzy logic based modeling and fuzzy control: FLD for input selection (type 1) 119] FLD for feedback error output control (type 2) 54] FLD for controlling the parameters of dynamic systems (type 3) [58], FLD for choosing the best compensator (type 4) 53,78] FLD derived from a multiple performance index (type 5) 114] FLD as a mathematical model for unknown or complex system dynamics (type 6) 113] Hierarchical FLD (type 7) 69] We must select the appropriate control and modeling .... B.Kosko, Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ, 1991.
....simulation due to the long learning time resulting from the credit assignment problem and the need to learn each behaviour as well as its variations individually on separate maps. To store associations between input vectors and trajectory velocities we use a Fuzzy Associative Memory (FAM) matrix [Kosko, 1992] as this provides good generalization capability as well as fast access to the fuzzy rule consequents as explained by [Sudkamp and Hammel 1994] In Section 2 of this paper, we briefly describe the FAM matrix used in our experiments as well as the fuzzy rule extraction procedure used to update the .... B. Kosko. Neural Networks and fuzzy Systems, Englewood Cliffs, NJ, Prentice Hall, Inc. 1995.
....# # A # B # B # ( A # B # ) 9. i(A, B) # u#U 1#(1 Au Bu ) U . 10. i(A, B) # u#U (1 Au )#Bu U . 11. i(A, B) # u#U (1 Au AuBu ) U . 12. i(A, B) sup # : #u # U we have A u # # # B u # # . Inclusion measure no.1 above is Kosko s inclusion measure [16]; no. 12 is introduced in [17] and does not appear very widely in the literature; for references to the remaining inclusion measures see [9] and [32] The only inclusion measure in the above list which is # transitive is no.12, Kundu s inclusion measure. In addition, Willmott introduces some .... B. Kosko. Neural Networks and Fuzzy Systems. Prentice-Hall, 1992.
....as an extension to these, where the resulting solution is implemented in the software as a tree structure, and it can be of a variable length. This approach has a definite advantage among other computational intelligence (CI) approaches as the neural networks (NN) or the fuzzy systems (FS) [Kosko 1992], by means that the extracting solution is both easily comprehensible and it does not require any special software (or a fuzzy controller) to be applied any further [Koza et. al 1999] It also does not require prior knowledge for the solution size in order to define the model (as it is essential .... Bart Kosko , Neural Networks and Fuzzy Systems , Prentice Hall, 1992
.... require data pre processing in order to avoid the noise adaptation [Bishop 1995] An implementation of a self learning fuzzy system may consist of an evolutionary training of the rule base and a neuro fuzzy training phase for tuning the membership functions of the premise part As described by Kosko [Kosko 1992] the rule base may be coded in a fuzzy associative memory (FAM) matrix. After FAM matrix consideration takes place, it is easy to construct an efficient binary coding to represent this FAM matrix in bit strings which will be used by a genetic algorithm to find the optimal solution [Bersini 1998] .... Kosko Bart, Neural Networks and Fuzzy Systems , Prentice Hall, 1992
....there are many problems whose solution only need qualitative information that is easy to pick up, while obtaining precise information to set up an accurate mathematical model may be costly or even impossible. This is frequently the case for problems of control design in an uncertain environment [4, 12], and has lead to many innovative engineering applications, such as in trac control [10] or the fuzzy control units in cameras and vacuum cleaners. In the following, we discuss fuzzy modeling based on the concept of surprise, see Section 3. This deviates from tradition [7] where the concept of .... ....call the solutions x a of (9) the ambivalence points of E. The set of points with s(xjE) 1 will be called the preference region of E. Points x minimizing s(xjE) also have special signi cance as the least surprising and hence most plausible points for a statement E. Compare this with Kosko s [12] notion of points of maximum entropy. While fuzzy logic (discussed in the next section) can be used to assign surprise values to composite statements, the surprise values of the constituents must be determined by some other means. Before discussing linguistic statements we shall look at a ....
..... A good choice of local matching strategy is the key for good results in the global matching process. This paper presents an approach to the local stereopsis correspondence problem by developing a learning strategy based on the Self Organizing Fea Z. Z ture Mapping SOFM algorithm Kohonen, 1989; Kosko, 1992; Martin Smith et al. 1993; Haykin, 1994; Sonka et al. 1995; Flanagan and Hasler, 1995 . Two sorts of techniques have been broadly used Z for stereo matching, Dhond and Aggarwal, 1989; Ozanian, 1995; Pajares, 1995 area based and fea Z. ture based. 1 Area based stereo techniques use cor .... ....constant or defines a decreasing sequence of positive numbers Z x on the interval 0,1 . Numerous simulations have shown that the best results are obtained if it is selected fairly wide in the beginning and then per Z. mitted to shrink with iteration k, and fulfills ck TM Z 0, k TM Kohonen, 1989; Kosko, 1992; Martin .Z. Smith et al. 1993; Haykin, 1994 . The function hd Z is a neighbourhood function Martin Smith et al. q 1993; Flanagan and Hasler, 1995 such that h : R TM R q . Finally, R is the radius of the hyper sphere. Experimental tests have shown that Rs10 is a satisfying value for the .... Kosko, B., 1992. Neural Networks and Fuzzy Systems. PrenticeHall, Englewood Cliffs, NJ.
A Soft Computing Approach for Modelling the Supervisor of.. - Stylios, Groumpos (1999) ....areas. For example, in political science [1] fuzzy cognitive maps were used to represent social scientific knowledge and describe decisionmaking methods. Kosko enhanced the power of cognitive maps considering fuzzy values for their concepts and fuzzy degrees of interrelationships between concepts [8, 9]. After this pioneering work, fuzzy cognitive maps attracted the attention of scientists in many fields and they have been used in a variety of different scientific problems. Fuzzy cognitive maps have been used for planning and making decisions in the field of international relations and political .... Kosko, B.: Neural Networks and Fuzzy Systems, Prentice-Hall, New York, 1992.
....This may increase the intelligence of the system; as the more intelligent a system becomes, the more symbolic and fuzzy representation is used. 2. Fuzzy cognitive maps An FCM is a methodology for representing the behaviour of models and it is a combination of fuzzy logic and neural networks (Kosko, 1986, 1992). An FCM describes the behaviour of a system in terms of concepts and eects among concepts. An FCM (Fig. 1) is a fuzzy signed directed graph with feedback, where nodes of the graph represent concepts or elements that comprise the model and are connected by signed and weighted arcs representing .... ....of the modelling, behaviour and operation of the complex lower level system and this is depicted in the upper level by the expert item that inuences the FCM. After primitive construction, the FCM can be re ned using training methods, based on unsupervised neural networks and learning algorithms (Kosko, 1986, 1992), i.e. the Hebbian learning algorithm. During the learning period, the weights of the interconnections will be adjusted according to existing measurements and data on the operation of the system, and then a more integrated FCM, will have been constructed. After the construction and training of .... Kosko, B. (1992) Neural Networks and Fuzzy Systems, PrenticeHall, Englewood Clis, NJ, pp. 152158.
Extension of bayesian decision theory and fuzzy logic to decision .. - Dierkes (1996) ....linguistic terms are then expressed by fuzzy sets which are defined by there membership functions. In the given example the linguistic variable would be height. The according 1 In this paper fuzzy set will be only described as far as needed for the used approaches, for more information see e.g. [Kos92b] 10 150 cm 200 cm small large 1 0 Height (x) Figure 2.3: Example fuzzy sets linguistic terms would be small and large. The fuzzy sets can be then defined over the universe [0cm; 270cm] by there membershipfunctions (see figure 2.3) In this example every person smaller than 150 cm is .... ....or cuting them. Here e.g. two fuzzy sets JSQ is suitable and PF is suitable with the membership functions as defined in figure 2.5 are given. 2 There exist a wide range of different functions for the AND operator. Common used operators has specific attributes and belongs to the so called t norms [Kos92b] 12 1 0 (x) JSQ is suitable PF is suitable Figure 2.5: Output fuzzy sets JSQ PF If we now evaluate the rule given above with the values for queue length as in table 2.3, then the value for Rule is: Rule = Minimum( P remise 1 (Rule) P remise 2 (Rule) P remise 3 (Rule) .... B. Kosko. Neural Networks and Fuzzy Systems. Prentice Hall, 1992.
A Neural Network Primer - Abdi (1994) (8 citations) .... source of reference can be found in fields as varied as physics of complex systems (e.g. Fogelman Souli e [23] Serra Zanarini [76] Goles Martinez [28] Weisbuch [82] engineering sciences or signal processing (e.g. Widrow Stearns [85] Catlin [18] Soucek [80] Garner [25] Kosko [43,44]) and neurosciences (e.g. Mac Gregor [49] Amit [7] 7. Acknowledgement Thanks are due to Jay Dowling, Betty Edelman, Alice O Toole, and Dominique Valentin for comments on earlier drafts of this paper. .... Kosko B., Neural Network and Fuzzy Systems. (Prentice-Hall, Englewwod Cliffs, 1991).
....(t) 5) where a d (t) is an appropriateness measure for d. When d is not meaningful, a d (t) 0. Note that as the robot moves, the effective number of participating local control laws may change. Other compositional approaches to control include potential field methods [2, 31] and fuzzy control [20, 10]. Appropriateness measures and other parameters of the control laws i may be acquired and optimized by function learning methods including neural nets (e.g. 29] and memory based learning [3, 22] Hill Climbing. Starting in the state where a trajectory following control law terminates, identify .... Bart Kosko. Neural Networks and Fuzzy Systems. Prentice-Hall, Englewood Cliffs, NJ, 1992.
....wehave been investigating the application of fuzzy logic #Zadeh 1965#, as fuzzy rule systems can easily cope with such situations through linguistic reasoning #Surmann, Peters, Huser 1995#. A fuzzy controller is also normally very robust and can tolerate major degradation of its rule structure, #Kosko 1992# and insensitivity to noise or uncertainties in the control inputs, which make it ideally suited to mobile robot control #Watanabe Pin 1993#. AFuzzy control system works by encoding an experts knowledge into a set of rules which are smoothly interpolated and the resultant is defuzzi#ed to .... ....A# and #y is B# then #z is C# #7# where x, y, z are linguistic variables representing inputs and outputs of the fuzzy controller, and A, B and C are the terms for the variables in the universes of discourse X, Y , and Z. Fuzzy rules can be represented by a fuzzy associative memory matrix, #FAM# #Kosko 1992#. In this system the base dimensions represent the input variables and eachFAM entry represents an output fuzzy set. There are typically 3 to 5 output membership sets, e.g. negative large #NL#, negative small #NS#, zero #ZE#, positive small #PS#, and positive large #PL#. Using a FAM .... Kosko, B. 1992. Neural Networks and Fuzzy Systems, A Dynamical Systems Approach to Machine Intelligence. Prentice Hall Int.
Adaptive Joint Fuzzy Sets for Function Approximation - Sanya Mitaim And (1997) Self-citation (Kosko) ....Centroid( w j a j (x)B j ) b) Fuzzy rules define patches in the input output space and cover the graph of the approximand f . This leads to exponential rule explosion in high dimensions. Optimal lone rules cover the extrema of the approximand. We used the standard additive model (SAM) [4, 6, 8] for the fuzzy function approximator: F (x) Centroid m w j a j (x)B j j=1 w j a j (x)V j c j j=1 w j a j (x)V j p j (x)c j : 1) The fuzzy system F : R covers the graph of an approximand f with m fuzzy rule patches of the form A j Theta B j ae R Theta R or of the .... B. Kosko. Neural Networks and Fuzzy Systems. Prentice Hall, 1991.
Kosko, B., Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ, 1992.
Adaptive Techniques for Multiple Actuator Blending - Menon, Iragavarapu (1998) Kosko, B., Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ, 1992.
What Procedure To Choose While Designing A Fuzzy Control? .. - Vladik Kreinovich Chris (1991) (2 citations) A survey of fuzzy clustering algorithms for pattern recognition - Baraldi, Blonda (1998) (2 citations) i) SelfOrganizing Map (SOM)ii) Fuzzy Learning Vector Quantization (FLVQ)iii) Fuzzy Adaptive Resonance ftp.icsi.berkeley.edu/pub/techreports/1998/tr-98-038.ps.gz Presupervised and Postsupervised Prototype Classifier Design - Kuncheva, Bezdek a class of fuzzy if-then systems [15]Learning Vector Quantization (LVQ) classi ers [11]12]14] www.bangor.ac.uk/~mas00a/papers/lktnn.ps.gz Soft vector quantization and the EM algorithm - Ethem Alpaydn Department (HCM)fuzzy c-means (FCM)fuzzy learning vector quantization (FLVQ)soft competition scheme (SCS) www.cmpe.boun.edu.tr/~ethem/files/papers/1147.pdf Soft-to-hard model transition in clustering: a review - Baraldi, Schenato (1999) hard c-means, Maximum-Entropy, Fuzzy Learning Vector Quantization (FLVQ)Neural Gas (NG) ftp.icsi.berkeley.edu/pub/techreports/1999/tr-99-010.ps.gz A Case Study On Two Groups Of GNP Classifiers - Kuncheva a class of fuzzy if-then systems Learning Vector Quantization (LVQ) classi ers edited nearest www.bangor.ac.uk/~mas00a/eufit98.ps.Z A Fuzzy Generalized Nearest Prototype Classifier - Kuncheva, Bezdek (1997) parts. For example, the supervised learning vector quantization (LVQ) model can be used to obtain V www.bangor.ac.uk/~mas00a/ifsa97.ps.gz A Fuzzy Generalized Nearest Prototype Classifier - Kuncheva, Bezdek (1997) parts. For example, the supervised learning vector quantization (LVQ) model can be used to obtain V www.bangor.ac.uk/~mas00a/ifsa97.ps.gz 6.1.3. Computação Evolutiva
Citado por: Model-based search for combinatorial optimization: A.. - Zlochin, Dorigo Solving Sequence Problems by Building and Sampling Edge.. - Tsutsui, Goldberg.. (2002) Multi-Objective Mixture-based Iterated Density Estimation.. - Thierens, Bosman (2001)
Abstract: Recently, there has been a growing interest in developing evolutionary algorithms based on probabilistic modeling. In this scheme, the offspring population is generated according to the estimated probability density model of the parent instead of using recombination and mutation operatom. In this paper, we have proposed probabilistic model-building genetic algo- rithms (PMBGAs) in permutation representation domain using edge histogram based sampling algorithms (EHBSAs). Two types of... Evolutionary Algorithm using Marginal Histogram Models.. - Tsutsui, Pelikan.. (2001) Mathematical Modelling of UMDAc Algorithm with.. - González.. (2002) Escaping Hierarchical Traps with Competent Genetic Algorithms - Pelikan, Goldberg Simplex Crossover and Linkage Identification: Single-Stage.. - Tsutsui, Goldberg (2002) Evolutionary Algorithm Using Marginal Histogram Models.. - Tsutsui, Pelikan.. (2001) Combining the Strengths of the Bayesian Optimization.. - Pelikan, Goldberg.. (2001) Implementation Issues for Reverse Hillclimbing - This An Overview of Genetic Algorithms: Part 2, Research Topics - Beasley, Bull, Martin (1993) Genetic Algorithms in Timetabling and Scheduling - Fang (1994) Linkage Learning Genetic Algorithm in C++ - Lobo (1998) Extended Compact Genetic Algorithm in C++ - Lobo, Harik (1999) Compressed Introns in a Linkage Learning Genetic Algorithm - Lobo, Deb, Goldberg.. (1998) Linkage Learning via Probabilistic Modeling in the ECGA - Harik - 1999 Using optimal dependency-trees for combinatorial optimization: Learning the stru.. - Baluja, Davies - 1997 Population-based incremental learning: A method for integrating genetic search b.. - Baluja – 1994
Introduction to the theory of neural computation - Hertz, Krogh et al. - 1993 An analysis of the behavior of a class of genetic adaptive s.. - De Jong - 1975 A connectionist machine for genetic hill climbing - Ackley - 1987 Removing the genetics from the standard genetic algorithm - Baluja, Caruana - 1995 Mixing in genetic algorithms - Thierens, Goldberg - 1993 Population-based incremental learning: A method for integrat.. - Baluja - 1994 The gambler's ruin problem - Harik, Cant'u-Paz et al. - 1997 Foundations of Genetic Algorithms - Belew, Vose et al. - 1993 Crossover's niche - Eshelman, Schaffer - 1993 Analyzing deception in trap functions - Deb, Goldberg - 1993 Simple genetic algorithms and the minimal - Goldberg – 1987 The Ant System: Optimization by a Colony of Cooper- ating Ag.. - Dorigo, Maniezzo et al. - 1996 Population-based incremental learning: A method for interact.. - Baluja - 1994 A survey of optimization by building and using probabilistic.. - Pelikan, Goldberg et al. - 1999 BOA: The Bayesian optimization algorithm - Pelikan, Goldberg et al. - 1999 Linkage learning via probabilistic modeling in the ECGA - Harik - 1999 Addi- son-Wesley publishing company - Goldberg - 1989 MIMIC: Finding optima by estimating probability densities - De Bonet, Isbell et al. - 1997 The compact genetic algorithm - Harik, Lobo et al. - 1998 From recombination of genes to the estimation of distributio.. - Mhlenbein, Paa - 1996 Edge assembly crossover: A high-power genetic algorithm for .. - Nagata, Kobayashi - 1997 Extending population-based incremental learning to continuou.. - Sebag, Ducoulombier - 1998 Improving TSP exchange heuristics by population genetics - Ulder, Pesch et al. - 1990 Estimation of distribution algorithms - Larranaga, Lozano - 2002 Continuous iterated density estimation evolutionary algorith.. - Bosman, Thierens - 2000 An algorithmic framework for density estimation based evolut.. - Bosman, Thierens - 1999 and Bayesian network - Pelikan, Goldberg et al. - 2000 Optimization in continuous do- mains by learning and simulat.. - Larranaga, Etxeberria et al. - 2000 Optimization by learning and simulation of Bayesian and gaus.. - Larranaga, Etxeberda et al. - 1999 A comparison of genetic sequence operators - Starkweather, McDaniel et al. - 1991 Evolutionary Algorithm using Marginal Histogram Models in Co.. - Tsutsui, Pelikan et al. - 2001 Solving the traveling salesman problem with EDAs - Robles, Miguel et al. - 2002 Telephone network traffic overloading diagnosis and evolutio.. - Server, Trave-Massuyes et al. - 1997 Probabilistic Model-Building Genetic Algorithms in Permutati.. - Tsutsui - 2002 A study of permutation crossover operators on the travel sal.. - Oliver, Smith et al. - 1987 Scheduling problems and traveling salesman problem: The gene.. - Whitley, Starkweather et al. - 1989 The Trav- eling Salesman Problem and its Variations - Johnson, McGeoch Utrecht Univer- sity - Bosman, Thierens - 2000 and Davies: Using optimum dependency-trees for combinatorial.. - Baluja - 1997
Genetic Algorithms for Social Innovation and Creativity - Kosoruko, Goldberg (2001) Evolutionary Algorithm Using Marginal Histogram Models.. - Tsutsui, Pelikan.. (2001) Modeling Tournament Selection With Replacement Using.. - Sastry, Goldberg (2001)
Population Based Incremental Learning: A Method for Integrating.. - Baluja (1994) (41 citations) Equilibrium Genetic Algorithm, Learning Vector Quantization. 3/41 Population Based Incremental www.cs.cmu.edu/afs/cs/user/baluja/www/papers/CMU-CS-94-163.ps.gz Optimization of classifiers using genetic algorithms - Merelo, Prieto, Morán (1996) others from neural networks: Kohonen's Learning Vector Quantization [3] LVQ)multilayer perceptrons kal-el.ugr.es/pub/papers/g-lvq-book.ps.gz 6.1.4. Inteligência Artificial Abstract: Knowledge acquisition is a frequent bottleneck in artificial intelligence applications. Neural learning may offer a new perspective in this field. Using Self-Organising Neural Networks, as the Kohonen model, the inherent structures in high-dimensional input spaces are projected on a low dimensional space. The exploration of structures resp. classes is then possible applying the U-Matrix method for the visualisation of data. Since Neural Networks are not able to explain the obtained results, a...
A Method for Temporal Knowledge Conversion - Guimarães, Ultsch Massively Parallel Reasoning - Bornscheuer, Hölldobler, Kalinke.. (1998) Hybrid Systems Architectures - Kurfeß (1996) Automatic Acquisition of Symbolic Knowledge from Subsymbolic.. - Ultsch, Korus (1995) Neural networks and their rules for classification in.. - Ultsch, Korus, Wehrmann (1995) Integration of Neural Networks and Knowledge-Based Systems in.. - Ultsch, al. (1995) Data Mining and Knowledge Discovery with Emergent Self-Organizing .. - Ultsch (1999) Self-Organization and Associative Memory - Teuvo - 1989 Book Details from Barnes & Noble Learning Efficient Classification Procedures and their Appli.. - Quinlan - 1984 Exploratory Data Analysis: Using Kohonen Networks on Transpu.. - Ultsch, Siemon - 1989 Automatic Acquisition of Symbolic Knowledge from Subsymbolic.. - Ultsch, Li - 1993 A hybrid Expert System for Avalanche Forecasting - Schweizer, Fohn et al. - 1993 Konnektionistische Modelle und ihre Integration mit wissensb.. - Ultsch - 1991 Wissensverarbeitung in neuronaler Architektur - Ultsch, Palm et al. - 1991 Neuronale Netze auf Transputern - Guimaraes, Korus - 1992 Self-Organising Neural Networks for Monitoring and Knowledge.. - Ultsch Neuronale Netze zur Unterstützung der Um weltforschung - Ultsch, Halmans - 1991 Taschenbuch der medizinisch-klinischen Diagnostik - Muller, Seifert - 1989 Clusteranalyse und Diskriminanzanlyse - Deichsel, Trampisch - 1985 Anwendung von Kohonen Netzen zur Darstellung und Steuerung v.. - Wayand - 1992 Prevision des grosses avalanches au moyens d'un model determ.. - Fohn, Hachler - 1978 Self-Organising Neural Networks for Visualisation and Classi.. - Ultsch – 1992
Integration of Neural Networks and Knowledge-Based Systems in.. - Ultsch, al. (1995) Neural networks and their rules for classification in.. - Ultsch, Korus, Wehrmann (1995) Automatic Acquisition of Symbolic Knowledge from Subsymbolic.. - Ultsch, Korus (1995)
A Method for Temporal Knowledge Conversion - Guimarães, Ultsch Integration of Neural Networks with Knowledge-Based Systems - Ultsch, Korus (1995) Automatic Acquisition of Symbolic Knowledge from Subsymbolic.. - Ultsch, Korus (1995) Massively Parallel Reasoning - Bornscheuer, Hölldobler, Kalinke.. (1998) Hybrid Systems Architectures - Kurfeß (1996) Neural networks and their rules for classification in.. - Ultsch, Korus, Wehrmann (1995) Integration of Neural Networks and Knowledge-Based Systems in.. - Ultsch, al. (1995) PREENS, a Parallel Research Execution Environment for.. - Vuurpijl, Schouten.. Process Monitoring and Visualisation Using Self-Organizing Maps - Simula, Kangas (1995) Hardware Implementations of Kohonen's Selforganizing.. - Speckmann, Thole.. (1992) Systematic Methods for Multivariate Data Visualization.. - König, Bulmahn, Glesner (1994) A Survey of Methods for Multivariate Data Projection.. - König A hardware supported system for Kohonen's Selforganizing Map - Thole, Speckmann.. (1993) Concept Formation by Combining Neural Networks and Machine Learning - Sklorz Coprocessors for special neural networks KOKOS and KOBOLD - Speckmann, Thole.. Chris Thornton - Cognitive And A Geographic Knowledge Representation System for.. - Chen, Smith.. Data mining and EEG - Flexer (2000) Exemplar-Based Reasoning in Geological Prospect Appraisal - Clark (1989) Classification With Overlapping Feature Intervals - Koc (1995) Data Mining and Knowledge Discovery with Emergent Self-Organizing .. - Ultsch (1999) An Artificial Life Approach to Data Mining - Ultsch Complete References April 1984 - February 1998 - Wirtz (1998) Self-Organizing Neural Networks for Knowledge Acquisition - Ultsch - 1992 Parallel Distributed Processing - Rumelhart, McClelland - 1986 Knowledge Processing in Neural Architecture - Palm, Goser et al. - 1992 RAMBOT: A connectionist expert system that learns by example - Mozer - 1987 Clusteranalyse und Diskriminanzanalyse - Deichsel, Trampisch - 1985 Self-Organizing Neural Networks for Exploratory Data Analysis - Ultsch, Siemon - 1992 Self organization of stable category recognition codes for analog input patterns - Grossberg, Carpenter - 1987 Using Activation Networks for Analogical Ordering of Consideration: Due Method f.. - Becks, Burchard et al. - 1990 Self organized feature maps for monitoring and knowledge acquisition of a chemic.. - Ultsch - 1993 Self-Organization and Associative Memory - Kohonen - 1989 Book Details from Barnes & Noble Connectionist Modells and their Integration with Knowledge-Based Systems - Ultsch - 1991 Self Organizing Feature Maps for Logical Unification - Ultsch, Guimaraes et al. - 1994 Optimizing logical proofs with connectionist networks - Ultsch, Hannuschka et al. - 1991 Information and Control - Zadeh - 1965 Neural Networks in Biochemical Analysia - Ultsch, Korus et al. - 1995 A hybrid Expert System for Avalanche Forecasting - Schweizer, Fohn et al. - 1993 Knowledge acquisition with self-organizing neural networks - Ultsch - 1992 Automatic Acquisition of Symbolic Knowledge from Subsymbolic Neural Networks - Ultsch, Li - 1993 Integration of distributed and symbolic knowledge representations - Hutchison, Stephens - 1987
Data exploration using self-organizing maps - Kaski (1997) Statistical Analysis of Consumer Perceptions - Strasser (2000) Growing Cell Structures - A Self-organizing Network for.. - Fritzke (1993) Unsupervised image segmentation with the self-organizing map.. - Iivarinen, Visa Self-Organizing Maps for Pattern Classification - Atukorale (1999) Optimization of Neural Networks: A Comparative Analysis.. - Sexton, Dorsey, Johnson (1999) Visualizing High-Dimensional Structure with the.. - Blackmore, Miikkulainen (1995) An Analysis of Recent Work on Clustering Algorithms - Fasulo (1999) Kohonen Feature Maps and Growing Cell Structures - a Performance.. - Fritzke (1993) Organization Measures for Self-Organizing Maps - Polani (1997) How Many Clusters? Which Clustering Method? Answers Via.. - Fraley, Raftery (1998) Visualizing Similarities in High Dimensional Input Spaces with .. - Köhle, Merkl (1996) Self-organising Data Mining -- An Intelligent.. - Johann-Adolf.. Self-Organizing Maps: Generalizations and New.. - Graepel, Burger.. (1998) Fuzzy Prediction of Timeseries - Pratap Khedkar (1992) Script Recognition with Hierarchical Feature Maps - Miikkulainen (1990) Segmentation Based Competitive Analysis with MULTICLUS and.. - Reutterer, Natter (1999) On Clustering Properties of Hierarchical Self-Organizing Maps - Lampinen (1992) RAMP: Rules Abstraction for Modeling and Prediction - Apte, Hong, Lepre, Prasad.. (1995) Unsupervised Catalog Classification - Murtagh (1995) 6.2. Learning Vector Quantization em Ciências Médicas e Biológicas 6.2.1. Projeto Genoma One of the most important problems in post-genome biology is to understand the genetic architecture (properties of individual genes to entire gene networks) of quantitative or complex traits, which is important in a number of biological contexts including medicine, agriculture, evolution and functional genomics. Combination of QTL mapping with functional genomics leads to identification of candidate genes, gene network inference, and identification of many genes and aspects of metabolism, physiology etc. otherwise missed. In a narrow view and in particular in the initial stages of biological (genomic) research, bioinformatics deals with the acquisition of relational databases, as well as the development of efficient methods for searching and viewing these data. In a broader and longer-term view, bioinformaticists develop statistical and algorithmic approaches to the production and extraction of information from large amounts of biological data. The development of Bioinformatics tools will be most successful if it integrates ideas and methods from different disciplines, including statistics, computer science, and engineering. An example of the need for such integration is classification or pattern recognition (e.g., for the analysis of microarray data and DNA sequence data), where methods are derived from theory in statistics, computer science and engineering (statistical decision theory, computational learning theory; multivariate statistical analysis, neural networks, learning vector quantization, self-organizing maps, support vector machines). Statistical geneticists are trained jointly in genetic/genomic data generation and experimentation, statistics, quantitative genetics, statistical and computational genetics, and population genetics. Statistical geneticists work in areas including gene discovery (e.g., genetic linkage studies, genetic map construction, population association studies using SNP polymorphisms), gene function investigation (e.g. analysis of transcription profiling data), analysis of DNA and protein sequences including probabilistic sequence alignment, molecular evolution, investigation of protein structure and protein evolution, and population genetics with applications in many other areas including forensic science and population association studies. Continued development of sound statistical methods is essential, in particular as gene discovery is moving from monogenic to complex traits and diseases, simplistic approaches based on either linkage or disequilibrium are replaced with combined linkage and linkage disequilibrium mapping, and as there is a move from comparing two mRNA populations to high-dimensional transcription profiling and the goal of unraveling gene networks and metabolic pathways. Optimizing the BAC-End Strategy for Sequencing the Human Genome - Richard M. Karp Ron Shamir April 24, 1999 Abstract: The rapid increase in human genome sequencing effort and the emergence of several alternative strategies for large-scale sequencing raise the need for a thorough comparison of such strategies. This paper provides a mathematical analysis of the BAC-end strategy of (Venter,1996) showing how to obtain an optimal choice of parameters. The analysis makes very mild assumptions. In particular, it accommodates variable clone length and inhomogeneity of the distribution of clone locations. Artigos Relacionados: Management of Space in Hierarchical Storage Systems - Ghandeharizadeh, Ierardi.. (1994) Splicing UNIX into a Genome Mapping Laboratory - Lincoln Stein (1994) Algorithms in Computational Biology - Pedersen (2000) An Algorithmic Approach to Multiple Complete Digest Mapping - Daniel Fasulo Tao (1997) Citações: Probability and random processes - Grimmet, Stirzaker - 1992 Genomic mapping by fingerprinting random clones: A mathemati.. - Lander, Waterman - 1988 A new strategy for genome sequencing - Venter, Smith - 1996 Mapping and sequencing the human genome - Council - 1988 Mapping our genes -- the genome projects - Technology, Congress - 1988 Analysis of sequence-taggedconnector strategies for DNA sequ.. - Siegel, Trask et al. - 1998
Algorithms for Optical Mapping - Karp, Shamir (1998) Algorithms and Complexity of Sandwich Problems in Graphs.. - Golumbic, Kaplan, Shamir (1994) 6.2.2 Detecção de clones Information and the Clone Mapping of Chromosomes - Bin Yu, T. P. Speed Abstract: A clone map of part or all of a chromosome is the result of organizing order and overlap information concerning collections of DNA fragments called clone libraries. In this paper, the expected amount of information (entropy) needed to create such a map is discussed. A number of different formalizations of the notion of a clone map are considered, and for each, exact or approximate expressions or bounds for the associated entropy are calculated. Based on these bounds, comparisons are made for... Artigos Relacionados: Revealing Hidden Interval Graph Structure in STS-Content Data - Harley, Bonner, Goodman (1998) Construction of Physical Maps From Oligonucleotide.. - Mayraz, Shamir (1998) A Robust Algorithm for Constructing Physical Maps From Noisy.. - Mayraz (1998) A Computational Approach to Sequence Assembly Validation - Kim, Liao, Perry, Zhang, Tomb Fast Approximate Matching in Restriction Site Mapping - Madani (1995) End Fragment Constraints in Stochastic Assembly of Contig.. - Platt, Dix, Macphee Citações:
An Introduction to Probability Theory and its Applications - Feller - 1968 Book Details from Amazon or Barnes & Noble Combinatorial Theory - Aigner - 1979 Book Details from Amazon or Barnes & Noble Genomic mapping by fingerprinting random clones: a mathemati.. - Lander, Waterman - 1988 Physical mapping of chromosomes: a combinatorial problem in .. - Alizadeh, Karp et al. - 1993 Random-clone strategy for genomic restriction mapping in yea.. - Olson, Dutchik et al. - 1986 Radiation hybrid mapping: A somatic cell genetic method for .. - Burmeister, Price et al. - 1990 Optimizing restriction fragment fingerprinting methods for o.. - Branscomb, Slezak et al. - 1990 Hybridization fingerprinting in genome mapping and sequencin.. - Lehrach, Drmanac et al. - 1990 the design of genome mapping experiments using short synthet.. - Fu, Timberlake et al. - 1992 Statistical Issues in Constructing High Resolution Physical .. - Nelson, Speed - 1994 A diary on information theory - Renyi - 1984 Book Details from Barnes & Noble Sequence-tagged sites - Green, Green - 1991 Ordering of cosmic clones covering the Herpes simplex virus .. - Craig, Nizetic et al. - 1990 Fluorescence in situ hybridization -- Applications in cytoge.. - Trask - 1991 Evaluating and Counting DNA Physical Maps - Newberg - 1993 Site http://stat-www.berkeley.edu/pub/users/binyu/publications.html Estimating L¹ Error of Kernel Estimator: Monitoring.. - Yu Iterated Logarithmic Expansions of the Pathwise Code Lengths for.. - Li, Yu (2000) "Comprestimation": Microarray Images in Abundance. - Jörnsten, Yu (2000)
geometry using artificial neural networks - AU Mattfeldt, T; Gottfried, HW; Schmidt, V; Kestler, HA Abstract: Stereology and stochastic geometry can be used as auxiliary tools for diagnostic purposes in tumour pathology. Whether first-order parameters or stochastic-geometric functions are more important for the classification of the texture of biological tissues is not known. In the present study, volume and surface area per unit reference volume, the pair correlation function and the centred quadratic contact density function of epithelium were estimated in three case series of benign and malignant lesions of glandular tissues. The information provided by the latter functions was summarized by the total absolute areas between the estimated curves and their horizontal reference lines. These areas are considered as indicators of deviation of the tissue texture from a completely uncorrelated volume process and from the Boolean model with convex grains, respectively. We used both areas and the first-order parameters for the classification of cases using artificial neural networks (ANNs). Learning vector quantization and multilayer feedforward networks with backpropagation were applied as neural paradigms. Applications included distinction between mastopathy and mammary cancer (40 cases), between benign prostatic hyperplasia and prostatic cancer (70 cases) and between chronic pancreatitis and pancreatic cancer (60 cases). The same data sets were also classified with linear discriminant analysis. The stereological estimates in combination with ANNs or discriminant analysis provided high accuracy in the classification of individual cases. The question of which category of estimator is the most informative cannot be answered globally, but must be explored empirically for each specific data set. Using learning vector quantization, better results could often be obtained than by multiplayer feedforward networks with backpropagation.
Abstract: As a recently developed and powerful classification tool, probabilistic neural network was used to distinguish cancer patients from healthy persons according to the levels of nucleosides in human urine. Two datasets (containing 32 and 50 patterns, respectively) were investigated and the total consistency rate obtained was 100% for dataset 1 and 94% for dataset 2. To evaluate the performance of probabilistic neural network, linear discriminant analysis and learning vector quantization network, were also applied to the classification problem. The results showed that the predictive ability of the probabilistic neural network is stronger than the others in this study. Moreover, the recognition rate for dataset 2 can achieve to 100% if combining, these three methods together, which indicated the promising potential of clinical diagnosis by combining different methods.
Abstract: Objective: The choice of therapy for prostatic cancer should depend on a rational preoperative estimate of tumor stage. Artificial neural networks were used to predict postoperative staging of prostatic cancer from sextant biopsies and routinely available preoperative data. Methods: In group I (97 cases), nonorgan confinement (tumor stage greater than or equal to pT3a) was predicted on the basis of age and six histopathological variables from sextant biopsies. In group II (77 cases), nonorgan confinement and extraprostatic organ infiltration (tumor classification greater than or equal to pT3b) were predicted from age, four histopathological variables, the preoperative PSA level, and the total prostate volume estimated by preoperative ultrasonography. Learning vector quantization (LVQ) networks were applied for this purpose and compared to multilayer perceptrons (MLP) and linear discriminant analysis (LDA). Results: Nonorgan confinement could be predicted correctly in 90% of newly presented cases from sextant biopsy histopathology alone. A similar accuracy of predicting nonorgan confinement (83%) was obtained by combining preoperative biopsy histology with clinical data. Extraprostatic organ infiltration could be predicted correctly in 82%. The best results were obtained by LVQ networks, followed by MLP networks and LDA. Conclusion: The postoperative tumor stage of prostatic cancer can be estimated with high accuracy, sensitivity and specificity from preoperative routine parameters using artificial neural networks, especially LVQ networks. The results suggest that this methodology should be evaluated in a larger prospective study 6.2.4. Outras Aplicações
Reverse Software Engineering Applications of.. - Whittington.. An Efficient Multiprocessor Mapping Algorithm for the.. - Whittington, Spracklen The Design and Evolution of Modular Neural Network Architectures - Happel, Murre (1994) The Application of Neural Networks to Tactical and Sensor .. - Whittington, Spracklen (1989) ANDS: A Second Generation Neural Network Development System - Whittington, Spracklen (1993) An Experimental Neural Network KBS Using An.. - Whittington, Spracklen (1990)
Self-Organizing Maps - Kohonen - 1995 Book Details from Amazon or Barnes & Noble Self-organized formation of topologically correct feature ma.. - Kohonen - 1982 LVQ PAK: The Learning Vector Quantization Program Package - Kohonen, Hynninen et al. - 1995 A single tree simulator for uneven-aged mixed species stands - Hasenauer - 1994 Ein Einzelbaumwachstumssimulator fur ungleichaltrige Fichten.. - Hasenauer - 1994 Modeling survival of loblolly pine trees in thinned and unth.. - Avila, Burkhart - 1992 FOREST: A computer model for simulating the growth reproduct.. - Ek, Monserud - 1974 A logistic model of mortality in thinned and unthinned mixed.. - Jr - 1986 Forest Tree Morality Simulation in Uneven-Aged Stands Using .. - Hasenauer, Merkl - 1997
Neural Network Technology to Support View Integration - Ellmer, Huemer, Merkl, Pernul (1995) Lessons Learned in Text Document Classification - Merkl (1997) Security For Next Generation Hypertext Systems - Merkl, Pernul (1994)
Self-Organizing Maps - Kohonen - 1995 Book Details from Amazon or Barnes & Noble Self-organized formation of topologically correct feature ma.. - Kohonen - 1982 LVQ PAK: The Learning Vector Quantization Program Package - Kohonen, Hynninen et al. - 1995 A single tree simulator for uneven-aged mixed species stands - Hasenauer - 1994 Ein Einzelbaumwachstumssimulator fur ungleichaltrige Fichten.. - Hasenauer - 1994 Modeling survival of loblolly pine trees in thinned and unth.. - Avila, Burkhart - 1992 FOREST: A computer model for simulating the growth reproduct.. - Ek, Monserud - 1974 A logistic model of mortality in thinned and unthinned mixed.. - Jr - 1986 Forest Tree Morality Simulation in Uneven-Aged Stands Using .. - Hasenauer, Merkl - 1997
Neural Network Technology to Support View Integration - Ellmer, Huemer, Merkl, Pernul (1995) Lessons Learned in Text Document Classification - Merkl (1997) Security For Next Generation Hypertext Systems - Merkl, Pernul (1994)
Abstract: . In this paper several neural network classification algorithms have been applied to a real-world data case of electron microscopy image classification in which it was known a priori the existence of two differentiated views of the same specimen. Using several labeled sets as a reference, the parameters and architecture of the classifier (both LVQ trained codebooks and BP trained neural-nets) were optimized using a genetic algorithm. The automatic process of training and optimization is...
Automatic Classification of Biological Particles From.. - Merelo And (1998) G-Prop: Global Optimization of Multilayer Perceptrons .. - Castillo, Merelo.. (2000) Evolving Multilayer Perceptrons - Castillo, Carpio, Merelo, Prieto.. Evolving Objects - Merelo, Carpio, Castillo, Rivas.. (2000) Optimization of classifiers using genetic algorithms - Merelo, Prieto, Morán (1996) G-Prop-II: Global Optimization of Multilayer.. - Castillo, Rivas.. (1999) G-Prop-III: Global Optimization of Multilayer.. - Castillo, Merelo, .. Domain-Specific Languages: from Design to Implementation .. - Thibault, Marlet, Consel (1999) Flexible and Efficient Sharing of Protected Abstractions - Candea (1998) Parser Evaluation: a Survey and a New Proposal - Carroll, Briscoe, Sanfilippo (1998)
The self-organizing map - Kohonen - 1990 Book Details from Amazon or Barnes & Noble The self-organizing map - Kohonen - 1990 Book Details from Amazon or Barnes & Noble Species adaptation genetic algorithms: a basis for a continu.. - Harvey - 1991 Towards Designing Artificial Neural Networks by Evolution - Yao, Liu - 1998 GAL: Networks that grow when they learn and shrink when they.. - Alpaydim - 1991 Prop: Global Optimization of Multilayer Perceptrons using GA.. - Castillo, Gonz'alez et al. - 1998 A connectionist algorithm for genetic search - Ackley - 1985 SA-Prop: Optimization of Multilayer Perceptron Parameters us.. - Castillo, Gonz'alez et al. - 1998 A vector quantization algorithm based on genetic algorithms .. - Monte, Hidalgo et al. - 1993 a combination of genetic algorithms and lvq - Merelo, Prieto - 1995 Six molecules of sv40 large T antigen assemble in a propelle.. - Martin, Gruss et al. - 1997 Automatic classification of biological particles from electr.. - Merelo, Prieto et al. - 1998 Multi-objective learning via genetic algorithms - Schaffer, Grefenstette - 1985 Constructive design of LVQ and DSM classifiers - Perez, Vidal - 1993 Pattern recognition and classification of images of biologic.. - Marabini, Carazo - 1994 Analysis of structural variability within two-dimensional bi.. - Fern'andez, Carazo - 1996 Identification of multiple analytes using an optical sensor .. - Johnson, Sutter et al. - 1997 Genetic algorithms for codebook generation in vq - Kaukoranta, Frnti et al. - 1997
Automatic Classification of Biological Particles From.. - Merelo And (1998) MasterMind - Using Gas Genetic Algorithms for Optimum Designing of Fuzzy.. - Rojas, Merelo, Pomares..
Abstract: . Automatic classification of transmission electron-microscopy images is an important step in the complex task of determining the structure of biologial macromolecules. The process of 3D reconstruction from a set of such images implies their previous classification into homogeneous image classes. In general, different classes may represent either distinct biochemical specimens or from different directions of an otherwise homogenous specimen. In this paper a neural network classification...
SA-Prop: Optimization of Multilayer Perceptron.. - Castillo.. (1998) G-Prop-II: Global Optimization of Multilayer.. - Castillo, Rivas.. (1999) Improved automatic classification of biological.. - Merelo, Prieto..
Optimization of classifiers using genetic algorithms - Merelo, Prieto, Morán (1996) Spin Images and Neural Networks for Efficient.. - de Alarcón.. (2002) Design of neural classifiers using variable-length.. - Merelo, Prieto.. (1995) An individual-based model that reproduces natural.. - Herráiz, Merelo.. Prop: Global Optimization of Multilayer Perceptrons using GAs - Castillo, Gonz'alez et al. - 1998 Pattern recognition via linear programming: Theory and application to medical di.. - Mangasarian, Setiono et al. - 1990 A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorith.. - Riedmiller, Braun – 1993 An Indexed Bibliography of Genetic Algorithms and Neural.. - Jarmo T. Alander (2001) Evolutionary Design of Neural Architectures - A.. - Balakrishnan, Honavar (1995) G-Prop: Global Optimization of Multilayer Perceptrons .. - Castillo, Merelo.. (2000) Edge Detection Techniques - An Overview - Ziou, Tabbone (1998) Contour fitting using stochastic and probabilistic relaxation .. - Daniel Rueckert Reducing the Variability in Product Density Kernel Estimators for .. - Collins
The self-organizing map - Kohonen - 1990 Book Details from Amazon or Barnes & Noble An introduction to the bootstrap - Efron, Tibshirani - 1993 GAL: Networks that grow when they learn and shrink when they.. - Alpaydim - 1991 A vector quantization algorithm based on genetic algorithms .. - Monte, Hidalgo et al. - 1993 a combination of genetic algorithms and lvq - Merelo, Prieto - 1995 Six molecules of sv40 large T antigen assemble in a propelle.. - Martin, Gruss et al. - 1997 Systems control with the genetic algorithm and the nearest n.. - Huang - 1992 Constructive design of lvq and dsm classifiers - P'erez, Vida - 1993 Hybridizing the genetic aglorithm and the k nearest neighbor.. - James, Kelly et al. - 1991 Pattern recognition and classification of images of biologic.. - Marabini, Carazo - 1994 Analysis of structural variability within two-dimensional bi.. - Fern'andez, Carazo - 1996 A GA-optimized neural network for classification of biologic.. - Merelo, Prieto et al. - 1997 Markov chain monte carlo and its application - Brooks - 1998
MasterMind - Using Gas Genetic Algorithms for Optimum Designing of Fuzzy.. - Rojas, Merelo, Pomares.. Designing Advertising Strategies using a Genetic Algorithm - Merelo Prieto 6.3. Learning Vector Quantization em Economia
The SOM in data mining: analysis of world pulp and paper technology - Vesanto (1997) Feature selection for Neural Networks through Functional.. - Haring, Kok, van Wezel Feature selection through Functional Links with.. - Haring, Kok, van Wezel A Comparative Study of Neural Networks in Bankruptcy Prediction - Back, Oosterom, al. (1994) Bankruptcy prediction models: probabilistic neural networks.. - Tyree, Long Predicting the Stock Market - Hellström, Holmström (1998) Classification of complex simple Lie algebras via projective .. - Landsberg, Manivel (1999) Estimating Relevant Input Dimensions for Self-organizing.. - Hammer, Villmann (2001) Remote Sensing Image Classification For Forestry Using Mrf.. - Yamazaki, Kansai
Structures of welfare and poverty in the world discovered by.. - Kaski, Kohonen - 1995 A comparative study of neural networks in bankruptcy predict.. - Back, Oosterom et al. - 1994 Analyzing nancial statements with the self-organizing map - Kiviluoto - 1996 analysis: Self-organizing neural networks for nancial diagno.. - Serrano-Cinca - 1994
The SOM in data mining: analysis of world pulp and paper technology - Vesanto (1997) Feature selection for Neural Networks through Functional.. - Haring, Kok, van Wezel Feature selection through Functional Links with.. - Haring, Kok, van Wezel Neural Networks: an Exploratory Data Analysis of Logistics.. - Wilppu SOM PAK: The Self-Organizing Map Program Package - Kohonen, Hynninen, Kangas.. (1996) Data exploration using self-organizing maps - Kaski (1997) LVQ PAK: The Learning Vector Quantization Program Package - Kohonen, Hynninen.. (1996) Classification of complex simple Lie algebras via projective .. - Landsberg, Manivel (1999) Estimating Relevant Input Dimensions for Self-organizing.. - Hammer, Villmann (2001) Remote Sensing Image Classification For Forestry Using Mrf.. - Yamazaki, Kansai A Novel Method of Protein Secondary Structure - Prediction With High (2001) A scalable Processor Array for Selforganizing Feature Maps - Rüping, Rückert Field Strength Prediction by Ray-Tracing for Adaptive.. - Fritsch, Tutschku.. (1995) A hardware supported system for Kohonen's Selforganizing Map - Thole, Speckmann.. (1993) S-Map: A network with a simple self-organization algorithm.. - Kiviluoto, Oja Self-organizing systems research in the social sciences.. - Contractor A Comparative Study of Neural Networks in Bankruptcy Prediction - Back, Oosterom, al. (1994) Bankruptcy prediction models: probabilistic neural networks.. - Tyree, Long Predicting the Stock Market - Hellström, Holmström (1998) Neural Networks in Economics: Background.. - Herbrich.. (1998) Analysing Bankruptcy Data with Multiple Methods - Hekanaho, Back, Sere, Laitinen (1998) Choosing the Best Set of Bankruptcy Predictors - Back, Sere, al. (1995) Neural Networks For Technical Analysis: A Study On KLCI - Yao, TAN, POH (1999) Choosing Bankruptcy Predictors Using Discriminant Analysis, .. - Back, Laitinen, al. Bankruptcy Prediction Using Artificial Neural Systems - Dorsey, Edmister, Johnson Evolving Artificial Neural Networks - Yao (1999) Neural Networks for Time Series Processing - Dorffner (1996) Predictable Patterns in Stock Returns - Hellström, Holmström (1998) Neural Networks Versus Logistic Regression In Financial.. - Tucker Neural networks in business: techniques and applications for.. - Smith, Gupta (2000) Statistical Pattern Recognition: A Review - Jain, Duin, Mao (1999) A comparative study on feedforward and recurrent neural.. - Hallas, Dorffner (1998) Rough Set Based Classification Methods and Extended.. - Deogun, Raghavan, al. (1994) Black-Box Modeling with State-Space Neural Networks - Rivals, Personnaz (1996) Evaluating Pruning Methods - Thimm, Fiesler (1995) A fuzzy rule based learning method for corporate.. - Thomaidis, Gounias.. 6.4. Learning Vector Quantization em outras áreas 6.4.1. Física: Ótica e tratamento de imagens
Citado por: Modeling Object Classes In Aerial Images Using Hidden - Markov Models Shawn Modeling Object Classes in Aerial Images Using Texture Motifs - Sitaram Bhagavathy Shawn (2002) Segmentation based Image Retrieval - Siebert (1998) Modeling Object Classes In Aerial Images Using Hidden - Markov Models Shawn Modeling Object Classes in Aerial Images Using Texture Motifs - Sitaram Bhagavathy Shawn (2002) Segmentation based Image Retrieval - Siebert (1998)
An Analytical Study on Image Databases - Fang A Pattern Thesaurus for Browsing Large Aerial Photographs - Ma And Manjunath (1996) Image Segmentation Using Curve Evolution And Region Stability - Baris Sumengen Manjunath A Texture Thesaurus for Browsing Large Aerial Photographs - Wei-Ying Ma And (1997) A texture descriptor for browsing and similarity retrieval - Manjunath, Wu, Newsam Pattern Recognition and Image Analysis - Gose, Johnsonbaugh et al. - 1996 Texture features for browsing and retrieval of image data - Manjunath, Ma - 1996 Photobook: Tools for Content-based Manipulation of Image Databases - Pentland, Picard et al. – 1994 Image Retrieval: Past, Present, And Future - Rui, Huang, Chang (1997) Image Retrieval: Current Techniques, Promising Directions.. - Rui, Huang, Chang (1999) Relevance Feedback Techniques in Interactive Content-Based .. - Rui, Huang, Mehrotra Image Retrieval using Color and Shape - Jain, Vailaya (1996) Automatic Feature Extraction and Indexing for Content-Based .. - Chang, Smith, Wang (1995) CANDID: Comparison Algorithm for Navigating Digital Image.. - Kelly, Cannon (1994)
The self-organizing map - Kohonen - 1990 Book Details from Amazon or Barnes & Noble Texture features for browsing and retrieval of image data - Manjunath, Ma - 1996 Texture features and learning similarity - Ma, Manjunath - 1996 Image indexing using a texture dictionary - Ma, Manjunath - 1995 Adaptive filtering and indexing for image databases - Alexandrov, Ma et al. - 1995 A digital library for geograpgically referenced materials - Smith - 1996 A multiresolution approach to image segmentation based on te.. - Ma, Manjunath
of solutions to this including the Learning Vector Quantization (LVQ) algorithms [9] To overcome some www.erg.abdn.ac.uk/public_html/publications/docs/gw-90-iee-nnet.ps Abstract: This paper examines the potential applications of artificial neural network based technology to industrial spectral analysis and the potential problems for such systems. The Adaptive Kohonen Feature Map model is introduced and described. The use of artificial neural network based systems are contrasted with a rule-based (expert system) approach for spectral recognition. An experimental neural network based spectral recognition system is described. 1 Introduction The industrial applications of...
Reverse Software Engineering Applications of.. - Whittington.. An Efficient Multiprocessor Mapping Algorithm for the.. - Whittington, Spracklen The Design and Evolution of Modular Neural Network Architectures - Happel, Murre (1994) The Application of Neural Networks to Tactical and Sensor .. - Whittington, Spracklen (1989) ANDS: A Second Generation Neural Network Development System - Whittington, Spracklen (1993) An Experimental Neural Network KBS Using An.. - Whittington, Spracklen (1990)
Parallel Distributed Processing: Explorations in the Microst.. - Rumelhart, McClelland - 1987 Book Details from Amazon or Barnes & Noble Statistical pattern recognition with neural networks: Benchm.. - Kohonen - 1988 Learning to tell two spirals apart - Lang, Witbrock - 1988 Self-organizing semantic maps - Ritter, Kohonen - 1989 Competitive Learning: From Interactive Activation to Adaptiv.. - Grossberg - 1988 Cluster Analysis Algorithms for data reduction and classific.. - Spath - 1980 Data representations in neural nets: an empirical study - Hancock - 1988 Connectionist Models Summer School - the - 1988 An experimental neural network KBS using an object-oriented .. - Whittington, Spracklen - 1990 Application and Implementation of Artificial Neural Networks - Whittington - 1993 Performance analysis and application of the bidirectional as.. - Mathai, Upadhyaya - 1989 A comparison of two Artificial Intelligence techniques in th.. - Davidge - 1989
Using ToolTalk to Implement a Distributed Discrete .. - Whittington.. ANDS: A Second Generation Neural Network Development System - Whittington, Spracklen (1993) The Application of Neural Networks to Tactical and Sensor .. - Whittington, Spracklen (1989) A Comparative Study of Several Color Models for Color Image.. - Gevers, Smeulders (1996) Wavelets as chromatin texture descriptors for the.. - Wouwer, Weyn.. (2000) Image annotation based on Learning Vector Quantization and.. - Blume, Ballard (1997)
Median Radial Basis Functions Neural Network - Bors, Pitas Median Radial Basis Functions Network for Optical Flow Processing - Bors, Pitas Esprit Bra Iii Project Nat 7130 - Number March Optical Flow Estimation and Moving Object Segmentation Based on .. - Bors, Pitas Moving scene segmentation using Median Radial Basis Function.. - Bors, Pitas (1997) Object Classification in 3-D Images Using Alpha-Trimmed Mean.. - Bors, Pitas
the statistical analysis of dirty pictures - Besag - 1986 Bayesian estimation of motion vector fields - Konrad, Dubois - 1992 Pattern Recognition: Statistical - Schalkoff - 1992 Multimodal estimation of discontinuous optical flow using Ma.. - Heitz, Bouthemy - 1993 An algorithm for simultaneous motion estimation and scene se.. - Chan, Sezan et al. - 1994 Minimal topology for a radial basis functions neural network.. - Bor, Gabbouj - 1994 Robust estimation of radial basis functions - Bor, Pitas - 1994 Applications of Communications Theory - Netravali, Haskell et al. - 1988 Median radial basis functions network for optical flow proce.. - Bor, Pitas - 1995
Robust Estimation for Radial Basis Functions - Bors, Pitas Shape-Based Interpolation Using Morphological Morphing - Bors, Kechagias, Pitas Robust RBF Networks - Bors, Pitas
|