Revisão bibliográfica redes neurais recorrentes



Download 406.67 Kb.
Page9/10
Date17.05.2017
Size406.67 Kb.
#18493
1   2   3   4   5   6   7   8   9   10

IJCNN International Joint Conference on Neural Networks, Beijing, China, Vol. 1, Publishing House of Electronics Industry, 1992.

Palavras-chave: learning, transducer, finite state



297 - Learning Internal Representations by Error Propagation

D. E. Rumelhart and G. E. Hinton and R. J. Williams

Parallel Distributed Processing, MIT Press, 1986.

Palavras-chave: learning, error, error prpagation

298 -Learning Large DeBruijn Automata with Feed-Forward Neural Networks

D. S. Clouse and C. L. Giles and B. G. Horne and G. W. Cottrell

Technical Report, Computer Science and Engineering, University of California at San Diego, Number CS94-398, 1994.

Palavras-chave: learning, automata feed forward neural net

299 -Learning long-term dependencies is not as difficult with NARX recurrent neural networks

T. Lin and B. G. Horne and P. Tino and C. L. Giles

Technical Report, Institute for Advanced Computer Studies, University of Maryland, Number UMIACS-TR-95-78 and CS-TR-3500, 1995.

Palavras-chave: learning, NARX, dependencies

300 - Learning Long-Term Dependencies with Gradient Descent is Difficult

Yoshua Bengio and P. Simard and P. Frasconi

IEEE Transactions on Neural Networks, 5(2), pp. 157-166, 1994.

Palavras-chave: learning, gradiend descent, training

301 -Learning Recursive Distributed Representations for Holistic Computation

Lonnie Chrisman

Connection Science, 3(4), pp. 345-366, 1991.

Palavras-chave: learning, recursive, holistic computations

302 -Learning Sequential Structure with the Real-time Recurrent Learning Algorithm

Anthony W. Smith and David Zipster

International Journal of Neural Systems, 1(2), pp. 125-131, 1989.

Palavras-chave: learning, sequential structure, real time learning

303 -Learning state space trajectories in recurrent neural networks

Barak Pearlmutter

Neural Computation, 1(2), pp. 263-269, 1989.

Palavras-chave: learning, state space trajectories

304 -Learning System Architetures Composed of Multiple Learning Modules

D. L. Reilly and C. Scofield and C. Elbaum and L. N. Cooper

Proceedings of the IEEE First International Conference On Neural Networks, 1987.

Palavras-chave: learning, architetures, multiple learning

305 -Learning the Past Tense of English Verbs using Recurrent Neural Networks

L. R. Leerink and M. Jabri

Australian Conference on Neural Networks, pp. 222-226, Australian National University, 1996.

Palavras-chave: learning, english, verbs, grammar

306 - Learning with product units

L. R. Leerink and C. L. Giles and B. G. Horne and M. A. Jabri

Advances in Neural Information Processing Systems 7, MIT Press.

Palavras-chave: learning, information

307 -Learning, Representation, and Synthesis of Automata and Sequential Machines in Recurrent Neural Networks

C. Lee Giles

AAAI-96 Fall Symposium Series Workshop on Learning Complex Behaviors in Adaptive Intelligent Systems, pp. 132-139, 1996.

Palavras-chave: learning, representation, syntesis automata

308 -Long Short Term Memory

S . Hochreiter and J. Schmidhuber

Neural Computation.

Palavras-chave: memory,



309 -Long Term Memory Storage Capacity of Multiconnected Neural Networks

P. Peretto and J. J. Niez

Biological Cybernetics, Vol. 54, p. 53, 1986.

Palavras-chave: memory, storage, multiconnection

310 -Learning the Past Tense of English Verbs using Recurrent Neural Networks

L. R. Leerink and M. Jabri

Australian Conference on Neural Networks, pp. 222-226, Australia National University, 1996.

Palavras-chave: learning, english, grammar

311 -Learning, Representation, and Synthesis of Automata and Sequential Machines in Recurrent Neural Networks

C. Lee Giles

AAAI-96 Fall Symposium Series Workshop on Learning Complex Behaviors in Adaptive Intelligent Systems, pp. 132-139, 1996.

Palavras-chave: learning, sntesis, sequntial machines

312 -Learning long-term dependencies is not as difficult with NARX recurrent neural networks

T. Lin and B. G. Horne and P. Tino and C. L. Giles

Advances in Neural Information Processing Systems 8, p. 577, MIT Press, 1996.

Palavras-chave: learning, NARX neural net, dependencies

313 - Learning Long-Term Dependencies with Gradient Descent is Difficult

Yoshua Bengio and P. Simard and P. Frasconi

IEEE Transactions on Neural Networks, 5(2), pp. 157-166, 1994.

Palavras-chave: learning, gradient method, training

314 -Machine Learning Using a Higher Order Correlational Network

Y. C. Lee and G. Doolen and H. H. Chen and G. Z. Sun and T. Maxwell and H. Y. Lee and C. L. Giles

Physica D, Vol. 22-D, Number 1-3, pp. 276-306, 1986.

Palavras-chave: machine learning, learning,



315 -Memory Neuron Networks for Identification and Control of Dynamical Systems

P. S. Sastry and G. Santharam and K. P. Unnikrishnan

IEEE Transactions on Neural Networks, 5(2), pp. 306-319, 1994.

Palavras-chave: memory, identification, control

316 -Memory-based Reinforcement Learning: Efficient Computation with Prioritized Sweeping

A. W. Moore and C. G. Atkeson

Advances in Neural Information Processing Systems 5, pp. 263-270, Morgan Kaufmann Publishers, 1993.

Palavras-chave: memory, reinforced learning ,learning

314 - Modular Recurrent Neural Networks for Mandarin Syllable Recognition

S.-H. Chen and Y.-F. Liao

IEEE-NN, 9(6), p. 1430, November 1998.

Palavras-chave: pattern recognition, pattern, mandarin



315 -Making the World Differentiable: On Using Supervised Learning Fully Recurrent Neural Networks for Dynamic Reinforcement Learning and Planning in Non-Stationary Environments

J. H. Schmidhuber

Technical Report, Technische Universität München, 1990.

Palavras-chave: learning, planning, non stationary envirolments

316 -Natural Language Grammatical Inference: A Comparison of Recurrent Neural Networks and Machine Learning Methods

Steve Lawrence and Sandiway Fong and C. Lee Giles

Symbolic, Connectionist, and Statistical Approaches to Learning for Natural Language Processing, Lecture notes in AI, pp. 33-47, Springer-Verlag, 1996.

Palavras-chave: grammar, language, machine learning

317 -Neural Network Learning and Expert Systems

S. I. Gallant

MIT Press, 1993.

Palavras-chave: learning, expert systems

318 - Neural Networks for control

E. Sontag

Essays on Control: Perspectives in the Theory and its Applications, pp. 339-380, Birkhauser, 1993.

Palavras-chave: control

319 -Neural Networks with External Memory Stack that Learn Context-Free Grammars from Examples

G. Z. Sun and H. H. Chen and C. L. Giles and Y. C. Lee and D. Chen

Proceedings of the Conference on Information Science and Systems, Vol. II, p. 649, 1990.

Palavras-chave: memory, learning,



320 - Noisy Recurrent Neural Networks: The Continuous-Time Case

S. Das and O. Olurotimi

IEEE-NN, 9(5), p. 913, September 1998.

Palavras-chave: noise , recurrente

321 - Nonlinear Prediction of Speech Signals Using Memory Neuron Networks

P. Poddar and K. P. Unnikrishnan

Neural Networks for Signal Processing: Proceedings of the 1991 IEEE Workshop, pp. 395-404, IEEE Press, 1991.

Palavras-chave: nonlinear prediction, speech, memory

322 -Non-Literal Transfer of Information among Inductive Learners

L. Y. Pratt

Neural Networks: Theory and Applications II, Academic Press, 1992.

Palavras-chave: learning, indutive leaners

323 - Natural Language Grammatical Inference: A Comparison of Recurrent Neural Networks and Machine Learning Methods

Steve Lawrence and Sandiway Fong and C. Lee Giles

Symbolic, Connectionist, and Statistical Approaches to Learning for Natural Language Processing, Lecture notes in AI, pp. 33-47, Springer Verlag, 1996.

Palavras-chave: grammar, learning, training

324 - On Recurrent Neural Networks and Representing Finite State Recognizers

M. W. Goudreau and C. Lee Giles and S. T. Chakradhar and D. Chen

Proceedings of the Third International Conference on Neural Networks, May 1993.

Palavras-chave: recognizers, finite state

325 -On the Applicability of Neural Network and Machine Learning Methodologies to Natural Language Processing

S. Lawrence and S. Fong and C. L. Giles

Technical Report, Institute for Advanced Computer Studies, University of Maryland, Number UMIACS-TR-95-64 and CS-TR-3479, June 1995.

Palavras-chave: machine learning, methodologies, language

326 -On the Computational Power of Neural Nets

H. T. Siegelmann and E. D. Sontag

Proceedings of the Fifth ACM Workshop on Computational Learning Theory, pp. 440-449, ACM, 1992.

Palavras-chave: computational power, lerning

327 -On the Effect of Analog Noise in Discrete-Time Analog Computations

Wolfgang Maass and Pekka Orponen

Neural Computation, Vol. 10, pp. 1071-1095, 1998.

Palavras-chave: noise, discrete time systems

328 -On the Non-Existence of a Unversal Learning Algorithm for Recurrent Neural Networks

H. Wiklicky

Advances in Neural Information Processing Systems 6, pp. 431-436, Morgan Kaufmann, 1994.

Palavras-chave: learning,



329 -On-Line Training of Recurrent Neural Networks with Continuous Topology Adaptation

D. Obradovic

IEEE Transactions on Neural Networks, 7(1), pp. 222-228, January 1996.

Palavras-chave: trainig, learning, continuous topology adaptation

330 -On the Applicability of Neural Network and Machine Learning Methodologies to Natural Language

Steve Lawrence and C. Lee Giles and Sandiway Fong

Processing Technical Report, Institute for Advanced Computer Studies, University of Maryland, College Park MD 20742, Number UMIACS-TR-95-64 and CS-TR-3479, 1995.

Palavras-chave: learning, language , method

331 -On the Non-Existence of a Unversal Learning Algorithm for Recurrent Neural Networks

H. Wiklicky

Advances in Neural Information Processing Systems 6, pp. 431-436, Morgan Kaufmann, 1994.

Palavras-chave: learning,

332 -Properties of Neural Networks with Applications to Modelling Non-linear Dynamical Systems

S. A. Billings and H. B. Jamaluddin and S. Chen

International Journal of Control, 55(1), pp. 193-224, 1992.

Palavras-chave:non linera systems, dynamic systems, proprieties

333 -Pruning Recurrent Neural Networks for Improved Generalization Performance

C. Lee Giles and Christian W. Omlin

IEEE Transactions on Neural Networks, 5(5), pp. 848-851, September 1994.

Palavras-chave: pruning



334 Pruning Recurrent Neural Networks for Improved Generalization Performance

C. W. Omlin and C. L. Giles

Technical Report, Rensselaer Polytechnic Institute, Number TR 93-6, April 1993.

Palavras-chave: pruning

335 -Pruning Recurrent Neural Networks for Improved Generalization Performance

C. W. Omlin and C. Lee Giles

IEEE Transactions on Neural Networks, 1995.

Palavras-chave: pruning, generalization,



336 - Pruning Recurrent Neural Networks for Improved Generalization Performance

Christian W. Omlin and C. Lee Giles

Technical Report, Rensselaer Polytechnic Institute, Computer Science Department, Number 93-6, April 1993.

Palavras-chave:pruning, generalization

337 -Random DFA's can be Approximately Learned from Sparse Uniform Examples

K. J. Lang

Proceedings of the Fifth ACM Workshop on Computational Learning Theory, pp. 45-52, ACM, 1992.

Palavras-chave: learning, DFA

338 -Recurrent Networks: Second Order Properties and Pruning

M. W. Pedersen and L. K. Hansen

Advances in Neural Information Processing Systems 7, MIT Press, 1995.

Palavras-chave: pruning, second order properties

339 -Recurrent Neural Networks and Robust Time Series Prediction

Jerome T. Connor and R. Douglas Martin and L. E. Atlas

IEEE Transactions on Neural Networks, 5(2), pp. 240-254, March 1994.

Palavras-chave: time series, prediction, robust prediction

340 -Recurrent Neural Networks for Adaptive Temporal Processing

Yoshua Bengio and P. Frasconi and M. Gori and G. Soda

Proceedings of the 6th Italian Workshop on Parallel Architectures and Neural Networks WIRN93, pp. 85-117, World Scientific Pub., 1993.

Palavras-chave: adaptive systems, processing , temporal, processing

341 -Recurrent Neural Networks, Context-Free Grammars, and Evolution

John Batali

Technical Report, Department of Cognitive Science, University of California at San Diego, 1995.

Palavras-chave: grammars, evotution, free grammars

342 -Recurrent Neural Networks, Hidden Markov Models and Stochastic Grammars

G. Z. Sun and H. H. Chen and Y. C. Lee and C. L. Giles

International Joint Conference on Neural Networks, San Diego, 1990, Vol. I, pp. 729-734, IEEE Press, 1990.

Palavras-chave: markov model, grammars, stocastic grammars

343 -Refinement of Approximate Reasoning-Based Controllers By Reinforcement Learning

H. R. Berenji

Machine Learning, Proceedings of the Eighth International International Workshop, p. 475, Morgan Kaufmann Publishers, 1991.

Palavras-chave: learning, machine learning, controlers

344 -Refining Algorithms with Knowledge-Based Neural Networks: Improving the Chou-Fasman Algorithm for Protein Folding

R. Maclin and J. W. Shavlik

Computational Learning Theory and Natural Learning Systems, MIT Press, 1992.

Palavras-chave: Chou-Fasman algorithm, learning, biomedic

345 -Regression Modeling in Back-Propagation and Projection Pursuit Learning

Jen-Neng Hwang and Shyh-Rong Lay and Martin Maechler and R. Douglas Martin and James Schimert

IEEE Transactions on Neural Networks, 5(3), pp. 342-353, 1994.

Palavras-chave: regression, back propagation, learning

346 - Remembering the Past: The Role of Embedded Memory in Recurrent Neural Network Architectures

C. L. Giles and T. Lin and B. G. Horne

Neural Networks for Signal Processing VII, Proceedings of The 1997 IEEE Workshop, IEEE Press, 1997.

Palavras-chave: memory, embebed memory

347 -Representation and Learning in Recurrent Neural Network Architectures,

C. L. Giles and B. G. Horne

Proceedings of the Eighth Yale Workshop on Adaptive and Learning Systems, 1994.

Palavras-chave: learning, architeture, representation

348 -Representation of Finite State Automata in Recurrent Radial Basis Function Networks

P. Frasconi and M. Gori and M. Maggini and G. Soda

Machine Learning, Vol. 23, pp. 5-32, 1996.

Palavras-chave: finite state, automata, radial base functions

349 -Recurrent Neural Networks, Hidden Markov Models and Stochastic Grammars

G. Z. Sun and H. H. Chen and Y. C. Lee and C. Lee Giles

International Joint Conference on Neural Networks, San Diego, 1990, Vol. I, pp. 729-734, IEEE Press, 1990.

Palavras-chave: markov, grammar, stocastic models

350 -Recurrent Neural Networks and Prior Knowledge for Sequence Processing: A Constrained Nondeterminstic Approach

P. Frasconi and M. Gori and G. Soda

Knowledge-Based Systems, 8(6), pp. 313-332, 1995.

Palavras-chave: sequence processing, non deterministic, constrained

351 -Recurrent Neural Networks Can Be Trained to Be Maximum A Posteriori Probability Classifiers

S. Santini and Del A. Bimbo

Neural Networks, 8(1), pp. 25-29, 1995.

Palavras-chave: Training, probability, classifier

352 Recurrent Neural Networks Can Learn to Implement Symbol-Sensitive Counting

Paul Rodriguez and Janet Wiles

Advances in Neural Information Processing Systems, Vol. 10, The MIT Press, 1998.

Palavras-chave: symbol sensitive,



353 -Recurrent Neural Networks, Context-Free Grammars, and Evolution

John Batali

Technical Report, Department of Cognitive Science, University of California at San Diego, 1995.

Palavras-chave: grammars, evolution

354 Recurrent neural networks: A functional approach

B. G. Horne

PhD Thesis, University of New Mexico, May 1993.

Palavras-chave: recurrent net

355 -Representation of Fuzzy Finite-state Automata in Continuous Recurrent Neural Networks

C. W. Omlin and K. K. Thornber and C. L. Giles

IEEE International Conference on Neural Networks (ICNN'96), p. 1023, IEEE Press, 1996.

Palavras-chave: fuzzy, finite automata, continuous neural net.

356 -Rule Checking with Recurrent Neural Networks

C. W. Omlin and C. L. Giles

IEEE Transactions on Knowledge and Data Engineering, 1995.

Palavras-chave: control, rule checking

357 -Rule Inference for Financial Prediction using Recurrent Neural Networks

C. Lee Giles and Steve Lawrence and A. C. Tsoi

Proceedings of IEEE/IAFE Conference on Computational Intelligence for Financial Engineering (CIFEr), pp. 253-259, IEEE, 1997.

Palavras-chave: prediction, finance, rule

358 -Rule Refinement with Recurrent Neural Networks

C. L. Giles and C. W. Omlin

1993 IEEE International Conference on Neural Networks (ICNN'93), Vol. II, p. 810, IEEE Press, 1993.

Palavras-chave: rule, refinement

359 -Second Order Derivatives for Network Pruning: Optimal Brain Surgeon

Babak Hassibi and David G. Stork

Advances in Neural Information Processing Systems 5, Morgan Kaufmann Publishers, 1993.


360 - Sequence Learning with Incremental Higher-Order Neural Networks

Mark B. Ring

Technical Report, Artificial Intelligence Laboratory, University of Texas at Austin, Number AI 93-193, January 1993.

Palavras-chave: learning, higher order neural net

361 -Sequential Behavior and Learning in Evolved Dynamical Neural Networks

B. M. Yamauchi and R. D. Beer

Adaptive Behavior, 2(3), pp. 219-246, 1994.

Palavras-chave: learning, dynamic systems, sequential



Download 406.67 Kb.

Share with your friends:
1   2   3   4   5   6   7   8   9   10



The database is protected by copyright ©ininet.org 2024
send message
    Main page
national academy