A learning algorithm for continually running fully recurrent neural networks

Authors:
Ronald J. Williams;David Zipser
Affiliations:
College of Computer Science, Northeastern University, Boston, MA 02115, USA;Institute for Cognitive Science, University of California, La Jolla, CA 92093, USA
Venue:
Neural Computation
Year:
1989

Citing 4
Cited 161

A self-optimizing, nonsymmetrical neural net for content addressable memory and pattern recognition

Physica D
Dynamics and architecture for neural computation

Journal of Complexity - Special Issue on Neural Computation
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning state space trajectories in recurrent neural networks

Neural Computation

Original Contribution: The gamma model-A new neural model for temporal processing

Neural Networks
Original Contribution: Hamiltonian dynamics of neural networks

Neural Networks
Original Contribution: Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks
Original Contribution: Subconnection neural network for event-driven temporal sequence processing

Neural Networks
Learning fixed point patterns by recurrent networks

Journal of Computer and System Sciences
Modeling a Refrigeration System Using Recurrent Neural Networks

Proceedings of the 6th International Conference on Computational Intelligence, Theory and Applications: Fuzzy Days
Online Symbolic-Sequence Prediction with Discrete-Time Recurrent Neural Networks

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
On Linear Separability of Sequences and Structures

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Improving Long-Term Online Prediction with Decoupled Extended Kalman Filters

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Learning from Chaos: A Model of Dynamical Perception

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Inductive Bias in Recurrent Neural Networks

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Multilevel Genetic Algorithm for the Complete Development of ANN

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Speech Recognition Using Fuzzy Second-Order Recurrent Neural Networks

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Localization of Sound Sources by Means of Recurrent Neural Networks

RSCTC '00 Revised Papers from the Second International Conference on Rough Sets and Current Trends in Computing
Time in Connectionist Models

Sequence Learning - Paradigms, Algorithms, and Applications
2005 Special issue: Recursive principal components analysis

Neural Networks - Special issue on neural networks and kernel methods for structured domains
Propagation and control of stochastic signals through universal learning networks

Neural Networks
An adaptive recurrent fuzzy system for nonlinear identification

Applied Soft Computing
Organization of the state space of a simple recurrent network before and after training on recursive linguistic structures

Neural Networks
A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation

Neurocomputing
A new recurrent neurofuzzy network for identification of dynamic systems

Fuzzy Sets and Systems
Adaptive control of a nonlinear dc motor drive using recurrent neural networks

Applied Soft Computing
Locally recurrent neural networks for wind speed prediction using spatial correlation

Information Sciences: an International Journal
A new boosting algorithm for improved time-series forecasting with recurrent neural networks

Information Fusion
Birdsong recognition using prediction-based recurrent neural fuzzy networks

Neurocomputing
Recurrent fuzzy network design using hybrid evolutionary learning algorithms

Neurocomputing
An augmented CRTRL for complex-valued recurrent neural networks

Neural Networks
A subgrouping strategy that reduces complexity and speeds up learning in recurrent networks

Neural Computation
Review:

Neural Computation
Learning state space trajectories in recurrent neural networks

Neural Computation
Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot Experiment

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation
Diagrammatic derivation of gradient algorithms for neural networks

Neural Computation
First-order recurrent neural networks and deterministic finite state automata

Neural Computation
Integration and differentiation in dynamic recurrent neural networks

Neural Computation
Alopex: A correlation-based learning algorithm for feedforward and recurrent neural networks

Neural Computation
Recurrent and feedforward polynomial modeling of coupled time series

Neural Computation
Dynamic Ridge Polynomial Neural Networks for multi-step financial time-series prediction

International Journal of Intelligent Systems Technologies and Applications
2008 Special Issue: Achieving "organic compositionality" through self-organization: Reviews on brain-inspired robotics experiments

Neural Networks
Financial time series prediction using polynomial pipelined neural networks

Expert Systems with Applications: An International Journal
Analysis and comparison of aircraft landing control using recurrent neural networks and genetic algorithms approaches

Neurocomputing
Long-term time series prediction with the NARX network: An empirical evaluation

Neurocomputing
Reinforcement learning of recurrent neural network for temporal coding

Neurocomputing
Dynamic Ridge Polynomial Neural Networks in Exchange Rates Time Series Forecasting

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Convergence of Gradient Descent Algorithm for a Recurrent Neuron

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
A Testbed for Neural-Network Models Capable of Integrating Information in Time

Anticipatory Behavior in Adaptive Learning Systems
Integrating Domain Knowledge in Equation Discovery

Computational Discovery of Scientific Knowledge
Policy Gradient Critics

ECML '07 Proceedings of the 18th European conference on Machine Learning
Practical Recurrent Learning (PRL) in the Discrete Time Domain

Neural Information Processing
Parallel Realisation of the Recurrent RTRN Neural Network Learning

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Hybrid Evolution of Heterogeneous Neural Networks

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
A Neuro Fuzzy Approach for Handling Structured Data

SUM '08 Proceedings of the 2nd international conference on Scalable Uncertainty Management
2008 Special Issue: The Emergent neural modeling system

Neural Networks
Study of multi-branch structure of Universal Learning Networks

Applied Soft Computing
Narrowband interference rejection in GPS receiver using adaptive lattice predictor

WSEAS TRANSACTIONS on SYSTEMS
Extracting symbolic knowledge from recurrent neural networks---A fuzzy logic approach

Fuzzy Sets and Systems
Reliability forecasting by recurrent Support Vector Regression

International Journal of Artificial Intelligence and Soft Computing
Physical time series prediction using Recurrent Pi-Sigma Neural Networks

International Journal of Artificial Intelligence and Soft Computing
A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance

Neural Networks
Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods

Applied Soft Computing
Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter

Fuzzy Sets and Systems
Group-Linking Method: A Unified Benchmark for Machine Learning with Recurrent Neural Network

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Structural Properties of Recurrent Neural Networks

Neural Processing Letters
AMA-MOSAICI: An automatic module assigning hierarchical structure to control human motion based on movement decomposition

Neurocomputing
Non-stationary and stationary prediction of financial time series using dynamic ridge polynomial neural network

Neurocomputing
Stable adaptive control with recurrent neural networks for square MIMO non-linear systems

Engineering Applications of Artificial Intelligence
Proto-predictive representation of states with simple recurrent temporal-difference networks

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Inducing hierarchical process models in dynamic domains

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Diffusion of context and credit information in Markovian models

Journal of Artificial Intelligence Research
Learning to count by think aloud imitation

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Recurrent neuro-fuzzy system for fault detection and isolation in nuclear reactors

Advanced Engineering Informatics
Learning iterative image reconstruction

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Evolino: hybrid neuroevolution / optimal linear search for sequence learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
2009 Special Issue: Mapping broadband electrocorticographic recordings to two-dimensional hand trajectories in humans

Neural Networks
Spurious valleys in the error surface of recurrent networks: analysis and avoidance

IEEE Transactions on Neural Networks
A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network

Neural Networks
Training Recurrent Neural Network Using Multistream Extended Kalman Filter on Multicore Processor and Cuda Enabled Graphic Processor Unit

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Modeling Dst with Recurrent EM Neural Networks

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Identification of a class of nonlinear systems by a continuous-time recurrent neurofuzzy network

ACC'09 Proceedings of the 2009 conference on American Control Conference
Echo-state-network-based real-time wind speed estimation for wind power generation

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Long-term prediction of time series by combining direct and MIMO strategies

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A robust extended Elman backpropagation algorithm

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
High order neural networks for wind speed time series prediction

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Bounded-time system identification under neuro-sliding training

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Temporal semantics: an adaptive resonance theory approach

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Overhead conductor thermal dynamics identification by using echo state networks

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A high-order recurrent neuro-fuzzy system with internal dynamics: Application to the adaptive noise cancellation

Fuzzy Sets and Systems
Controller for TORCS created by imitation

CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Levenberg-Marquardt-based OBS algorithm using adaptive pruning interval for system identification with dynamic neural networks

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
A new method in modeling central pattern generators to control quadruped walking robots

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Pipelined Chebyshev functional link artificial recurrent neural network for nonlinear adaptive filter

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Letters: Efficient online recurrent connectionist learning with the ensemble Kalman filter

Neurocomputing
Characterization of training errors in supervised learning using gradient-based rules

Neural Networks
Autonomous learning algorithm for fully connected recurrent networks

Neurocomputing
Roles of the prefrontal neurons in delayed matching-to-category task: a modeling study

Neurocomputing
Locally recurrent neural networks for long-term wind speed and power prediction

Neurocomputing
A multiobjective genetic algorithm for obtaining the optimal size of a recurrent neural network for grammatical inference

Pattern Recognition
A comparison of selected training algorithms for recurrent neural networks

PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Selective noise cancellation using independent component analysis

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Recursive Bayesian recurrent neural networks for time-series modeling

IEEE Transactions on Neural Networks
Learning to imitate stochastic time series in a compositional way by chaos

Neural Networks
Comparison of echo state networks with simple recurrent networks and variable-length Markov models on symbolic sequences

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Optimal brain surgeon for general dynamic neural networks

EPIA'07 Proceedings of the aritficial intelligence 13th Portuguese conference on Progress in artificial intelligence
Multiple-output modeling for multi-step-ahead time series forecasting

Neurocomputing
On the weight convergence of Elman networks

IEEE Transactions on Neural Networks
Black-box identification of a class of nonlinear systems by a recurrent neurofuzzy network

IEEE Transactions on Neural Networks
SMARTDIAB: a communication and information technology approach for the intelligent monitoring, management and follow-up of type 1 diabetes patients

IEEE Transactions on Information Technology in Biomedicine - Special section on new and emerging technologies in bioinformatics and bioengineering
Constructive training of recurrent neural networks using hybrid optimization

Neurocomputing
Functional identification of biological neural networks using reservoir adaptation for point processes

Journal of Computational Neuroscience
Nonlinear adaptive equalizer using a pipelined decision feedback recurrent neural network in communication systems

IEEE Transactions on Communications
Convergence analysis of three classes of split-complex gradient algorithms for complex-valued recurrent neural networks

Neural Computation
Information processing in complex networks

IEEE Circuits and Systems Magazine - Special issue on complex networks applications in circuits and systems
Identification of finite state automata with a class of recurrent neural networks

IEEE Transactions on Neural Networks
Parallel realisation of the recurrent Elman neural network learning

ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
An MDL-based Hammerstein recurrent neural network for control applications

Neurocomputing
Dynamic Ridge Polynomial Neural Network: Forecasting the univariate non-stationary and stationary trading signals

Expert Systems with Applications: An International Journal
Turbulence encountered landing control using hybrid intelligent system

ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Pipelined functional link artificial recurrent neural network with the decision feedback structure for nonlinear channel equalization

Information Sciences: an International Journal
Time-dependent series variance estimation via recurrent neural networks

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Adaptive recurrent neuro-fuzzy networks based on Takagi-Sugeno inference for nonlinear identification in mechatronic systems

KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part I
On the learning of ESN linear readouts

CAEPIA'11 Proceedings of the 14th international conference on Advances in artificial intelligence: spanish association for artificial intelligence
A generalized LSTM-like training algorithm for second-order recurrent neural networks

Neural Networks
Original article: Learning over sets with Recurrent Neural Networks: An empirical categorization of aggregation functions

Mathematics and Computers in Simulation
A new recurrent neurofuzzy network for identification of dynamic systems

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Local recurrent sigmoidal-wavelet neurons in feed-forward neural network for forecasting of dynamic systems: Theory

Applied Soft Computing
Cooperative motor learning model for cerebellar control of balance and locomotion

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
The study of the robust learning algorithm for neural networks

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part II
A hybrid neuro-fuzzy approach for spinal force evaluation in manual materials handling tasks

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part III
An evolved recurrent neural network and its application

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Recurrent support vector machines in reliability prediction

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
A scheduling method of data transmission in the internet communication by recurrent neural network

KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
An efficient hybrid approach for online recognition of handwritten symbols

MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence
Recognizing connected digit strings using neural networks

TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
Imitating others by composition of primitive actions: A neuro-dynamic model

Robotics and Autonomous Systems
Polynomial pipelined neural network and its application to financial time series prediction

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Goal-oriented behavior generation for visually-guided manipulation task

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Dyna: extending datalog for modern AI

Datalog'10 Proceedings of the First international conference on Datalog Reloaded
Brief State estimation of continuous-time radial basis function networks

Automatica (Journal of IFAC)
Book review: Neural and adaptive systems: fundamentals through simulations

Automatica (Journal of IFAC)
Decentralized discrete-time neural control for a Quanser 2-DOF helicopter

Applied Soft Computing
2012 Special Issue: An extended echo state network using Volterra filtering and principal component analysis

Neural Networks
Identification of nonlinear dynamics using a general spatio-temporal network

Mathematical and Computer Modelling: An International Journal
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review
Parallel realisation of the recurrent multi layer perceptron learning

ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
An innovative hybrid neuro-wavelet method for reconstruction of missing data in astronomical photometric surveys

ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
Recognition of assamese phonemes using RNN based recognizer

CMMR'11 Proceedings of the 8th international conference on Speech, Sound and Music Processing: embracing research in India
Learning in fully recurrent neural networks by approaching tangent planes to constraint surfaces

Neural Networks
Adaptive control design using stability analysis and tracking errors dynamics for nonlinear square MIMO systems

Engineering Applications of Artificial Intelligence
Minimum-risk training of approximate CRF-based NLP systems

NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Dynamic neural cortical ensembles model

Optical Memory and Neural Networks
A context layered locally recurrent neural network for dynamic system identification

Engineering Applications of Artificial Intelligence
RETRACTED: Hopf bifurcation stability in Hopfield neural networks

Neural Networks
Discrete-time inverse optimal neural control for synchronous generators

Engineering Applications of Artificial Intelligence
Potentials of Quadratic Neural Unit for Applications

International Journal of Software Science and Computational Intelligence
A bio-inspired modular hierarchical structure to plan the sit-to-stand transfer under varying environmental conditions

Neurocomputing
Dynamical genetic programming in xcsf

Evolutionary Computation
Selective Recurrent Neural Network

Neural Processing Letters
Stability and Hopf bifurcation in an unidirectional ring of n neurons with distributed delays

Neurocomputing
Time-dependent series variance learning with recurrent mixture density networks

Neurocomputing
A biological gradient descent for prediction through a combination of stdp and homeostatic plasticity

Neural Computation
Goal-oriented behavior sequence generation based on semantic commands using multiple timescales recurrent neural network with initial state correction

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks. These algorithms have (1) the advantage that they do not require a precisely defined training interval, operating while the network runs; and (2) the disadvantage that they require nonlocal communication in the network being trained and are computationally expensive. These algorithms allow networks having recurrent connections to learn complex tasks that require the retention of information over time periods having either fixed or indefinite length.