Constructing deterministic finite-state automata in recurrent neural networks
Journal of the ACM (JACM)
Analysis of dynamical recognizers
Neural Computation
CHILD: A First Step Towards Continual Learning
Machine Learning - Special issue on inductive transfer
Explanation, Representation and the Dynamical Hypothesis
Minds and Machines
Efficient Algorithms for the Inference of Minimum Size DFAs
Machine Learning
Rule Revision With Recurrent Neural Networks
IEEE Transactions on Knowledge and Data Engineering
Natural Language Grammatical Inference with Recurrent Neural Networks
IEEE Transactions on Knowledge and Data Engineering
Finite-state computation in analog neural networks: steps towards biologically plausible models?
Emergent neural computational architectures based on neuroscience
On the Dynamics of Robot Exploration Learning
ECAL '99 Proceedings of the 5th European Conference on Advances in Artificial Life
Imitation and Cooperation in Coupled Dynamical Recognizers
ECAL '99 Proceedings of the 5th European Conference on Advances in Artificial Life
Finite-State Computation in Analog Neural Networks: Steps towards Biologically Plausible Models?
Emergent Neural Computational Architectures Based on Neuroscience - Towards Neuroscience-Inspired Computing
The road sign problem revisited: handling delayed response tasks with neural robot controllers
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Simulating turn-taking behaviours with coupled dynamical recognizers
ICAL 2003 Proceedings of the eighth international conference on Artificial life
Inducing grammars from sparse data sets: a survey of algorithms and results
The Journal of Machine Learning Research
Undecidability in the Imitation Game
Minds and Machines
Adaptability and diversity in simulated turn-taking behavior
Artificial Life
Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
The Applicability of Recurrent Neural Networks for Biological Sequence Analysis
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Neural Networks - 2004 Special issue: New developments in self-organizing systems
Clustering Irregular Shapes Using High-Order Neurons
Neural Computation
Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
IEEE Intelligent Systems
Adaptive Behavior in Autonomous Agents
Presence: Teleoperators and Virtual Environments
Acquiring a Functionally Compositional System of Goal-Directed Actions of a Simulated Agent
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Associative Learning on a Continuum in Evolved Dynamical Neural Networks
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Group-Linking Method: A Unified Benchmark for Machine Learning with Recurrent Neural Network
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Self-organization of symbolic processes through interaction with the physical world
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
A model for hormonal modulation of learning
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
A dynamical systems perspective on agent-environment interaction
Artificial Intelligence
Spatio-temporal memories for machine learning: a long-term memory organization
IEEE Transactions on Neural Networks
Training of recurrent internal symmetry networks by backpropagation
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Modeling tool-body assimilation using second-order recurrent neural network
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
BICONN: a binary competitive neural network
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Simulated evolution of discourse with coupled recurrent networks
ACAL'07 Proceedings of the 3rd Australian conference on Progress in artificial life
Dynamical Systems Interpretation of Reversal of Subjective Temporal Order Due to Arm Crossing
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
A mathematical model for Cantor coding in the hippocampus
Neural Networks
Dynamic social simulation with multi-agents having internal dynamics
JSAI'03/JSAI04 Proceedings of the 2003 and 2004 international conference on New frontiers in artificial intelligence
Recognition and generation of sentences through self-organizing linguistic hierarchy using MTRNN
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part III
Imitating others by composition of primitive actions: A neuro-dynamic model
Robotics and Autonomous Systems
On the dynamics of robot exploration learning
Cognitive Systems Research
Adaptability and diversity in simulated turn-taking behavior
Artificial Life
| Hi-index | 0.00 |
A higher order recurrent neural network architecture learns to recognize and generate languages after being “trained” on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the learning process illustrates a new form of mechanical inference: Induction by phase transition. A small weight adjustment causes a “bifurcation” in the limit behavior of the network. This phase transition corresponds to the onset of the network's capacity for generalizing to arbitrary-length strings. Second, a study of the automata resulting from the acquisition of previously published training sets indicates that while the architecture is not guaranteed to find a minimal finite automaton consistent with the given exemplars, which is an NP-Hard problem, the architecture does appear capable of generating non-regular languages by exploiting fractal and chaotic dynamics. I end the paper with a hypothesis relating linguistic generative capacity to the behavioral regimes of non-linear dynamical systems.