Incremental learning of sequence patterns with a modular network model

Authors:
Ichiro Igari;Jun Tani
Affiliations:
Brain Science Institute, RIKEN, 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan;Brain Science Institute, RIKEN, 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan
Venue:
Neurocomputing
Year:
2009

Citing 10
Cited 2

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Emergence and Categorization of Coordinated Visual Behavior ThroughEmbodied Interaction

Machine Learning - Special issue on learning in autonomous robots
Neural learning of embodied interaction dynamics

Neural Networks - Special issue on neural control and robotics: biology and technology
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

Neural Networks - Special issue on organisation of computation in brain-like systems
Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Adaptive mixtures of local experts

Neural Computation
Intrinsic Motivation Systems for Autonomous Mental Development

IEEE Transactions on Evolutionary Computation
Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance

Neural Networks
An incremental neural network with a reduced architecture

Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

The relationship between generalization and differentiation fluctuates depending on the ongoing context, which is extracted by the current adaptive capability of the learner. In the present report, we numerically examine the relationship between generalization and differentiation using a novel connectionist model. The simulation results of incremental learning indicate that the newly added sequence modifies the previously learned internal representations in a different manner, depending on the inconsistency with the preceding task. This observation supports our assertion that it is fundamentally important to investigate how the transition dynamics of learning toward a goal affects the finally acquired structure of the learner.