Feature discovery by competitive learning
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Improving the convergence of the back-propagation algorithm
Neural Networks
The neurobiological significance of the new learning models
Computational neuroscience
Temporal difference learning and TD-Gammon
Communications of the ACM
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Temporal Difference Model Reproduces Anticipatory Neural Activity
Neural Computation
Infinite-horizon policy-gradient estimation
Journal of Artificial Intelligence Research
Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
Neural Computation
Elman Backpropagation as Reinforcement for Simple Recurrent Networks
Neural Computation
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Temporal context as cortical spatial codes
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Goal-directed feature learning
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Dissociable neural effects of long-term stimulus-reward pairing in macaque visual cortex
Journal of Cognitive Neuroscience
Developmental stereo: topographic iconic-abstract map from top-down connection
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Error-backpropagation in networks of fractionally predictive spiking neurons
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Biologically plausible multi-dimensional reinforcement learning in neural networks
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Supervised learning in multilayer spiking neural networks
Neural Computation
Hi-index | 0.00 |
Animal learning is associated with changes in the efficacy of connections between neurons. The rules that govern this plasticity can be tested in neural networks. Rules that train neural networks to map stimuli onto outputs are given by supervised learning and reinforcement learning theories. Supervised learning is efficient but biologically implausible. In contrast, reinforcement learning is biologically plausible but comparatively inefficient. It lacks a mechanism that can identify units at early processing levels that play a decisive role in the stimulus-response mapping. Here we show that this so-called credit assignment problem can be solved by a new role for attention in learning. There are two factors in our new learning scheme that determine synaptic plasticity: (1) a reinforcement signal that is homogeneous across the network and depends on the amount of reward obtained after a trial, and (2) an attentional feedback signal from the output layer that limits plasticity to those units at earlier processing levels that are crucial for the stimulus-response mapping. The new scheme is called attention-gated reinforcement learning (AGREL). We show that it is as efficient as supervised learning in classification tasks. AGREL is biologically realistic and integrates the role of feedback connections, attention effects, synaptic plasticity, and reinforcement learning signals into a coherent framework.