Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning

DOI10.1162/08997660152002834zbMath0963.68643DBLPjournals/neco/OReilly01OpenAlexW2153758134WikidataQ34270227 ScholiaQ34270227MaRDI QIDQ2723303

Randall C. O'Reilly

Publication date: 5 July 2001

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/08997660152002834

zbMATH Keywords

computational modelscognitive neuroscience

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99)

Related Items (13)

Fading memory and time series prediction in recurrent networks with different forms of plasticity ⋮ Hold your horses: a dynamic computational role for the subthalamic nucleus in decision making ⋮ Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn ⋮ Stimulus space complexity determines the ratio of specialist and generalist neurons during pattern recognition ⋮ Fast and Robust Learning by Reinforcement Signals: Explorations in the Insect Brain ⋮ Learning Classification in the Olfactory System of Insects ⋮ Inhibition in Multiclass Classification ⋮ A tutorial on approximate Bayesian computation ⋮ Making Working Memory Work: A Computational Model of Learning in the Prefrontal Cortex and Basal Ganglia ⋮ How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors ⋮ Receptive Field Self-Organization in a Model of the Fine Structure in V1 Cortical Columns ⋮ Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments ⋮ Preintegration Lateral Inhibition Enhances Unsupervised Learning

Cites Work

• Dynamics and architecture for neural computation
• A simplified neuron model as a principal component analyzer
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• A Simple Neural Network Exhibiting Selective Activation of Neuronal Ensembles: From Winner-Take-All to Winners-Share-All
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning