Selectively Grouping Neurons in Recurrent Networks of Lateral Inhibition

DOI10.1162/089976602760408008zbMath1024.92003WikidataQ39635749 ScholiaQ39635749MaRDI QIDQ4409381

H. Sebastian Seung, Richard H. R. Hahnloser, Xiaohui Xie

Publication date: 30 June 2003

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

Full work available at URL: https://doi.org/10.1162/089976602760408008

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

92C20: Neural biology

92B20: Neural networks for/in biological studies, artificial life and related topics

Related Items

Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks, Line attractors of coupled ring neural networks with block circulant weight matrix, Sequential Attractors in Combinatorial Threshold-Linear Networks, Encoding Binary Neural Codes in Networks of Threshold-Linear Neurons, Pattern Completion in Symmetric Threshold-Linear Networks, Selectivity and Stability via Dendritic Nonlinearity, Analysis of Cyclic Dynamics for Networks of Linear Threshold Neurons, A competitive layer model for cellular neural networks, Nerve theorems for fixed points of neural networks, Dynamic updating of distributed neural representations using forward models, Heteroclinic binding, Fixed Points of Competitive Threshold-Linear Networks, Competitive Layer Model of Discrete-Time Recurrent Neural Networks with LT Neurons, A VIEW OF NEURAL NETWORKS AS DYNAMICAL SYSTEMS

Cites Work

• A Competitive-Layer Model for Feature Binding and Sensory Segmentation
• Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions
• Qualitative behaviour of some simple networks
• Neural networks and physical systems with emergent collective computational abilities.
• Learning the parts of objects by non-negative matrix factorization
• Neurons with graded response have collective computational properties like those of two-state neurons.