Bidirectional associative memories
IEEE Transactions on Systems, Man and Cybernetics
Self-organization and associative memory: 3rd edition
Self-organization and associative memory: 3rd edition
Mathematical methods in artificial intelligence
Mathematical methods in artificial intelligence
Neural correlation via random connections
Neural Computation
Self-organizing maps
Artificial intelligence: a new synthesis
Artificial intelligence: a new synthesis
Cortical dynamics of three-dimensional surface perception: binocular and half-occluded scenic images
Transactions of the Society for Computer Simulation International - Special issue: simulation methodology in transportation systems
Pattern Recognition by Self-Organizing Neural Networks
Pattern Recognition by Self-Organizing Neural Networks
A Biologically Motivated Solution to the Cocktail Party Problem
Neural Computation
How precise is neuronal synchronization?
Neural Computation
IEEE Transactions on Information Theory
A New Associative Model with Dynamical Synapses
Neural Processing Letters
A powerful and general approach to context exploitation in natural language processing
CLS '04 Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics
Hi-index | 0.00 |
This chapter presents the first comprehensive high-level theory of the information processing function of mammalian cortex and thalamus; herein viewed as a unary structure. The theory consists of four major elements: two novel associative memory neuronal network structures (feature attractor networks and antecedent support networks ), a universal information processing operation (consensus building), and an overall real-time brain control system (the brain command loop). One important derived type of thalamocortical neural network is also presented, the hierarchical abstractor (which, as with all other networks of thalamocortex, is "constructed" out of antecedent support and feature attractor networks). Some smaller constructs are also introduced. Arguments are presented as to why this theory must be basically correct. READER WARNING: The content of this chapter is complicated and almost entirely novel and unfamiliar. Detailed study and multiple readings may be required. Effort expended in learning its content will be richly rewarded. Carrying out computer experiments can be a useful learning adjunct. For simplicity and readability, the theory is presented as fact, without constant recitation of disclaimers such as "it is hypothesized."