Journal ArticleDOI
Non-holographic associative memory
TLDR
The features of a hologram that commend it as a model of associative memory can be improved on by other devices.Abstract:
The features of a hologram that commend it as a model of associative memory can be improved on by other devices.read more
Citations
More filters
Journal ArticleDOI
A low-order model of biological neural networks
TL;DR: In this article, a biologically plausible low-order model (LOM) of biological neural networks is proposed, which is a recurrent hierarchical network of models of dendritic nodes and trees; spiking and nonspiking neurons; unsupervised, supervised covariance and accumulative learning mechanisms; feedback connections; and a scheme for maximal generalization.
Journal ArticleDOI
Reinforcement learning in a bio-connectionist model based in the thalamo-cortical neural circuit
TL;DR: In this paper, a reinforcement learning program is supported by a bio-connectionism, which links the thalamo-cortical mechanism reproduced with animal perception, and the agent is assigned to a character that must learn by trial and error from its own experience upon recognition of aversive and appetitive patterns.
Dissertation
A Scalable Parallel Algorithm for the Simulation of Structural Plasticity in the Brain
TL;DR: Inspired by hierarchical methods for solving n-body problems in particle physics, this dissertation presents a scalable approximation algorithm for simulating structural plasticity based on MSP and shows through experimental validation that the approximation underlying the algorithm does not adversely affect the quality of the results.
Feature learning in deep classifiers through Intermediate Neural Collapse
TL;DR: Rangamani et al. as discussed by the authors empirically study the evolution of the covariance and mean of representations across different layers and show that as they move deeper into a trained neural network, the within-class covariance decreases relative to the between-class correlation.
Journal ArticleDOI
Deductive rules in holographic reduced representation
TL;DR: An inference process based on the rules modus ponens and modus tollens is described, which exploits a simple algebraic operation of scalar product of distributed representations to measure an overlap between two structured concepts.
References
More filters
Journal ArticleDOI
Theory of Optical Information Storage in Solids
TL;DR: The theory of three-dimensional optical storage lends support to Beurle’s proposed mechanism of information storage in the brain, and makes three- dimensional storage very suitable for associative memories.
Journal ArticleDOI
Holographic Model of Temporal Recall
TL;DR: It is shown that there is at least one other mathematical model, which is considered to be a closer analogue of holography, because it operates with triple products of the temporal function to be recognized or recalled.
Journal ArticleDOI
Improved holographic model of temporal recall.
TL;DR: The modified static system described here is an alternative to Longuet-Higgins' model and takes account of the weaknesses of the nervous system as well as of its powers to imitate human memory with models.
Journal ArticleDOI
The Classification of Modifiable Synapses and Their Use In Models For Conditioning
TL;DR: It is argued that if the conditioning and memory mechanisms of the nervous system store information by means of modifiable synapses, some of these must be of class B or C, and if the models are to be given the property of extinction, classical conditioning requires modifiablesynapses of classes A and B or of class C.