Paper Info
Title
A Neural Network Assembly Memory Model Based on an Optimal Binary Signal Detection Theory
Abstract
A ternary/binary data coding algorithm and conditions under which Hopfield networks implement optimal convolutional and Hamming decoding algorithms has been described. Using the coding/decoding approach (an optimal Binary Signal Detection Theory, BSDT) introduced a Neural Network Assem- bly Memory Model (NNAMM) is built. The model provides optimal (the best) basic memory performance and demands the use of a new memory unit archi- tecture with two-layer Hopfield network, N-channel time gate, auxiliary refer- ence memory, and two nested feedback loops. NNAMM explicitly describes the dependence on time of a memory trace retrieval, gives a possibility of metamemory simulation, generalized knowledge representation, and distinct description of conscious and unconscious mental processes. A model of small- est inseparable part or an "atom" of consciousness is also defined. The NNAMM's neurobiological backgrounds and its applications to solving some interdisciplinary problems are shortly discussed. BSDT could implement the "best neural code" used in nervous tissues of animals and humans.
Year
Venue
Keywords
2003
Clinical Orthopaedics and Related Research
hopfield network,evolutionary computing,feedback loop,quantitative method,memory model,signal detection theory,artificial intelligent,neural code,information retrieval,neural network
Field
DocType
Volume
Hamming code,Neural coding,Computer science,Recurrent neural network,Theoretical computer science,Memory model,Artificial intelligence,Binary data,Decoding methods,Artificial neural network,Hopfield network,Machine learning
Journal
cs.AI/0309
ISSN
Citations 
PageRank 
Problemy Programmirovaniya (Programming Problems, Kyiv, Ukraine), 2004, no. 2-3, pp. 473-479.
1
0.56
References 
Authors
4
2
Name
Order
Citations
PageRank
Petro M. Gopych14310.68
V. N. Karazin210.56