ITM Web of Conferences
Volume 6, 20166th Seminar on Industrial Control Systems: Analysis, Modeling and Computation
|Number of page(s)||5|
|Published online||25 March 2016|
Analytical estimates of efficiency of attractor neural networks with inborn connections
1 Moscow Institute of Physics and Technology, Dolgoprudny, Moscow Region, 141700, Russia
2 Scientific Research Institute for System Analysis, RAS, Moscow, Nakhimovskiy Prospect 36, b.1, 117218, Russia
3 Moscow Technological Institute, Moscow, Leninskii Prospect 38a, 119334, Russia
a Corresponding author: firstname.lastname@example.org
The analysis is restricted to the features of neural networks endowed to the latter by the inborn (not learned) connections. We study attractor neural networks in which for almost all operation time the activity resides in close vicinity of a relatively small number of attractor states. The number of the latter, M, is proportional to the number of neurons in the neural network, N, while the total number of the states in it is 2N. The unified procedure of growth/fabrication of neural networks with sets of all attractor states with dimensionality d=0 and d=1, based on model molecular markers, is studied in detail. The specificity of the networks (d=0 or d=1) depends on topology (i.e., the set of distances between elements) which can be provided to the set of molecular markers by their physical nature. The neural networks parameters estimates and trade-offs for them in attractor neural networks are calculated analytically. The proposed mechanisms reveal simple and efficient ways of implementation in artificial as well as in natural neural networks of multiplexity, i.e. of using activity of single neurons in representation of multiple values of the variables, which are operated by the neural systems. It is discussed how the neuronal multiplexity provides efficient and reliable ways of performing functional operations in the neural systems.
© Owned by the authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.