Analysis of oscillator neural networks for sparsely coded phase patterns

DOI10.1088/0305-4470/33/48/308MaRDI QIDQ2703482zbMATH OpenOpenAlexFDO

Authors Masaki Nomura, Toshio Aoyagi

Publication date 5 March 2001

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0004278

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: We study a simple extended model of oscillator neural networks capable of storing sparsely coded phase patterns, in which information is encoded both in the mean firing rate and in the timing of spikes. Applying the methods of statistical neurodynamics to our model, we theoretically investigate the model's associative memory capability by evaluating its maximum storage capacities and deriving its basins of attraction. It is shown that, as in the Hopfield model, the storage capacity diverges as the activity level decreases. We consider various practically and theoretically important cases. For example, it is revealed that a dynamically adjusted threshold mechanism enhances the retrieval ability of the associative memory. It is also found that, under suitable conditions, the network can recall patterns even in the case that patterns with different activity levels are stored at the same time. In addition, we examine the robustness with respect to damage of the synaptic connections. The validity of these theoretical results is confirmed by reasonable agreement with numerical simulations.

Recommendations

• Analysis of recurrent networks of pulse-coupled noisy neural oscillators
• Analysis of a neural oscillator
• Oscillatory Networks: Pattern Recognition Without a Superposition Catastrophe
• Multi-parameter oscillatory coupling functions in neural networks
• Oscillator neural network model with distributed native frequencies
• Neural coding in networks of multi-populations of neural oscillators
• Phase-amplitude descriptions of neural oscillator models
• Periodic oscillation for discrete-time Hopfield neural networks

Cited in

(8)

• Oscillatory associative memory network with perfect retrieval
• A complex-valued associative memory for storing patterns as oscillatory states
• Dynamics of Sequence-Associative Memory for Discrete Maps in XY Spin Systems
• Analysis of oscillator neural network without Lyapunov function
• Oscillator neural network model with distributed native frequencies
• Rate and temporal coding with a neural oscillator
• Oscillatory Networks: Pattern Recognition Without a Superposition Catastrophe
• Oscillatory neural network for pattern recognition: trajectory based classification and supervised learning

This page was built for publication: Analysis of oscillator neural networks for sparsely coded phase patterns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2703482)