Spatiotemporal contextual learning network with excitatory and inhibitory synapses for spiking neural network hardware
Open Access
- 1 January 2024
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in Nonlinear Theory and Its Applications, IEICE
- Vol. 15 (4) , 796-810
Abstract
A spatiotemporal contextual learning network (STCLN) model is suitable for edge applications. To implement the STCLN model as a small analog asynchronous integrated circuit with low power consumption, this study proposes to introduce the excitatory and inhibitory synapses into the STCLN model which can be implemented by an event-driven spiking neural network (SNN) circuit. Through the performance evaluation of the proposed STCLN model for SNN, the optimal ratio of the excitatory and inhibitory synapse is derived.Keywords
This publication has 17 references indexed in Scilit:
- An Extended Spatiotemporal Contextual Learning and Memory Network Model for Hardware ImplementationProcedia Computer Science, 2023
- Context-Dependent Learning and Memory Based on Spatio-Temporal Learning Rule2021
- Fractal Structure in Hokusai’s “Great Wave” and the Memory Neural Network2021
- A Structure and Function of Hippocampal Memory Networks in Consolidating Spatiotemporal Contexts2018
- Principles of Computational Modelling in Neuroscience2011
- Interaction between the Spatiotemporal Learning Rule (STLR) and Hebb type (HEBB) in single pyramidal cells in the hippocampal CA1 AreaCognitive Neurodynamics, 2007
- A Model of the Hippocampal–cortical Memory SystemBiological Cybernetics, 2006
- The spatiotemporal learning rule and its efficiency in separating spatiotemporal patternsBiological Cybernetics, 2005
- Cantor coding in the hippocampusJapan Journal of Industrial and Applied Mathematics, 2001
- Hippocampal LTP Depends on Spatial and Temporal Correlation of InputsNeural Networks, 1996