Associative Learning of Integrate-and-Fire Neurons with Memristor-Based Synapses

Authors:
Shiping Wen;Zhigang Zeng;Tingwen Huang
Affiliations:
Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan, China 430074 and Key Laboratory of Image Processing and Intelligent Control of Education Minist ...;Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan, China 430074 and Department of Control Science and Engineering, Huazhong University of Science and ...;Texas A & M University at Qatar, Doha, Qatar 5825
Venue:
Neural Processing Letters
Year:
2013

Citing 21
Cited 0

Analog VLSI and neural systems

Analog VLSI and neural systems
Robust stability for uncertain delayed fuzzy hopfield neural networks with Markovian jumping parameters

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
Improved robust stability criteria for delayed cellular neural networks via the LMI approach

IEEE Transactions on Circuits and Systems II: Express Briefs
State estimation for neural networks with mixed interval time-varying delays

Neurocomputing
Experimental demonstration of associative memory with memristive neural networks

Neural Networks
Spatial Point-Data Reduction Using Pulse Coupled Neural Network

Neural Processing Letters
Cellular Neural Networks for Gray Image Noise Cancellation Based on a Hybrid Linear Matrix Inequality and Particle Swarm Optimization Approach

Neural Processing Letters
Original article: LMI criteria on exponential stability of BAM neural networks with both time-varying delays and general activation functions

Mathematics and Computers in Simulation
New passivity analysis for neural networks with discrete and distributed delays

IEEE Transactions on Neural Networks
Leakage Delays in T---S Fuzzy Cellular Neural Networks

Neural Processing Letters
Impulsive effects on stability of high-order BAM neural networks with time delays

Neurocomputing
Exponential stability of impulsive high-order Hopfield-type neural networks with delays and reaction-diffusion

International Journal of Computer Mathematics
Dynamics Analysis of a Class of Memristor-Based Recurrent Networks with Time-Varying Delays in the Presence of Strong External Stimuli

Neural Processing Letters
Guaranteed Cost Stabilization of Time-varying Delay Cellular Neural Networks via Riccati Inequality Approach

Neural Processing Letters
Bogdanov-Takens bifurcation in a single inertial neuron model with delay

Neurocomputing
A neuromorphic VLSI device for implementing 2D selective attention systems

IEEE Transactions on Neural Networks
A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory

IEEE Transactions on Neural Networks
Temporal coding in a silicon network of integrate-and-fire neurons

IEEE Transactions on Neural Networks
A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity

IEEE Transactions on Neural Networks
Stabilizing Effects of Impulses in Discrete-Time Delayed Neural Networks

IEEE Transactions on Neural Networks
Hebbian Learning in Spiking Neural Networks With Nanocrystalline Silicon TFTs and Memristive Synapses

IEEE Transactions on Nanotechnology

Quantified Score

Hi-index	0.00

Visualization

Abstract

A memrsitor is a two-terminal electronic device whose conductance can be precisely modulated by charge or flux through it. In this paper, we present a class of memristor-based neural circuits comprising leaky integrate-and-fire (I & F) neurons and memristor-based learning synapses. Employing these neuron circuits and corresponding SPICE models, the properties of a two neurons network are shown to be similar to biology. During correlated spiking of the pre- and post-synaptic neurons, the strength of the synaptic connection increases. Conversely, it is diminished when the spiking is uncorrelated. This synaptic plasticity and associative learning is essential for performing useful computation and adaptation in large scale artificial neural networks. Finally, future circuit design and consideration are discussed with the memristor-based neural networks.