Feedback artificial neural network training method and feedback artificial neural network calculating system

Abstract

The invention discloses a feedback artificial neural network training method and a feedback artificial neural network calculating system and belongs to the field of calculation of neural networks. According to the artificial neural network training method, the synapse weight is adjusted according to a feedforward signal and a feedback signal at the two ends of each neural synapse; when the signals at the two ends of each neural synapse are an excitation feedforward signal and an excitation feedback signal respectively, the synapse weight is adjusted to the maximum value; when the signals at the two ends of each neural synapse are a tranquillization feedforward signal and an excitation feedback signal respectively, the synapse weight is adjusted to the minimum value. According to the feedback artificial neural network calculating system, each node circuit comprises a calculating module, a feedforward module and a feedback module and the node circuits are connected through the neural synapses simulated by memristors, and a series of pulse signals are adopted to achieve the feedback artificial neural network training method. An artificial neural network provided by the system and the method is high in rate of convergence, and the artificial neural network calculating system is few in control element, low in energy consumption and capable of being applied to data mining, pattern recognition, image recognition and other respects.

Description

technical field [0001] The invention belongs to the field of artificial neural network computing systems, and more specifically relates to a feedback type artificial neural network training method and a feedback type artificial neural network computing system. Background technique [0002] Synaptic connections in the brain are structures where impulses from one neuron are transmitted to another. The axon of the previous neuron forms a synaptic connection with the dendrite of the next neuron. When the nerve pulse generated by the previous neuron reaches a certain intensity, the neuron changes from a resting state to an excited state, and the nerve pulse is transmitted from the previous neuron to the next neuron through the synaptic connection, and the next neuron generates The strength of the nerve impulse depends on the conduction ability of the nerve synapse; when the nerve impulse produced by the previous neuron does not reach this intensity and the neuron is in a resting...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the above defects or improvement needs of the prior art, the present invention provides a feedback-based artificial neural network computing system and a feedback-based artificial neural network training method, the purpose of which is to simplify the artificial neural network training method and reduce the number of artificial neural networks. Network control components, thereby solving the technical problems of complex realization of existing artificial neural networks, high energy consumption, and slow convergence

Images