Optical neural network reconstruction-inhibition neuron model and architecture

Through the reconstruction-suppression neuron model and architecture of the optical neural network, combined with the optical reconstruction module and the suppression neuron module, reconstructible modulation and filtering are realized, which solves the computing power and power consumption problems of electronic computing technology when dealing with large-scale complex algorithms, and achieves high-performance optical computing and energy efficiency improvement.

CN119886245AActive Publication Date: 2025-04-25TSINGHUA UNIVERSITY
6 Cites 0 Cited by

Patent Information

Application Number
CN202510379742.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-28
Publication Date
2025-04-25
Estimated Expiration
2045-03-28

AI Technical Summary

Technical Problem

Existing electronic computing technologies encounter severe problems in computing power and power consumption when dealing with large-scale complex algorithms, and it is difficult to meet the needs of rapidly developing artificial intelligence and scientific computing.

Method used

A photoneural network reconstruction-suppression neuron model and architecture is proposed. Through the combination of optical reconstruction module and inhibition neuron module, reconfigurable modulation and filtering are realized, and optical calculation and brain-like neuron methods are deeply integrated.

Benefits of technology

It improves the computing density and efficiency, enhances the model's adaptability to complex tasks, realizes high-performance optical computing, and reduces system energy consumption.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of optical computing, in particular to an optical neural network reconstruction-inhibition neuron model and architecture. The model comprises an optical reconstruction module used for receiving an optical input signal and carrying out reconfigurable modulation on the optical input signal to obtain a modulated optical signal, and a modulation parameter corresponding to the reconfigurable modulation is determined by an optical calculation task corresponding to the optical input signal; and the inhibition neuron module is used for constructing a filtering channel corresponding to the optical calculation task, filtering the modulated optical signal according to the filtering channel, and obtaining and outputting an optical output signal. By the adoption of the scheme, high-performance optical calculation can be achieved.
Need to check novelty before this filing date? Find Prior Art