Pulse neural network training method, storage medium, chip and electronic product

Abstract

The invention relates to a spiking neural network training method, a storage medium, a chip and an electronic product. In order to overcome the problem that an algorithm and hardware are difficult to fit due to device mismatch in the prior art and enable a trained network to well adapt to hardware characteristics of different sensors, various event-based and rate-based enhancements are carried out on training data; comprising the steps of random thermal noise generation, shot noise simulation, adaptive data rate adjustment and random firmware necrosis, training is carried out based on enhanced data, and configuration parameters enabling the prediction performance of the pulse neural network to be optimal are obtained. According to the method, the application adaptation problem when different sensors or different environments are connected with pulse neural network hardware is efficiently and uniformly solved, the chip performance is more stable and effective, and the reasoning result is more consistent. The method is suitable for the field of brain-like chips, in particular to the field of pulse neural network training.

Description

technical field [0001] The invention relates to a pulse neural network training method, a storage medium, a chip and an electronic product, in particular to a pulse neural network training method for adapting device mismatch between different sensors, a storage medium, a chip and an electronic product. Background technique [0002] Sensors, such as event cameras (also known as event-driven cameras, dynamic vision sensors), audio front ends, etc., convert changing information into events. Event camera is a novel image sensing hardware device, and it is also one of the research hotspots in recent years. Each pixel of an event camera receives a light change signal independently, and asynchronously sends out a pulse event when the light changes, so it does not have the concept of a frame in a traditional camera. Although there are also cases of processing data generated by event cameras through traditional artificial neural networks (ANN) (usually requiring frame compression pr...

AI Technical Summary

Problems solved by technology

[0012] Although data enhancement technology can increase the diversity of data and solve the problem of unfitting or overfitting caused by insufficient data volume, it still cannot solve the problem of difficult fit between algorithms and hardware caused by device mismatch.

Images