NEURAL NETWORK CIRCUIT, EDGE DEVICE AND METHOD FOR NEURAL NETWORK CALCULATION

摘要

Provides a high-performance neural network circuit that can be embedded in embedded devices such as IoT devices. The neural network circuit includes: a first memory for storing input data; a convolution operation circuit for performing a convolution operation on the input data and weights stored in the first memory; and a first memory for storing convolution operation output data of the convolution operation circuit a quantization arithmetic circuit comprising two memories and a quantization arithmetic circuit for performing a quantization operation on the convolutional arithmetic output data stored in the second memory, wherein the quantization arithmetic output data of the quantization arithmetic circuit is stored in the first memory and the first The quantization operation output data stored in the memory is input to the convolution operation circuit as the input data.