ASIC design

In this project, you are going to design and implement an artificial neural network (ANN) that can recognize handwritten digits. The hand written digits are provided as images with 8×8 pixels. Each pixel has a value ranging from -0.5 to 0.5. It is represented by 8-bit fidžed point Ϯ͛s complementarLJ nƵmbers with 7 fractional bits. As shown in Figure 1, the ANN to be implemented has three layers: input, hidden, and output layers. The input layer has 64 nodes, each corresponding to a pixel of the digit image. The output layer has 10 nodes, each corresponding to a digit value (from 0 to 9). There are 12 nodes are in the hidden layer.

ASIC FPGA

Nº del proyecto: #27933526

Sobre el proyecto