Design of Neural Network Identification System Based on FPGA

According to the principle of BP neural network algorithm, this paper uses a FPGA (Field Programmable Gate Array) to implement a three-layer BP (back propagation) neural network system that recognizes the handwritten digits of the MNIST library. The system selects 100 test samples from the MNIST database and performs simulation tests on the recognition accuracy of the circuit in the FPGA development platform Quartus II 13.0 and Modelsim. The digital recognition accuracy of the simulation is 89%, which can be used in a simple pattern recognition system.