A Method for Obtaining Highly Robust Memristor Based Binarized Convolutional Neural Network

AbstractRecently, memristor based binarized convolutional neural network has been widely investigated owing to its strong processing capability, low power consumption and high computing efficiency.However, it has not been widely applied in the field of embedded neuromorphic computing for manufacturing technology of the memristor being not mature. With respect to this, we propose a method for obtaining highly robust memristor based binarized convolutional neural network. To demonstrate the performance of the method, a convolutional neural network architecture with two layers is used for simulation, and the simulation results show that binarized convolutional neural network can still achieve more than 96.75% recognition rate on MNIST dataset under the condition of 80% yield of the memristor array, and the recognition rate is 94.53% when the variation of memristance is 26%, and it is 94.66% when the variation of the neuron output is 0.8.