Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

TL;DR

This paper extends resistive processing units (RPUs) to convolutional neural networks, demonstrating how to map CNN layers onto RPU arrays and mitigate analog noise effects for effective training.

Contribution

It introduces methods for mapping CNNs onto RPU hardware, managing noise and variability, and enabling successful training with resistive devices, broadening RPU applicability.

Findings

Effective CNN mapping onto RPU arrays demonstrated

Noise and bound management techniques improve training accuracy

Techniques applicable to various neural network architectures

Abstract

In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive Processing Unit (RPU) devices we extend here towards convolutional neural networks (CNNs). We show how to map the convolutional layers to RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed due to analog nature of the computations performed on the arrays effect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of RPU approach for large class of neural network architectures.