Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors

11/27/2019
by   Baogang Zhang, et al.
0

Analog computing based on memristor technology is a promising solution to accelerating the inference phase of deep neural networks (DNNs). A fundamental problem is to map an arbitrary matrix to a memristor crossbar array (MCA) while maximizing the resulting computational accuracy. The state-of-the-art mapping technique is based on a heuristic that only guarantees to produce the correct output for two input vectors. In this paper, a technique that aims to produce the correct output for every input vector is proposed, which involves specifying the memristor conductance values and a scaling factor realized by the peripheral circuitry. The key insight of the paper is that the conductance matrix realized by an MCA is only required to be proportional to the target matrix. The selection of the scaling factor between the two regulates the utilization of the programmable memristor conductance range and the representability of the target matrix. Consequently, the scaling factor is set to balance precision and value range errors. Moreover, a technique of converting conductance values into state variables and vice versa is proposed to handle memristors with non-ideal device characteristics. Compared with the state-of-the-art technique, the proposed mapping results in 4X-9X smaller errors. The improvements translate into that the classification accuracy of a seven-layer convolutional neural network (CNN) on CIFAR-10 is improved from 20.5

READ FULL TEXT
research
09/19/2023

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks

Analog computing has reemerged as a promising avenue for accelerating de...
research
01/23/2018

Flexible Deep Neural Network Processing

The recent success of Deep Neural Networks (DNNs) has drastically improv...
research
10/02/2022

Reliability-Aware Deployment of DNNs on In-Memory Analog Computing Architectures

Conventional in-memory computing (IMC) architectures consist of analog m...
research
10/30/2019

Training DNN IoT Applications for Deployment On Analog NVM Crossbars

Deep Neural Networks (DNN) applications are increasingly being deployed ...
research
03/30/2017

Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics

Artificial Neural Network computation relies on intensive vector-matrix ...
research
04/05/2021

A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays

We introduce the IBM Analog Hardware Acceleration Kit, a new and first o...

Please sign up or login with your details

Forgot password? Click here to reset