DeepAI AI Chat
Log In Sign Up

Adaptive Block Floating-Point for Analog Deep Learning Hardware

by   Ayon Basumallik, et al.

Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital counterparts. However, recent studies show that DNNs on AMS devices with fixed-point numbers can incur an accuracy penalty because of precision loss. To mitigate this penalty, we present a novel AMS-compatible adaptive block floating-point (ABFP) number representation. We also introduce amplification (or gain) as a method for increasing the accuracy of the number representation without increasing the bit precision of the output. We evaluate the effectiveness of ABFP on the DNNs in the MLPerf datacenter inference benchmark – realizing less than 1% loss in accuracy compared to FLOAT32. We also propose a novel method of finetuning for AMS devices, Differential Noise Finetuning (DNF), which samples device noise to speed up finetuning compared to conventional Quantization-Aware Training.


page 1

page 2

page 3

page 4


Cheetah: Mixed Low-Precision Hardware Software Co-Design Framework for DNNs on the Edge

Low-precision DNNs have been extensively explored in order to reduce the...

Development of Quantized DNN Library for Exact Hardware Emulation

Quantization is used to speed up execution time and save power when runn...

Stochastic Deep Learning in Memristive Networks

We study the performance of stochastically trained deep neural networks ...

Fixed-point quantization aware training for on-device keyword-spotting

Fixed-point (FXP) inference has proven suitable for embedded devices wit...

Impact of L1 Batch Normalization on Analog Noise Resistant Property of Deep Learning Models

Analog hardware has become a popular choice for machine learning on reso...

A Framework for Semi-Automatic Precision and Accuracy Analysis for Fast and Rigorous Deep Learning

Deep Neural Networks (DNN) represent a performance-hungry application. F...