Supported-BinaryNet: Bitcell Array-based Weight Supports for Dynamic Accuracy-Latency Trade-offs in SRAM-based Binarized Neural Network

11/19/2019
by   Shamma Nasrin, et al.
0

In this work, we introduce bitcell array-based support parameters to improve the prediction accuracy of SRAM-based binarized neural network (SRAM-BNN). Our approach enhances the training weight space of SRAM-BNN while requiring minimal overheads to a typical design. More flexibility of the weight space leads to higher prediction accuracy in our design. We adapt row digital-to-analog (DAC) converter, and computing flow in SRAM-BNN for bitcell array-based weight supports. Using the discussed interventions, our scheme also allows a dynamic trade-off of accuracy against latency to address dynamic latency constraints in typical real-time applications. We specifically discuss results on two training cases: (i) learning of support parameters on a pre-trained BNN and (ii) simultaneous learning of supports and weight binarization. In the former case, our approach reduces classification error in MNIST by 35.71 decreases from 1.4 27.65 overheads, we propose a dynamic drop out a part of the support parameters. Our architecture can drop out 52 without losing accuracy. We also characterize our design under varying degrees of process variability in the transistors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/12/2020

A Power-Efficient Binary-Weight Spiking Neural Network Architecture for Real-Time Object Classification

Neural network hardware is considered an essential part of future edge d...
research
06/01/2023

Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models

Recent work in speech-to-speech translation (S2ST) has focused primarily...
research
08/24/2023

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency

Efficiently optimizing multi-model inference pipelines for fast, accurat...
research
07/19/2016

Runtime Configurable Deep Neural Networks for Energy-Accuracy Trade-off

We present a novel dynamic configuration technique for deep neural netwo...
research
04/09/2018

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications

This work proposes an automated algorithm, called NetAdapt, that adapts ...
research
12/30/2018

Space Expansion of Feature Selection for Designing more Accurate Error Predictors

Approximate computing is being considered as a promising design paradigm...
research
08/29/2023

OSA-HCIM: On-The-Fly Saliency-Aware Hybrid SRAM CIM with Dynamic Precision Configuration

Computing-in-Memory (CIM) has shown great potential for enhancing effici...

Please sign up or login with your details

Forgot password? Click here to reset