MinConvNets: A new class of multiplication-less Neural Networks

01/23/2021
by   Xuecan Yang, et al.
0

Convolutional Neural Networks have achieved unprecedented success in image classification, recognition, or detection applications. However, their large-scale deployment in embedded devices is still limited by the huge computational requirements, i.e., millions of MAC operations per layer. In this article, MinConvNets where the multiplications in the forward propagation are approximated by minimum comparator operations are introduced. Hardware implementation of minimum operation is much simpler than multipliers. Firstly, a methodology to find approximate operations based on statistical correlation is presented. We show that it is possible to replace multipliers by minimum operations in the forward propagation under certain constraints, i.e. given similar mean and variances of the feature and the weight vectors. A modified training method which guarantees the above constraints is proposed. And it is shown that equivalent precision can be achieved during inference with MinConvNets by using transfer learning from well trained exact CNNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/26/2019

Deep Learning Training with Simulated Approximate Multipliers

This paper presents by simulation how approximate multipliers can be uti...
research
07/20/2020

Effects of Approximate Multiplication on Convolutional Neural Networks

This paper analyzes the effects of approximate multiplication when perfo...
research
06/01/2018

A new class of irreducible pentanomials for polynomial based multipliers in binary fields

We introduce a new class of irreducible pentanomials over F_2 of the for...
research
09/20/2021

GhostShiftAddNet: More Features from Energy-Efficient Operations

Deep convolutional neural networks (CNNs) are computationally and memory...
research
05/09/2023

DietCNN: Multiplication-free Inference for Quantized CNNs

The rising demand for networked embedded systems with machine intelligen...
research
04/12/2020

Minimal Filtering Algorithms for Convolutional Neural Networks

In this paper, we present several resource-efficient algorithmic solutio...
research
09/20/2022

CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 Diagnosis

This paper proposes transferred initialization with modified fully conne...

Please sign up or login with your details

Forgot password? Click here to reset