DeepAI AI Chat
Log In Sign Up

Computational Cost Reduction in Learned Transform Classifications

04/26/2015
by   Emerson Lopes Machado, et al.
0

We present a theoretical analysis and empirical evaluations of a novel set of techniques for computational cost reduction of classifiers that are based on learned transform and soft-threshold. By modifying optimization procedures for dictionary and classifier training, as well as the resulting dictionary entries, our techniques allow to reduce the bit precision and to replace each floating-point multiplication by a single integer bit shift. We also show how the optimization algorithms in some dictionary training methods can be modified to penalize higher-energy dictionaries. We applied our techniques with the classifier Learning Algorithm for Soft-Thresholding, testing on the datasets used in its original paper. Our results indicate it is feasible to use solely sums and bit shifts of integers to classify at test time with a limited reduction of the classification accuracy. These low power operations are a valuable trade off in FPGA implementations as they increase the classification throughput while decrease both energy consumption and manufacturing cost.

READ FULL TEXT
02/09/2014

Dictionary learning for fast classification based on soft-thresholding

Classifiers based on sparse representations have recently been shown to ...
07/01/2020

Optimisation of the PointPillars network for 3D object detection in point clouds

In this paper we present our research on the optimisation of a deep neur...
11/28/2017

A Transprecision Floating-Point Platform for Ultra-Low Power Computing

In modern low-power embedded platforms, floating-point (FP) operations e...
05/02/2018

Compressed Dictionary Learning

In this paper we show that the computational complexity of the Iterative...
06/20/2017

Improving text classification with vectors of reduced precision

This paper presents the analysis of the impact of a floating-point numbe...
07/03/2016

Understanding the Energy and Precision Requirements for Online Learning

It is well-known that the precision of data, hyperparameters, and intern...
06/21/2020

Efficient Integer-Arithmetic-Only Convolutional Neural Networks

Integer-arithmetic-only networks have been demonstrated effective to red...