DeepAI AI Chat
Log In Sign Up

Computational Cost Reduction in Learned Transform Classifications

by   Emerson Lopes Machado, et al.

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.


Dictionary learning for fast classification based on soft-thresholding

Classifiers based on sparse representations have recently been shown to ...

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...

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

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

Compressed Dictionary Learning

In this paper we show that the computational complexity of the Iterative...

Improving text classification with vectors of reduced precision

This paper presents the analysis of the impact of a floating-point numbe...

Understanding the Energy and Precision Requirements for Online Learning

It is well-known that the precision of data, hyperparameters, and intern...

Efficient Integer-Arithmetic-Only Convolutional Neural Networks

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