# Computational Cost Reduction in Learned Transform Classifications

arXiv: https://arxiv.org/abs/1504.06779 · HTML: https://mlsanity.com/paper/1504.06779/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2015.

## Built on by (most cited first, 1 of 1)

- [Low-complexity Approximate Convolutional Neural Networks](https://mlsanity.com/paper/2208.00087/) (2022)

## Abstract (arXiv)

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.