# Computational complexity reduction of deep neural networks

arXiv: https://arxiv.org/abs/2207.14620 · HTML: https://mlsanity.com/paper/2207.14620/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 29 Jul 2022.

## Builds on (most cited first, 7 of 7)

- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [A Critical Review of Recurrent Neural Networks for Sequence Learning](https://mlsanity.com/paper/1506.00019/) (2015)
- [Solving machine learning optimization problems using quantum computers](https://mlsanity.com/paper/1911.08587/) (2019)
- [Complexity and mission computability of adaptive computing systems](https://mlsanity.com/paper/1808.09586/) (2018)
- [Optimization problems with low SWaP tactical Computing](https://mlsanity.com/paper/1902.05070/) (2019)
- [Optimization and synchronization of programmable quantum communication channels](https://mlsanity.com/paper/1805.05923/) (2018)
- [Genetic optimization algorithms applied toward mission computability models](https://mlsanity.com/paper/2005.13105/) (2020)

## Abstract (arXiv)

Deep neural networks (DNN) have been widely used and play a major role in the field of computer vision and autonomous navigation. However, these DNNs are computationally complex and their deployment over resource-constrained platforms is difficult without additional optimizations and customization. In this manuscript, we describe an overview of DNN architecture and propose methods to reduce computational complexity in order to accelerate training and inference speeds to fit them on edge computing platforms with low computational resources.