# Machine Learning with Clos Networks

## TL;DR

This paper introduces a novel approach to enhance small neural networks' accuracy by applying Clos network concepts, exploring deeper architectures, and analyzing ReLU effects, with initial results on CIFAR-10.

## Contribution

It proposes a new methodology inspired by Clos networks for improving small neural network performance and investigates the impact of network depth and ReLU nonlinearity.

## Key findings

- Deeper networks with the same parameter count improve accuracy.
- ReLU nonlinearity affects accuracy in separable networks.
- Initial results show promise on CIFAR-10 dataset.

## Abstract

We present a new methodology for improving the accuracy of small neural networks by applying the concept of a clos network to achieve maximum expression in a smaller network. We explore the design space to show that more layers is beneficial, given the same number of parameters. We also present findings on how the relu nonlinearity ffects accuracy in separable networks. We present results on early work with Cifar-10 dataset.