Comparing neural network training performance between Elixir and Python

TL;DR

This paper compares the training performance of neural networks between Elixir and Python, finding Python generally performs better but Elixir remains a viable alternative for GPU-intensive tasks.

Contribution

It provides the first comparative analysis of CNN training performance on MNIST and CIFAR-10 datasets between Elixir and Python.

Findings

Python achieved better training results overall.

Elixir is a viable alternative for GPU-intensive neural network training.

The study offers insights into using Elixir for machine learning tasks.

Abstract

With a wide range of libraries focused on the machine learning market, such as TensorFlow, NumPy, Pandas, Keras, and others, Python has made a name for itself as one of the main programming languages. In February 2021, Jos\'e Valim and Sean Moriarity published the first version of the Numerical Elixir (Nx) library, a library for tensor operations written in Elixir. Nx aims to allow the language be a good choice for GPU-intensive operations. This work aims to compare the results of Python and Elixir on training convolutional neural networks (CNN) using MNIST and CIFAR-10 datasets, concluding that Python achieved overall better results, and that Elixir is already a viable alternative.