Comparing neural network training performance between Elixir and Python
This is an incremental comparison of programming languages for neural network training, relevant for developers choosing tools for machine learning tasks.
This work compared the training performance of convolutional neural networks (CNNs) on MNIST and CIFAR-10 datasets between Python and Elixir, finding that Python achieved overall better results while Elixir is a viable alternative.
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, José 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.