June 30, 2022, 1:18 p.m. | Roland Schätzle

Towards Data Science - Medium towardsdatascience.com

Photo by Braden Collum on Unsplash

Flux.jl on MNIST — A performance analysis

After having defined a variety of models and training algorithms in a previous article, we have now a look on how well they perform when applied to the MNIST dataset.

Introduction

In a previous article (Flux.jl on MNIST — Variations of a theme) we have defined three different neural networks (NN) for the purpose of recognizing handwritten digits using the MNIST dataset. Moreover we implemented …

analysis data science julia machine learning mnist neural networks performance performance analysis

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne