June 23, 2022, 2:49 p.m. | Roland Schätzle

Towards Data Science - Medium towardsdatascience.com

Photo by James Orr on Unsplash

Flux.jl on MNIST — Variations of a theme

Flux.jl is a ML-stack offering lightweight components to create models and train them. Using the MNIST dataset we will see how easy it is to build different approaches for classification of this dataset just by plugging such components together.

Overview

Flux.jl

Flux.jl is a package written in 100% Julia. It’s aimed at building models which are typically trained using an iterative approach based on automated differentiation. …

data science julia machine learning mnist neural networks programming

Senior Machine Learning Engineer

@ GPTZero | Toronto, Canada

ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)

@ HelloBetter | Remote

Doctoral Researcher (m/f/div) in Automated Processing of Bioimages

@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena

Seeking Developers and Engineers for AI T-Shirt Generator Project

@ Chevon Hicks | Remote

Senior Applied Data Scientist

@ dunnhumby | London

Principal Data Architect - Azure & Big Data

@ MGM Resorts International | Home Office - US, NV