March 22, 2022, 1:52 p.m. | Raveena Jayadev

Towards Data Science - Medium towardsdatascience.com

Hands-On Tutorial; Shifting Perspective in AI

A spatial perspective to MNIST data, rather than the usual vector-treatment

Photo by nine koepfer on Unsplash

By 2022, the MNIST dataset has become the “Hello-World” dataset of people entering AI. Hell, it’s probably been that for a few years already.

In the usual AI treatment of MNIST––whether loading the data into a neural network, logistic regression, random forest, insert-AI-algorithm-here, each digit, with its pixel values, is treated as a vector (so the square …

artificial intelligence computer vision gaussian-mixture-model mnist

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

Machine Learning Engineer - Sr. Consultant level

@ Visa | Bellevue, WA, United States