a00ayad00/MNIST-Classification-Problem

MNIST-Classification

we will be using the MNIST dataset, which is a set of 70,000 small images of digits handwritten by high school students and employees of the US Census Bureau. Each image is labeled with the digit it represents. This set has been studied so much that it is often called the "Hello Worl" of Machine Learning

The project contains the following subjects:

-Binary Classification.

-Precision/Recall Tradeoff.

-The ROC Curve (receiver operating characteristic).

-Multiclass Classification.

-Error Analysis.

-Multilabel Classification.

-Multioutput Classification.

Note: This project from what I learned from "Hands on ML and DL" E-book.