Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 

Repository files navigation

QuickStart

Books

Python Programming And Numerical Methods: A Guide For Engineers And Scientists

Free programming books in many languages

Technical

The guide to Git I never had

Google Python Style Guide

Google developer documentation style guide

Building Implicit Interfaces in Python with Protocol Classes

Pytest Approx for Accurate Numeric Testing

How to Write a Git Commit Message

How to organize your Python data science project

Semantic Versioning 2.0.0

Software licensing

Choose an open source license

How to Use GNU Licenses for Your Own Software

Educational

Mathematical Pathways to Machine Learning

A common gap between foundational mathematics courses and introductory machine learning is the lack of a clear bridge between them. First-year students often study calculus and linear algebra as separate subjects without seeing how these ideas work together in modern machine learning. At the same time, many excellent machine-learning books assume more mathematical background than beginning students have.

I developed this book to help fill that gap. It shows how linear algebra represents data and models, calculus explains sensitivity and backpropagation, and optimization turns derivatives into learning algorithms.

Growing out of my MATH 225 lectures at Penn State, the book is designed primarily for first-year university students with little or no prior exposure to machine learning. It combines accessible mathematical explanations and worked examples with direct connections to machine learning. Short programming exercises using NumPy will be released later.

My hope is that the book will be useful not only to students, but also to instructors designing interdisciplinary mathematics and machine-learning

Building LLMs from scratch

Physics informed neural networks (PINNS)

What is Automatic Differentiation?

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors