Deep Learning Framework From Scratch Using Numpy

TL;DR

This paper presents ArrayFlow, a comprehensive deep learning framework built from scratch with Python and Numpy, demonstrating core components like automatic differentiation and optimization through practical examples.

Contribution

It introduces a complete, general-purpose deep learning framework developed from elementary principles, emphasizing educational clarity and foundational understanding.

Findings

Successfully implemented automatic differentiation and gradient optimization.

Applied framework to computer vision, shape modeling, and differential equations.

Demonstrated the framework's versatility through diverse problem solving.

Abstract

This work is a rigorous development of a complete and general-purpose deep learning framework from the ground up. The fundamental components of deep learning - automatic differentiation and gradient methods of optimizing multivariable scalar functions - are developed from elementary calculus and implemented in a sensible object-oriented approach using only Python and the Numpy library. Demonstrations of solved problems using the framework, named ArrayFlow, include a computer vision classification task, solving for the shape of a catenary, and a 2nd order differential equation.