Deep Learning Research

ML From Scratch

Deconstructing intelligence by building it from the ground up using Pure NumPy.

Learning Philosophy

This repository follows one core rule: Implement everything manually. By bypassing high-level abstractions like scikit-learn for the core logic, we gain a visceral understanding of vectorization, optimization behavior, and the mathematical foundations of intelligence. It is a journey through the "black box", turning magic into mathematics.

First Principles

Every algorithm is implemented from scratch using NumPy. No shortcuts, no black boxes. Just raw linear algebra and calculus.

Mathematical Depth

Detailed derivations and explanations accompanying each implementation. Understanding the 'Why' before the 'How'.

Visual Intuition

Step-by-step visualizations of decision boundaries, loss landscapes, and iterative convergence.

Implemented Algorithms

K-Nearest Neighbors

Linear Regression

Logistic Regression

Naive Bayes

Perceptron

Support Vector Machine

Decision Tree

Random Forest

PCA

K-Means Clustering

AdaBoost

Linear Discriminant Analysis

Research Stack

NumPy

Matplotlib

Pandas

Jupyter

Python 3.10+

← Back to Selected Works

Loading System...

MM.

ML From Scratch

Learning Philosophy

First Principles

Mathematical Depth

Visual Intuition

Implemented Algorithms

Research Stack

ML From Scratch

Learning Philosophy

First Principles

Mathematical Depth

Visual Intuition

Implemented Algorithms

Research Stack