Neural Network Learning Hub!

AI Learning Roadmap


Section 1: Foundations (Math, Regression, Classification, XOR)


These four projects build the mental model of linear algebra → optimization → nonlinearity.


  1. Single‑Feature Linear Regression

    • MSE, gradients, update
    • r, R², OLS
    • Geometry of projection

  2. Multi‑Feature Regression

    • Vectorized dot products
    • Weight vector as a direction in feature space
    • Plane instead of line
    • Residual vectors

  3. Binary Classification

    • Logistic regression
    • Sigmoid
    • Cross‑entropy
    • Decision boundary geometry

  4. Neural Network for XOR

    • Hidden layer
    • Activation functions
    • Why linear models fail
    • Geometry of separating non‑linearly separable data

  5. The Design Matrix

    • Why ML always uses a matrix
    • How neural networks generalize it
    • How shapes flow through the system
    • How this is a neural network layer


Neural Networks Simple Math 3 images explaining what these 5 projects teach.


Section 2: Building Real Neural Networks (Projects 6–10)


This is where you move from single neurons to full, modular neural network architectures—first from scratch, then with PyTorch.


  1. Build a Neural Network Class From Scratch

    • A Layer class
    • A NeuralNetwork class
    • Forward pass
    • Backprop
    • Training loop
    • Loss functions
    • Activation functions
    • Modular architecture

  2. Introduction to PyTorch (Tensors, Autograd, Modules)

    • How PyTorch replaces your manual gradients
    • How nn.Module mirrors your custom class
    • How autograd works
    • How optimizers work
    • How to rewrite your Project 5 network in PyTorch

  3. Recurrent Neural Networks (RNNs)

    • Sequence modeling
    • Hidden state
    • Unrolling
    • Vanishing gradients
    • PyTorch’s nn.RNN

  4. LSTM Networks

    • The natural evolution of Project 7
    • Gates
    • Cell state
    • Long‑term memory
    • Why LSTMs solve vanishing gradients
    • PyTorch’s nn.LSTM

  5. GRU or CNN (Your Choice)

    • Explore GRU as a simplified gated RNN, or
    • Explore CNNs for spatial feature extraction
    • Compare trade‑offs and ideal use cases

The Core Concepts of Machine Learning