Every lecture, downloadable

Code & Resources Library

Every lecture pairs its math with a small, runnable Python script that reproduces the lecture's own worked numerical example — download it, run it, and check the printed numbers against the page. Where a proper implementation is too heavy for a single demo (training a real CNN, a full seq2seq model, a production autoencoder), the card below also links to a stable, official external tutorial or Colab notebook.

💾 24 lectures · all code is plain NumPy unless noted, with a few Keras/TensorFlow examples for the heavier architectures.

Module A Foundations of Neural Networks

Lecture 01

Course Introduction & The Deep Learning Landscape

One-time environment setup — checks that NumPy, Matplotlib, scikit-learn and TensorFlow are installed before you start the course.

Lecture 02

Machine Learning Foundations Recap

Fits polynomials of increasing degree to a synthetic dataset to visualize underfitting vs. a good fit vs. overfitting.

Lecture 03

The Perceptron & Biological Inspiration

Trains a single perceptron on the AND-gate dataset from scratch, reproducing the lecture's hand-worked weight updates.

Lecture 04

Feedforward Neural Networks & Forward Propagation

A pure-NumPy forward pass function (X·W1+b1 → ReLU → ·W2+b2 → sigmoid) matching the lecture's worked example.

Lecture 05

Activation Functions

Plots sigmoid/tanh/ReLU/Leaky ReLU and their derivatives, and reproduces the sigmoid-vs-tanh gradient-update comparison.

Lecture 06

Probability, Loss Functions & Cross-Entropy

Computes binary cross-entropy on a toy prediction and a manual KL-divergence calculation between two discrete distributions.

Lecture 07

Gradient Descent & Stochastic Gradient Descent

Reproduces the convergent (η=0.1) and divergent (η=1.1) gradient-descent runs on L(w)=(w−3)², plus a mini-batch GD demo.

Lecture 08

Backpropagation: The Core Algorithm

Full from-scratch backprop implementation reproducing the lecture's exact worked forward+backward pass and a 200-step training loop.

Lecture 09

Advanced Optimizers

Computes one update step under plain SGD, Momentum, AdaGrad and Adam from the same starting point, matching the lecture's comparison.

Module B Evaluation & Practical Implementation

Lecture 10

Evaluation Metrics

Reproduces every metric worked example on the page — MSE/MAE, two confusion matrices, and the full 21-row ROC/PR threshold scan.

Lecture 11

Building Neural Networks in Python

The same architecture built two ways: a hand-derived NumPy training loop, and the equivalent Keras/TensorFlow model.

Module C Convolutional Neural Networks

Lecture 12

CNNs: Motivation & Architecture

Reproduces the MLP parameter-explosion numbers, the conv filter-bank parameter formula, and the 1×1-conv channel-reduction example.

Lecture 13

Convolution, Padding, Stride & Pooling

Implements the output-size formula, the exact 4×4 max-pooling example, and the Sobel edge-detection worked example.

Lecture 14

CNN in Practice

A complete, runnable Keras CNN for MNIST (Conv→Pool→Conv→Pool→Flatten→Dense→Softmax), the instructor's own layer sizes.

Module D Sequence Models

Lecture 15

Recurrent Neural Networks

A scalar RNN forward pass reproducing h₁, h₂, h₃ from the lecture, showing the same weights reused at every timestep.

Lecture 16

Vanishing/Exploding Gradients

Multiplies chains of <1 and >1 gradient factors to show, numerically, how a long BPTT chain vanishes or explodes.

Lecture 17

LSTM Networks: Gates & Memory

One full LSTM cell timestep in NumPy — forget/input/candidate/output gates — reproducing the lecture's exact numeric walkthrough.

Lecture 18

LSTM Variants

A Keras Bidirectional(LSTM) layer plus an illustrative encoder-decoder skeleton showing how the pieces connect.

Full trainable seq2seq-with-attention tutorial: TensorFlow — NMT with Attention (Colab-enabled) ↗
Lecture 19

Word Embeddings & Tokenization

Byte Pair Encoding merge-training implemented from scratch on the instructor's own corpus (huggingface, hugging, face, hug, …).

Module E Attention & Transformers

Lecture 20

Attention & Self-Attention (Transformers)

A complete, seeded NumPy implementation of scaled dot-product self-attention — Q/K/V projection, scaled softmax, weighted-sum output.

Module F Unsupervised & Energy-Based Models

Lecture 21

Self-Organizing Maps & K-Means

Reproduces the competitive-learning winner-update example and a from-scratch K-means loop on a small synthetic 2D dataset.

Lecture 22

Boltzmann Machines, EBMs & DBNs

One full Contrastive Divergence (CD-1) training step on a tiny 2-visible/1-hidden RBM, reproducing every number in the lecture exactly.

Module G Autoencoders

Lecture 23

Autoencoders: Architecture & Training

A linear autoencoder forward pass (clean + masked-noise denoising), reproducing MSE≈0.1444/0.1921, plus a KL sparsity-penalty snippet.

Lecture 24

Advanced Autoencoders & Applications

Computes the contractive penalty (Jacobian Frobenius norm, reproduces 0.29) plus a Keras Conv2D/Conv2DTranspose autoencoder skeleton.