All courses

Intermediate · module I6

Neural Networks and Deep Learning Essentials

By the end: Explain how a neural network learns, train a small network, and describe what CNNs, RNNs and Transformers are used for

Start here
Covers
How neural networks work and learn, and the main deep learning architectures, with hands-on simulators
Contents
4 chapters, 16 topics
Time
About 3 hours
Level
Intermediate
Your progress
0 / 16

This module builds on Machine Learning Foundations. We suggest looking at it first, but the choice is yours.

Chapter 1 From Neuron to Network

  1. 1.1

    Biological and Artificial Neurons

    What the brain inspired, and what a computer neuron actually computes

    Interactive: one neuron, three dials

    y = f(w·x + b)

    10 min Activity
  2. 1.2

    The Perceptron

    Weights, bias and a threshold, and the XOR problem

    Interactive: separate two groups with a line

    10 min Read Activity
  3. 1.3

    Activation Functions

    Sigmoid, tanh, ReLU and softmax, and why they are needed

    Interactive: compare activation curves

    ReLU(x) = max(0, x)

    10 min Read
  4. 1.4

    Layers and Network Architecture

    Input, hidden and output layers, and depth

    Interactive: build a network layer by layer

    12 min Activity

Chapter 2 How Networks Learn

  1. 2.1

    Forward Propagation and Loss

    Producing a prediction and measuring its error

    Interactive: trace numbers through a network

    10 min Read
  2. 2.2

    Backpropagation and Gradient Descent

    Sending the error backwards to adjust every weight

    Interactive: watch weights update

    12 min Read
  3. 2.3

    Epochs, Batches and Learning Rate

    The settings that control training

    Interactive: train with different learning rates

    10 minBeing written
  4. 2.4

    Overfitting, Dropout and Regularisation

    Keeping a network from memorising

    Interactive simulator

    10 minBeing written

Chapter 3 Deep Learning Architectures

  1. 3.1

    Convolutional Neural Networks

    How networks find edges, shapes and objects in images

    Interactive: apply image kernels

    12 min Activity
  2. 3.2

    Recurrent Neural Networks and LSTMs

    Networks with memory for sequences

    Interactive: predict the next letter

    10 minBeing written
  3. 3.3

    Attention and Transformers

    How a model decides which words matter, the idea behind every LLM

    Interactive: attention heat map

    12 minBeing written
  4. 3.4

    Transfer Learning and Pre-Trained Models

    Reusing a trained model for a new task

    Code: classify images with a pre-trained model

    12 minBeing written

Chapter 4 Building Networks

  1. 4.1

    Training a Network Without Code

    Exploring networks in a visual simulator

    Lab: neural network playground

    12 min Activity
  2. 4.2

    Your First Network in Keras

    Building, training and evaluating a small network

    Code: a digit recogniser

    20 minBeing written
  3. 4.3

    Limits of Deep Learning

    Data hunger, cost, explainability and brittleness

    Discussion

    6 minBeing written
  4. 4.4

    Module Review and Assessment

    Exercises and a scored quiz

    Graded quiz and lab

    15 minBeing written