This module provides an introduction to the theory and implementation of neural networks and an understanding of the important computational neural network architecture and methodology. It aims to give students sufficient knowledge to enable employment or postgraduate study involving neural networks.
This module provides an introduction to the theory and implementation of neural networks, both biological and artificial. It aims to give students sufficient knowledge to enable employment or postgraduate study involving neural networks.
This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.
Introduction: What Is a Neural Network; Biological Neural Networks; Basic Principles of Artificial Neural Networks; Basic Terminology and Notation; Different Types of Neural Networks; AI Tasks in Neural Networks; Pre-Stage: Creating the Network.
Single-Layer Perceptron: McCulloch-Pitts Neuron; Definition of Perceptron; Weights, Bias, Node, Activation Functions; Perceptron Case Study: Digital Number Recognition; Mimic Logic Operations (AND, OR, NOT); XOR Linear Inseparability Problem.
Multi-Layer Forward Propagation: Representation of Multi-Layer Neural Networks; Predicting Multi-Layer Neural Network Output; Common Nonlinear Activation Functions; How to Choose an Activation Function for Your Model; Forward Propagation for Deep Neural Networks; Vectorisation
Loss Function & Gradient Descent: Different Loss Functions (e.g., MAE, MSE, Cross Entropy Loss); 1D & 2D Forms of Gradient Descent Methods; Variations of Gradient Descent (e.g., Momentum, RMSProp, Adam); Saddle Points; Gradient Descent vs. Newton Method; Stochastic & Mini-Batch Gradient Descent
Backpropagation: Computation Graph; Matrix Calculus Revisited; Backpropagation in Logistic Regression; Backpropagation in Multi-Layered NNs; Vanishing Gradient Problems
Overfitting & Regularization: Bias and Variance; What is Regularization; How does Regularization help in Reducing Overfitting; Different Regularization Techniques (e.g., L1 and L2 Regularization, Dropout, Data Augmentation, Early Stopping)
Recurrent Neural Network: Sequence Model; One-hot Representation; Forward and Backward Propagations; Different Types of Recurrent Neural Networks; Bidirectional Recurrent Neural Network; Vanishing & Exploding Gradient Problems; Gated Recurrent Units (GRU); Long Short-Term Memory Networks (LSTM)
Making Your Own Neural Network from Scratch: The Tools You Will Need
Recent Advances in Neural Networks (Optional): Structural Similarity Search, Graph Embedding, Time Series Analysis
By the end of the module, students should be able to:
Michael Taylor. Make Your Own Neural Network: An In-Depth Visual Introduction for Beginners. Amazon Digital Services LLC - Kdp Print Us, 2017, ISBN: 1549869132, 9781549869136
Graupe Daniel. Principles of Artificial Neural Networks: Basic Designs to Deep Learning (4th Edition). World Scientific, 2019, ISBN: 9811201242, 9789811201240
James Loy. Neural Network Projects with Python: The ultimate guide to using Python to explore the true power of neural networks through six projects, Packt Publishing Ltd, 2019, ISBN: 1789133319, 9781789133318
tbc
tbc
Type | Required |
---|---|
Lectures | 30 sessions of 1 hour (20%) |
Private study | 120 hours (80%) |
Total | 150 hours |
Private study, background reading and revision
No further costs have been identified for this module.
You do not need to pass all assessment components to pass the module.
Students can register for this module without taking any assessment.
Weighting | Study time | |
---|---|---|
assignment | 20% | |
On-campus Examination | 80% | |
CS331 Examination ~Platforms - AEP
|
Weighting | Study time | |
---|---|---|
In-person Examination - Resit | 100% | |
CS331 resit Examination
|
Individual written feedback on coursework
This module is Optional for:
This module is Option list A for:
This module is Option list B for: