Lectures, Practicals, Coursework.

Foundations of deep learning and learning in nature,
PyTorch programming, Designing deep neural network architectures,
Adversarial models, Energy-based models and Flow models,
Sequential models and Transformers, Generalisation theory

• Code: https://github.com/atapour/dl-pytorch
• Video Playlist: https://www.youtube.com/playlist?list=PL2r9oIU-8q1DnJWrzS30daRjvePyLom4G

Lectures, Practicals, Coursework.

Introduction to Image Processing, Applications and limitations of Image Processing,
Local Transforms, Point Transforms, Contrast Enhancement, Noise and Filtering,
Spatial Filtering, Histograms, Histogram Equalisation, CLAHE, Global Transforms,
Fourier Domain, Fourier Transform, High/Low/Band Pass Filtering, Colours,
Colour Spaces, Colour Processing, Discrete Cosine Transform, Image Compression.

• Code: https://github.com/atapour/ip-python-opencvh
• Video Playlist: https://www.youtube.com/playlist?list=PL2r9oIU-8q1APr8ZUDkwtl7GZ0VJkO6tx

Lectures, Practicals, Coursework.

UNIX/Linux and C, Intro, HelloWorld, Compiling, Pre-processor,
Control flow and functions, Data types, structs and unions,
Memory access using pointers, Dynamic memory management,
Scope of variables and recursive functions, Debugging,
Large programs and external libraries, Intro to C++.

PhD Supervision.

Research Projects:

• Off-road Autonomous Navigation
• On-Vehicle BCI
• Image Inpainting Methods and Applications
• 3D Sensing via 360 Panoramic Images

UG and MSc Supervision.

Machine Learning Projects, including:

• Predicting Video Game Outcome and Player Rankings
• Anomaly Detection
• Ocular Symmetry for MS Diagnosis

PhD Supervision.

Research Projects:

• Analysis of Different Machine Learning and Inference Methodologies on Edge Devices
• Temporal Graph Representation and Comparison
• Multi-Task Learning
• Neural Architecture Search

MSc Supervision.

Machine Learning Projects, including:

• AI and Dermatology
• Bias Removal in Skin Lesion Identification
• Image-to-Image Translation
• Detecting Clouds in Satellite Images
• Segmenting Marine Life Images
• Fake News Classification using Transformers
• Mobile Use Driving Violation Detection
• Banking Data Modelling
• Analysis of Synthetic Environments for RL-Based Driving
• Improved Knowledge Graph Building using Transformers
• Bias Removal in Semantic Segmentation
• Fine-Grained Classification using Limited Data

Dissertation Supervision.

Machine Learning Projects:

• Image Colourisation
• Deep Learning for Image Inpainting
• Diagnosing the Parkinson’s Disease

Lectures, Practicals, Coursework.

What is Deep Learning? Applications of Deep Learning, Loss functions and Backpropagation, training and optimisation,
Classification/Regression, Convolutional Neural Networks, Computer Vision applications, Recurrent Neural Networks,
Natural Language Processing applications, Improved training and performance of neural networks, Generative models,
Ethics and challenges of Deep Learning, Deep Reinforcement Learning, embeddings and Representation Learning.

Practicals.

Software development practices, requirements discovery and analysis, software Design, testing, human computer interaction, software quality and process, project management, etc.

Practicals.

Artificial Intelligence Search: heuristic searches, local searches, simulated annealing, genetic algorithms, etc.
Graphics: 3D graphics construction, rendering, modelling, transformation, shading, texture mapping, OpenGL, etc.
Digital Communication: entropy, information theory, lossless compression, encryption algorithms, etc.
Image Processing: transformation functions, histograms, spatial linear and nonlinear filters, JPEG, colour spaces, etc.

Practicals.

Systems programming: C, Bash, etc.
Functional programming, Haskell.
Object oriented programming: Java, Python.
Web Programming: HTML, JavaScript, PHP.

Practicals.

Real-Time Systems, C.

Lectures and Practicals.

C, C++, Java.

Lectures.

Concepts and principles, design, automation systems and enterprise planning.

Lectures and Coursework.

Introduction, architecture, lexical and syntax analysis, parsing methods, error recovery, semantic analysis, run-time environments, etc.

Lectures and Coursework.

Stochastic search methods, combinatorial optimisation, soft-computing methods, principles of machine learning, neural networks, image processing and computer vision, etc.

Lectures.

Graduate level course for computer science students.