Artificial Intelligence and Machine Learning

MTH1602 Statistics and Probabilities in Computing

3 hours No requisites

MTH2143 Differential equations and Linear Algebra

3 hours No requisites

1 Introduction to AI and Machine Learning / Overview of Artificial Intelligence (AI) and its history / Machine Learning (ML) vs. AI vs. Deep Learning (DL) / Real-world applications of AI and ML / Ethics and societal impact of AI

2 Supervised Learning - Regression / Introduction to supervised learning / Linear regression and its assumptions / Polynomial regression / Gradient descent and optimization / Performance evaluation: RMSE, MAE, R² Score

3 Supervised Learning - Classification / Logistic regression / Decision trees and random forests / Support Vector Machines (SVM) / Evaluation metrics: Precision, Recall, F1-score, AUC-ROC

4 Unsupervised Learning - Clustering / Introduction to unsupervised learning / K-means clustering / Hierarchical clustering / DBSCAN / Evaluating clustering performance

5 Unsupervised Learning - Dimensionality Reduction / Curse of dimensionality / Principal Component Analysis (PCA) / t-SNE and UMAP / Autoencoders for feature extraction

6 Neural Networks and Deep Learning Basics / Biological vs. artificial neurons / Multi-layer perceptron (MLP) / Activation functions: ReLU, Sigmoid, Softmax / Backpropagation and optimization techniques (SGD, Adam)

7 Deep Learning - Convolutional Neural Networks (CNNs) / Basics of image processing / Convolutional layers, pooling layers / Popular architectures: LeNet, AlexNet, VGG, ResNet / Applications of CNNs in computer vision

8 Reinforcement Learning (RL) / Basics of reinforcement learning / Markov Decision Processes (MDP) / Q-learning and Deep Q Networks (DQN) / Policy gradients and actor-critic methods / RL applications in gaming and robotics

9 Model Evaluation, Bias, and Interpretability / Overfitting and underfitting / Bias-variance tradeoff / Explainable AI (XAI) techniques / SHAP and LIME for model interpretability

10 AI Ethics and Fairness / Bias in AI models / Data privacy and security concerns / Regulations and policies in AI (GDPR, AI Act) / Responsible AI and ethical considerations

11 Practical Applications and Real-World Projects / Building an end-to-end ML pipeline / Deploying AI models with Flask, FastAPI, or Streamlit / MLOps and model monitoring / Working with cloud AI services (Google AI, AWS, Azure)

1.1 Mapped to: K1

Understand core AI and ML concepts, including supervised, unsupervised, and reinforcement learning.

Teaching Strategy Lecture, excersise