This course provides a foundational understanding of Artificial Intelligence (AI) for students with limited mathematics and computer science backgrounds. It covers essential concepts including data preparation, decision trees, neural networks, and model evaluation. The course is designed to be accessible and practical, focusing on concepts and applications rather than complex mathematics.
1. Data preparation (1.1 Overview of AI applications and impacts. , 1.2 Introduction to data preparation and its importance. , 1.3 Basics of data cleaning, normalisation, and splitting., 1.4 Importance of feature engineering in AI. , 1.5 Techniques for feature extraction and selection. , 1.6 Data normalisation and scaling methods.)
2. Decision Trees (2.1 Basics of decision tree algorithms. , 2.2 Understanding tree structures and nodes. , 2.3 Implementing decision trees: i.e. ID3, C4.5, and CART algorithms. , 2.4 Pruning techniques for decision trees. , 2.5 Ensemble methods: Random Forests and Gradient Boosting Machines. , 2.6 Advantages and limitations of decision trees and ensemble methods.)
3. Neural Networks (3.1 Basics of neural networks and their architecture. , 3.2 Understanding neurons, activation functions, and layers. , 3.3 Introduction to feedforward neural networks. , 3.4 Understanding backpropagation and gradient descent. , 3.5 Training neural networks: epochs, batch size, and learning rates. , 3.6 Overfitting and regularisation techniques e.g., dropout, L2 regularisation. , 3.7 Overview of popular AI tools: TensorFlow, Keras, PyTorch. , 3.8 Introduction to software libraries for decision trees and neural networks. , 3.9 Setting up and using these tools for AI projects.)
4. Evaluation of AI models (4.1 Key evaluation metrics: accuracy, precision, recall, F1 score. , 4.2 Understanding confusion matrices and ROC curves. , 4.3 Model validation techniques: cross-validation and train-test split. , 4.4 Techniques for optimizing AI models. , 4.5 Hyperparameter tuning and grid search. , 4.6 Model selection and evaluation strategies.)
5. Project (5.1 Review and reflection on key concepts and techniques. , 5.2 Integration of learned concepts into a comprehensive AI project. , 5.3 Project planning, implementation, groupwork and presentation tasks.)
By the end of the course, students should be able to do the following:
Curriculum explorer: Click here
SCQF Level: 11
Credits: 15