Course overview
This introductory course aims to equip students with a foundational understanding of Artificial Intelligence (AI) and Machine Learning (ML) through the practical application of algorithms using Python. Students will explore essential pre-deep learning techniques, focusing on implementing and interpreting AI and ML models, and understanding evaluation metrics. The course covers topics such as data preprocessing, supervised learning algorithms like regression and classification, unsupervised learning techniques such as clustering, and a basic introduction to neural networks. Designed to prepare students for advanced studies in deep learning, this course will enable them to apply, assess, and refine ML algorithms effectively, setting a robust foundation for tackling more complex AI challenges in future endeavours.
- Foundations Of Ai And Supervised Learning
- Model Evaluation And Advanced Learning Techniques
- Unsupervised Learning And Neural Networks
Course learning outcomes
- Comprehensive understanding of AI and ML principles, including basic Python applications
- Proficiency in data preprocessing techniques (handling missing data, normalization, feature engineering)
- Ability to critically assess ML models using evaluation metrics and techniques to address overfitting/underfitting
- Capability to develop, apply, and tune supervised learning algorithms to real-world data
- Mastery of unsupervised learning methods and their applications to discover patterns in data
- Basic understanding of neural network architectures and their applications