ML2 - Intermediate Machine Learning
For signups and further details, please contact Ms. Irene Ong Hwei Nee.
This MOOC-style course builds on the ML1 course by extending classical machine learning concepts into a statistical learning framework. It further introduces neural networks and advanced deep learning models, including CNNs and RNNs. The course concludes with a mini-project, enabling students to integrate and apply knowledge gained across both ML1 and ML2 in a practical, problem-solving context.
- The course comprises of 7 lectures (each up to 60 mins long).
- 7 auto-graded programming labs that complement the lectures.
- 1 mini-project.
- The Final Contest will be a Kaggle/Coursemology based competition along with a few MCQs.
- Students are expected to follow the learning flow at their own pace to prepare themselves for the Final Contest.
- Statistics and Bayes Rule
- Statistical Machine Learning
- Neural Networks
- Convolutional Neural Networks (CNN) — Part 1
- Convolutional Neural Networks (CNN) — Part 2
- Recurrent Neural Networks (RNN) — Part 1
- Recurrent Neural Networks (RNN) — Part 2