A remote Machine Learning module for MSc Applied Computational Science & Engineering began on 27 April, led by Prof Olivier Dubrule and Navjot Kukreja
The three week course is attended by approximately 70 students from the Applied Computational Science and Engineering MSc. However, because of the huge interest in Machine Learning, 30 PhD students and staff also were very keen to attend, which was possible thanks to the remote nature of the course. The record of the largest attendance for a course provided by the Earth Sciences and Engineering Department was beaten with an attendance of 99 the first day!
The course, which is performed remotely with Microsoft Teams, alternates days of theory presentation and exercises with days of coding with Python.
The Applied Computational Science and Engineering students are using tools such as Google Colab, Jupyter notebooks and the lectures are made interactive thanks to the use of Microsoft Teams chat. If required, students can also interact on a one-to-one basis with the five Teaching Assistants of the course, Deborah Pelacani-Cruz, Ming Rui Zhang, Andrea Gayon Lombardo, Zainab Titus and Harriet Dawson.
It is also a great learning experience for the instructors. When Olivier teaches, Navjot acts as moderator in the chat to make sure all the questions from students are addressed. Then Olivier becomes the moderator when Navjot teaches.
All the teaching staff finds this experience extremely rewarding, and are pleasantly surprised with what can be achieved. After the first week of teaching, many of the students are also extremely positive about the experience.
This introduction to Machine Learning will cover the following topics:
- Unsupervised and Supervised Machine Learning and Logistic Regression
- Feed-Forward Neural Networks
- Bias and Variance in Neural Networks
- Convolutional Neural Networks
- Recurrent Networks and Probabilities for Deep Learning
- Unsupervised Learning and Generative Networks
Want to study with us?
Find out more on our Applied Computational Science and Engineering MSc page.
Article text (excluding photos or graphics) © Imperial College London.
Photos and graphics subject to third party copyright used with permission or © Imperial College London.