Course details
- Duration: 7 x 1.5 hours live lectures delivering via Microsoft Teams with group discussions and questions.
Web based exercises and quizzes will be provided for formative feedback.Group projects for assessing the learning outcomes, supported by 5 x 1 hour tutorials.
1 x 2 hour session on final day for project presentation.
Total learning hours: 17.5 hours
Learn from Imperial’s Data Science Institute experts live online!
Everyone knows data is essential, but society still needs to gain the skills and tools to understand large datasets. Humans and AI applications are producing more data than ever, so it becomes more important to process the data and draw the right conclusion by understanding the limitations of your models.
This master class will give participants an understanding of these technologies and apply the knowledge and learning experience to design and develop machine learning techniques specific to real-world datasets. The course also focuses on advanced Machine Learning techniques drawn from the hands-on research experience of the presenters.
Topics covered include:
- Introduction to machine learning: This will be a hands-on guide on dealing with data for a typical machine learning pipeline, plus advanced skills required to process data effectively.
- Computer vision and applications: Focus on the latest advancements in computer vision and understand how all these techniques can be applied to various applications, including healthcare.
- Text data: To process text data efficiently and understand the basics of text data analysis.
- Data learning: To approach using data assimilation techniques integrated with machine learning to solve complex data-driven problems.
Live classes will be delivered on weekdays.
Project work will be done through team-based learning and tutorials. Final projects will be presented in groups on the last day of the programme. A prize will be awarded to the team with the best project.
The programme will be delivered over Microsoft Teams. Online project channels will be allocated to each team for project work. Students will be able to use the channel at any time to work on their project.
The entire programme will be taught in English.
More information
On completion of this masterclass, you’ll be able to:
- Process and produce an advanced Machine Learning pipeline.
- Understand structure of an efficient Machine Learning algorithm that can be used for text and image processing, as well as Data Learning.
- Apply the knowledge and experience gained to develop a Machine Learning project and understand the performance metrics.
- Evaluate uncertainty and noise in big data systems and propose methods to reduce the errors propagation.
- Evaluate, select, and apply models and technologies to perform data learning.
- Design strategies to manage big data for real world forecasting models using data compressions and data decompressions.
This masterclass is designed for undergraduate or postgraduate students studying in a technical subject, e.g. Engineering, Computing, Software Engineering, Math, Physics or related disciplines.
English requirements:
All students are required to have a good command of English, and if it is not their first language, they will need to satisfy the College requirement as follows:
a minimum score of IELTS (Academic Test) 6.5 overall (with no less than 6.0 in any element) or equivalent.
- TOEFL (iBT) 92 overall (minimum 20 in all elements)
- CET- 4 (China) minimum score of 550
- CET- 6 (China) minimum score of 520
Technical requirements:
All students are expected to already have basic Artificial Intelligence and Machine learning knowledge and have a good level of Python, with a good understanding of statistics and numerical processing.
Students will need to have access to a computer with a webcam, microphone and good internet connection to attend the live classes.
Students will receive a verified Imperial College London digital certificate on successful completion of this masterclass and a prize will be awarded to the best project team. Each student will also receive a transcript for their project marks.