Course ID:  M57013R6

Credits: 3

Objective: 

Artificial intelligence (AI) has advanced modern biology and medicine. The goal of this course is to teach computational scientists and biomedical scientists the AI methods used in modern biomedicine. This course primarily focuses on the fundamentals of machine learning methods, which can be applied to biological and medical data.

Course Prerequisites: Linear algebra and Programming experiences are required

Outline:

1. Introduction to artificial intelligence and biomedical applications 

2. Model performance measurement 

3. Supervised learning: regression analysis, logistic regression 

4. Supervised learning: recurrent neural networks 

5. Supervised learning: transformers 

6. Unsupervised learning: K-means, expectation-maximization 

7. Unsupervised learning: generative models 

8. Reinforcement learning 

9. Genomics and biomedical databases 

10. Genomics and biomedical DB: next-generation sequencing 

11. Applications of deep neural networks in biomedicine 

12. Language-based artificial intelligence methods: word embeddings 

13. Biomedical data visualization: t-SNE 

14. Biomedical image processing: convolutional neural networks 

15. Artificial intelligence assisted medical decision making 

16. Final report

Teaching Method:  

Class Notes  

Journal articles  

Homework

Reference:  

•  B. Alberts, A. Johnson, J. Lewis, D. Morgan, and M. Raff Molecular Biology of the Cell. W. W. Norton & Company, 2014.  

• C.M. Bishop Pattern Recognition and Machine Learning. Springer, 2011.  

• D.S. Sivia and J. Skilling Data Analysis: A Bayesian Tutorial. Oxford, 2006.