Morning 9:30 - 12:00
Afternoon 13:00 - 17:00
- Understand basic concept of machine learning, including supervised/unsupervised learning, clustering, classification, regression, and evaluation metrics.
- Identify proper model for different machine learning tasks
- Train a classifier with scikit learn
- Understand what Large Language Model is and how to apply it in text mining
Jupyter Notebook for live examples, Breast Cancer Wisconsin Dataset for hands-on
9:30 – 10:30 Machine Learning 101
- What is Machine Learning
- Applications in health data science
- Unsupervised learning: clustering
- Supervised learning
- Linear regression: the difference in purpose compared to the usage in statistic
- Classification: binary and multiple classification
10:30 – 10:45 Break
10:45 – 12:00 Classification and Scikit-Learn
- Scikit-Learn for Machine Learning: train and predict with classification examples
- General idea of how to choose a model
- How to evaluate a machine learning model
- Introducing the hands-on exercise: using scikit-learn for cancer prediction
12:00 - 13:00 Lunch break
13:00 – 15:00 Hands-on: using scikit-learn for cancer prediction with Breast Cancer Wisconsin (Diagnostic) Dataset
15:00 – 15:30 Break
15:30 – 17:00 Large Language Model and Prompt Engineering
- What is large language model?
- The difference between traditional Machine learning models and LLM
- Existing protocols for creating a prompt
- How to use Llama-2-7b for systematic review study screening on Google Colab