四川大学国际课程周

SICHUAN UNIVERSITY UIP 2022

学习资料专区

教师 Teacher

T Huiru Zheng
计算机学院

推荐资源 Recommended Material

课程名称 Course Title

Machine Learning

"This course provides an introduction to the key concepts of machine learning (ML) and its applications in Bioinformatics for second- or third-year students who are interested in multidisciplinary research and applications. The course will not have any prerequisites. It will equip students with essential machine learning skills and allow them exploring a new career or research area in the future. Practical examples will be used to demonstrate the concept, algorithms and real-world applications. AIMS: To introduce the fundamentals of ML, including knowledge representation, modelling, learning and evaluation; To develop the capability in applying the knowledge and tools to build ML models for various types of problems in computational biology; To develop the skills for solving problems in Bioinformatics using ML TEACHING FORMAT: Lectures will be delivered in Jupyter Notebooks; Scikit-learn and python will be used in lectures, practicals, and assessments LEARNING OUTCOMES: Successful students will be able to:Demonstrate understanding of the fundamentals in the core areas of ML such as knowledge representation, modelling, learning and evaluation;Develop ML models for various types of problems in Bioinformatics including classification and clustering; and evaluate them using a metric of choice;Employ ML techniques to solve practical problems in the real word;Exercise self-motivation and original thinking. "

课程大纲 Course Outline

"1. Introduction to Machine learning - The machine learning core concepts, workflow, design and analysis of machine learning experiments 2. Supervised learning - Introduction to classification - Classification algorithms - Data preprocessing and feature selection - Assessing classification performance 3. Unsupervised learning - Introduction to clustering - Clustering algorithms (K-means, K-means++, Hierarchical Clustering, Density Based Clustering) - Data preprocessing, feature selection and Dimensionality reduction - Cluster validity and evaluation 4. Ethical AI and Explainable AI 5. Practicals: - Exercises involving Scikit -learn"