Advanced Machine Learning for the Biomedical Sciences II
Spring 2023 (3 units)
Will not be taught during 2023-2024 academic year.
This course builds upon the introduction to machine learning taught in Machine Learning in R for the Biomedical Sciences: Methods for Prediction, Pattern Recognition, and Data Reduction (BIOSTAT 216) to provide a deeper mathematical and statistical understanding of machine learning algorithms. The applied focus is on solving problems of prediction, pattern recognition and data reduction in the biomedical sciences, but other applications will also be mentioned. Instruction includes how to manipulate and customize popular machine learning algorithms to best satisfy specific research needs. The R software environment will be used throughout.
Objectives
The objectives for this course are for participants to:
- Understand mathematical and statistical foundations of several contemporary machine learning algorithms;
- Select among available machine learning algorithms to identify the most appropriate for a given research question; and
- Apply and customize state-of-the-art machine learning algorithms to tabular data, biomedical imaging data, sequence data, and time series to address research questions in the biomedical sciences.
Prerequisites
- Introduction to Computing in the R Software Environment (BIOSTAT 213), or equivalent experience;
- Machine Learning in R for the Biomedical Sciences: Methods for Prediction, Pattern Recognition, and Data Reduction (BIOSTAT 216), or equivalent experience; and
- Biostatistical Methods for Clinical Research II (BIOSTAT 208), or equivalent experience.
Faculty
| Course Director: |
Associate Professor, Radiation Oncology |
Format
Each week, new material is introduced via recommended reading and interactive lectures, lasting between 60 to 90 minutes, in which discussion is encouraged. Homework assignments, designed to reinforce the core concepts, will be given every other week. The philosophy of the course is to steadily build a knowledge base over the course of the academic quarter, and that ample time is needed between each new installment of material to optimize comprehension.
Lectures
Content: Introduction of new material. Interaction and discussion are encouraged. Lecture recordings will be available online later in the day.
Time: Thursdays, 1:15 to 2:45 PM.
Large Group Discussion
Time: Thursdays, 2:45 to 4:15 PM.
The syllabus for the quarter shows dates and times for all activities.
Materials
Pattern Recognition and Machine Learning by B. Christopher. Springer Publishers. 2007.
The Elements of Statistical Learning: Data Mining, Inference, and Prediction by H. Trevor, T. Robert and F. Jerome. Springer Publishers. 2nd Edition. 2009.
Books may be purchased either through the publisher or a variety of commercial venues (e.g., Amazon.com).
Software
R
Rstudio
All course materials and handouts will be posted on the course's syllabus.
Grading
Grades will be based on total points achieved on the homework assignments (65%) and final project (35%). Any homework turned in late will be penalized 25% of possible points. Please note that late final projects are not accepted.
Students not in full-year TICR Programs who satisfactorily pass all course requirements will receive a Certificate of Course Completion.
Only UCSF students (defined as individuals enrolled in UCSF degree or certificate programs) will receive academic credit for courses. Official transcripts are available to UCSF students only. A Certificate of Course Completion will be available upon request to individuals who are not UCSF students and satisfactorily pass all course requirements.
To Enroll
ATCR and MAS students use the Student Portal
Students taking individual courses:
Course Fees
How to pay (please read before applying)
Only one application needs to be completed for all courses desired during the quarter.
Spring 2023 Course Schedule. Spring 2024 schedule available Feb 1.
Will not be taught during 2023-2024 academic year.