Machine Learning in Bioinformatics

BIOMATH M226 - Machine Learning in Bioinformatics

HUM GEN M226 - Machine Learning in Bioinformatics

BIOINFO M226 - Machine Learning in Bioinformatics

<p>(Formerly numbered M226.) Lecture, four hours; outside study, eight hours. Enforced requisite: course 32 or Program in Computing 10C with grade of C– or better. Recommended: one course from Biostatistics 100A, 110A, Civil Engineering 110, Electrical and Computer Engineering 131A, Mathematics 170A, or Statistics 100A. Familiarity with probability, statistics, linear algebra, and algorithms expected. Designed for engineering students as well as students from biological sciences and medical school. Biology has become data-intensive science. Bottleneck in being able to make sense of biological processes has shifted from data generation to statistical models and inference algorithms that can analyze these datasets. Statistical machine learning provides an important toolkit in this endeavor. Biological datasets offer new challenges to the field of machine learning. Examination of statistical and computational aspects of machine learning techniques and their application to key biological questions. Letter grading.</p>

Computer Science

Henry Samueli School of Engineering and Applied Science

Container 1

COM SCI 226 - Machine Learning in Computational Genomics

Machine Learning in Computational Genomics

Students will learn about probabilistic models, efficient inference and learning in these models, model assessment, and interpreting the inferences to address the biological question at hand. The course will enable students to formulate the biological question as problems in statistical inference, to understand the assumptions and tradeoffs underlying these formulations, to find or develop efficient inference algorithms and to assess the quality of their inferences.

A second goal is to get students started on independent research. An open-ended research project will form a major part of the course.

General Catalog

Machine Learning in Computational Genomics

COM SCI 226

4 units