STATS M231A
Pattern Recognition and Machine Learning
Description: (Same as Computer Science M276A.) Lecture, three hours; discussion, one hour. Designed for graduate students. Fundamental concepts, theories, and algorithms for pattern recognition and machine learning that are used in computer vision, image processing, speech recognition, data mining, statistics, and computational biology. Topics include Bayesian decision theory, parametric and nonparametric learning, clustering, complexity (VC-dimension, MDL, AIC), PCA/ICA/TCA, MDS, SVM, boosting. S/U or letter grading.
Units: 4.0
Units: 4.0
1 of 1
Most Helpful Review
Winter 2024 - Loved this class. The professor is super clear and concise in explaining difficult concepts, and it was the first presentation of machine learning concepts where I felt like I truly understood. We went over the basics including linear regression and perceptrons, but we also talked about more recent models including the architecture of diffusion models, transformer models, and even SORA. Homeworks include theory problems, which are fine if you pay attention to the lectures, and some coding problems to get some practice with the theory. The final exam was essentially like the last homework. Definitely recommend this class to anyone who's interested in learning more deeply about machine learning models.
Winter 2024 - Loved this class. The professor is super clear and concise in explaining difficult concepts, and it was the first presentation of machine learning concepts where I felt like I truly understood. We went over the basics including linear regression and perceptrons, but we also talked about more recent models including the architecture of diffusion models, transformer models, and even SORA. Homeworks include theory problems, which are fine if you pay attention to the lectures, and some coding problems to get some practice with the theory. The final exam was essentially like the last homework. Definitely recommend this class to anyone who's interested in learning more deeply about machine learning models.
AD
1 of 1
