STATS 102B
Introduction to Computation and Optimization for Statistics
Description: Lecture, three hours; discussion, one hour. Requisites: courses 100B, 102A, Mathematics 33A. Introduction to computational methods and optimization useful for statisticians. Use of computer programming to solve statistical problems. Topics include vector/matrix computation, multivariate normal distribution, principal component analysis, clustering analysis, gradient-based optimization, EM algorithm for missing data, and dynamic programming. P/NP or letter grading.
Units: 4.0
Units: 4.0
1 of 1
Most Helpful Review
Spring 2024 - Great class. Good professor, though slightly overrated in my opinion (but I'd definitely take him again lol). Odd tests. This is basically a ML class (less intensive maybe as CS). He uses his slides and explains well. He records it too. We learn the standard algos like KNN, K means, Neural nets, EM algorithm, Bayes classifier, SVM, PCA and their math behind it. He teaches the concepts well and makes it extremely concise (dims it down to make it simple to understand, maybe too simple). His homeworks are heavily weighted, so make sure to finish them well. 6 of them, each being 6%. The view quiz this quarter changed such that he'd provide the last one after the recording stopped to incentivize people to come in person. The tests are pretty weird. They are easy and seem like high school style. The thing is he doesn't give much partial credit at all. And since the style is like high school, some questions about machine learning and long math calculations are all for a fill-in-the-blank. And so even with your work, you can end up getting 0. So double check your work.
Spring 2024 - Great class. Good professor, though slightly overrated in my opinion (but I'd definitely take him again lol). Odd tests. This is basically a ML class (less intensive maybe as CS). He uses his slides and explains well. He records it too. We learn the standard algos like KNN, K means, Neural nets, EM algorithm, Bayes classifier, SVM, PCA and their math behind it. He teaches the concepts well and makes it extremely concise (dims it down to make it simple to understand, maybe too simple). His homeworks are heavily weighted, so make sure to finish them well. 6 of them, each being 6%. The view quiz this quarter changed such that he'd provide the last one after the recording stopped to incentivize people to come in person. The tests are pretty weird. They are easy and seem like high school style. The thing is he doesn't give much partial credit at all. And since the style is like high school, some questions about machine learning and long math calculations are all for a fill-in-the-blank. And so even with your work, you can end up getting 0. So double check your work.
Most Helpful Review
Spring 2020 - I don't say this lightly. She is by far the worst teacher of knowledge I've ever witnessed in my entire life, perhaps throughout the entire existence of human history. She is, without a doubt, 95% of the reason for my crippling depression. The other 5% is the death of my dog. You heard it right folks, she makes me 19 times more depressed than the death of my dog. Her homework ruins my days, make me fall into an existential crisis and makes me cry. I truly cannot tell you this feeling of dread I experience thinking about her class, it's a feeling I hope none of you reading this will ever need to experience.
Spring 2020 - I don't say this lightly. She is by far the worst teacher of knowledge I've ever witnessed in my entire life, perhaps throughout the entire existence of human history. She is, without a doubt, 95% of the reason for my crippling depression. The other 5% is the death of my dog. You heard it right folks, she makes me 19 times more depressed than the death of my dog. Her homework ruins my days, make me fall into an existential crisis and makes me cry. I truly cannot tell you this feeling of dread I experience thinking about her class, it's a feeling I hope none of you reading this will ever need to experience.
AD
1 of 1
