## BIOMEDIN 215: Data Driven Medicine

With the spread of electronic health records and increasingly low cost assays for patient molecular data, powerful data repositories with tremendous potential for biomedical research, clinical care and personalized medicine are being built. But these databases are large and difficult for any one specialist to analyze. To find the hidden associations within the full set of data, we introduce methods for data-mining at the internet scale, the handling of large-scale electronic medical records data for machine learning, methods in natural language processing and text-mining applied to medical records, methods for using ontologies for the annotation and indexing of unstructured content as well as semantic web technologies. Prerequisites:
CS 106A; familiarity with statistics and biology. Highly recommended:
STATS 216. Recommended: one of
CS 246,
STATS 305, or
CS 229.

Terms: Aut
| Units: 3

## CS 224D: Deep Learning for Natural Language Processing

Deep learning approaches have obtained very high performance across many different natural language processing tasks. In this class, students will learn to understand, implement, train, debug, visualize and potentially invent their own neural network models for a variety of language understanding tasks. The course provides a deep excursion from early models to cutting-edge research. Applications will range across a broad spectrum: from simple tasks like part of speech tagging, over sentiment analysis to question answering and machine translation. The final project will involve implementing a complex neural network model and applying it to a large scale NLP problem. We will introduce a common programming framework for deep learning for the problem sets.Prerequisites: programming abilities (python), linear algebra,
Math 21 or equivalent, machine learning background (
CS 229 or similar) Recommended:
CS 224N,
EE364a (convex optimization),
CS 231N

Terms: Spr
| Units: 3-4

Instructors:
Socher, R. (PI)
;
Bagadia, S. (TA)
;
Dindi, D. (TA)
;
Hong, J. (TA)
;
Ramsundar, B. (TA)
;
Yan, Q. (TA)
;
arivazhagan, N. (TA)

## CS 229: Machine Learning (STATS 229)

Topics: statistical pattern recognition, linear and non-linear regression, non-parametric methods, exponential family, GLMs, support vector machines, kernel methods, model/feature selection, learning theory, VC dimension, clustering, density estimation, EM, dimensionality reduction, ICA, PCA, reinforcement learning and adaptive control, Markov decision processes, approximate dynamic programming, and policy search. Prerequisites: linear algebra, and basic probability and statistics.

Terms: Aut, Spr
| Units: 3-4

Instructors:
Duchi, J. (PI)
;
Ng, A. (PI)
;
Ahluwalia, V. (TA)
;
Ahres, Y. (TA)
;
Alban-Hidalgo, M. (TA)
;
Anenberg, B. (TA)
;
Bahtchevanov, I. (TA)
;
CHU, H. (TA)
;
Corbett-Davies, S. (TA)
;
Donnat, C. (TA)
;
Du, Y. (TA)
;
Friedberg, R. (TA)
;
Guu, K. (TA)
;
Haque, A. (TA)
;
How, P. (TA)
;
Ishfaq, H. (TA)
;
Iyer, K. (TA)
;
Jiang, X. (TA)
;
Kaplow, I. (TA)
;
Lim, D. (TA)
;
Lin, Y. (TA)
;
Martinez, A. (TA)
;
McCann, B. (TA)
;
Parthasarathy, N. (TA)
;
Qin, J. (TA)
;
Rosenman, E. (TA)
;
Samar, A. (TA)
;
Sesia, M. (TA)
;
Sun, Y. (TA)
;
Tsai, S. (TA)
;
Turan, D. (TA)
;
Vyas, S. (TA)
;
Wang, H. (TA)
;
Zhou, L. (TA)
;
Zhu, M. (TA)

## CS 229T: Statistical Learning Theory (STATS 231)

(Same as
STATS 231) How do we formalize what it means for an algorithm to learn from data? This course focuses on developing mathematical tools for answering this question. We will present various common learning algorithms and prove theoretical guarantees about them. Topics include online learning, kernel methods, generalization bounds (uniform convergence), and spectral methods. Prerequisites: A solid background in linear algebra and probability theory, statistics and machine learning (
STATS 315A or
CS 229). Convex optimization (
EE 364a) is helpful but not required.

Terms: Win
| Units: 3

## STATS 231: Statistical Learning Theory (CS 229T)

(Same as
STATS 231) How do we formalize what it means for an algorithm to learn from data? This course focuses on developing mathematical tools for answering this question. We will present various common learning algorithms and prove theoretical guarantees about them. Topics include online learning, kernel methods, generalization bounds (uniform convergence), and spectral methods. Prerequisites: A solid background in linear algebra and probability theory, statistics and machine learning (
STATS 315A or
CS 229). Convex optimization (
EE 364a) is helpful but not required.

Terms: Win
| Units: 3

Filter Results: