## BIODS 237: Deep Learning in Genomics and Biomedicine (BIOMEDIN 273B, CS 273B, GENE 236)

Recent breakthroughs in high-throughput genomic and biomedical data are transforming biological sciences into "big data" disciplines. In parallel, progress in deep neural networks are revolutionizing fields such as image recognition, natural language processing and, more broadly, AI. This course explores the exciting intersection between these two advances. The course will start with an introduction to deep learning and overview the relevant background in genomics and high-throughput biotechnology, focusing on the available data and their relevance. It will then cover the ongoing developments in deep learning (supervised, unsupervised and generative models) with the focus on the applications of these methods to biomedical data, which are beginning to produced dramatic results. In addition to predictive modeling, the course emphasizes how to visualize and extract interpretable, biological insights from such models. Recent papers from the literature will be presented and discussed. Students will be introduced to and work with popular deep learning software frameworks. Students will work in groups on a final class project using real world datasets. Prerequisites: College calculus, linear algebra, basic probability and statistics such as
CS 109, and basic machine learning such as
CS 229. No prior knowledge of genomics is necessary.

Terms: Aut
| Units: 3

## BIOMEDIN 273B: Deep Learning in Genomics and Biomedicine (BIODS 237, CS 273B, GENE 236)

Recent breakthroughs in high-throughput genomic and biomedical data are transforming biological sciences into "big data" disciplines. In parallel, progress in deep neural networks are revolutionizing fields such as image recognition, natural language processing and, more broadly, AI. This course explores the exciting intersection between these two advances. The course will start with an introduction to deep learning and overview the relevant background in genomics and high-throughput biotechnology, focusing on the available data and their relevance. It will then cover the ongoing developments in deep learning (supervised, unsupervised and generative models) with the focus on the applications of these methods to biomedical data, which are beginning to produced dramatic results. In addition to predictive modeling, the course emphasizes how to visualize and extract interpretable, biological insights from such models. Recent papers from the literature will be presented and discussed. Students will be introduced to and work with popular deep learning software frameworks. Students will work in groups on a final class project using real world datasets. Prerequisites: College calculus, linear algebra, basic probability and statistics such as
CS 109, and basic machine learning such as
CS 229. No prior knowledge of genomics is necessary.

Terms: Aut
| Units: 3

## CS 217: Hardware Accelerators for Machine Learning

This course provides in-depth coverage of the architectural techniques used to design accelerators for training and inference in machine learning systems. This course will cover classical ML algorithms such as linear regression and support vector machines as well as DNN models such as convolutional neural nets, and recurrent neural nets. We will consider both training and inference for these models and discuss the impact of parameters such as batch size, precision, sparsity and compression on the accuracy of these models. We will cover the design of accelerators for ML model inference and training. Students will become familiar with hardware implementation techniques for using parallelism, locality, and low precision to implement the core computational kernels used in ML. To design energy-efficient accelerators, students will develop the intuition to make trade-offs between ML model parameters and hardware implementation techniques. Students will read recent research papers and complete a design project. Prerequisites:
CS 149 or
EE 180.
CS 229 is ideal, but not required.

Last offered: Winter 2020

## 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, deep learning, model/feature selection, learning theory, ML advice, clustering, density estimation, EM, dimensionality reduction, ICA, PCA, reinforcement learning and adaptive control, Markov decision processes, approximate dynamic programming, and policy search. Prerequisites: knowledge of basic computer science principles and skills at a level sufficient to write a reasonably non-trivial computer program in Python/numpy, familiarity with probability theory to the equivalency of CS109 or
STATS116, and familiarity with multivariable calculus and linear algebra to the equivalency of
MATH51.

Terms: Aut, Spr
| Units: 3-4

Instructors:
Charikar, M. (PI)
;
Ma, T. (PI)
;
Ng, A. (PI)
;
Re, C. (PI)
;
Caron, P. (TA)
;
Ding, T. (TA)
;
Do, D. (TA)
;
Edupuganti, V. (TA)
;
Fuster, A. (TA)
;
Jain, S. (TA)
;
Jiang, Q. (TA)
;
Jung, S. (TA)
;
Kamalu, J. (TA)
;
Li, H. (TA)
;
Liu, Y. (TA)
;
Nie, X. (TA)
;
Shu, R. (TA)
;
Smit, A. (TA)
;
Sun, A. (TA)
;
Tullis, I. (TA)
;
Waites, C. (TA)
;
Wolff, C. (TA)
;
Yuan, H. (TA)
;
Z. HaoChen, J. (TA)
;
Zalouk, S. (TA)
;
Zhu, M. (TA)

## CS 229M: Machine Learning Theory (STATS 214)

How do we use mathematical thinking to design better machine learning methods? This course focuses on developing mathematical tools for answering these questions. This course will cover fundamental concepts and principled algorithms in machine learning. We have a special focus on modern large-scale non-linear models such as matrix factorization models and deep neural networks. In particular, we will cover concepts and phenomenon such as uniform convergence, double descent phenomenon, implicit regularization, and problems such as matrix completion, bandits, and online learning (and generally sequential decision making under uncertainty). Prerequisites: linear algebra (
MATH 51 or
CS 205), probability theory (
STATS 116,
MATH 151 or
CS 109), and machine learning (
CS 229,
STATS 229, or
STATS 315A).

Terms: Win
| Units: 3

## CS 230: Deep Learning

Deep Learning is one of the most highly sought after skills in AI. We will help you become good at Deep Learning. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach. AI is transforming multiple industries. After this course, you will likely find creative ways to apply it to your work. This class is taught in the flipped-classroom format. You will watch videos and complete in-depth programming assignments and online quizzes at home, then come in to class for advanced discussions and work on projects. This class will culminate in an open-ended final project, which the teaching team will help you on. Prerequisites: Familiarity with programming in Python and Linear Algebra (matrix / vector multiplications).
CS 229 may be taken concurrently.

Terms: Aut, Win, Spr
| Units: 3-4
| UG Reqs: WAY-AQR, WAY-FR

Instructors:
Katanforoosh, K. (PI)
;
Ng, A. (PI)
;
A. Hudson, D. (TA)
...
more instructors for CS 230 »

Instructors:
Katanforoosh, K. (PI)
;
Ng, A. (PI)
;
A. Hudson, D. (TA)
;
Chuang, J. (TA)
;
Datta, A. (TA)
;
Desai, S. (TA)
;
Garg, D. (TA)
;
Hong, F. (TA)
;
Kanodia, A. (TA)
;
Khullar, P. (TA)
;
Kothari, T. (TA)
;
Li, J. (TA)
;
Mao, H. (TA)
;
Mousavi, S. (TA)
;
Pal, A. (TA)
;
Ruan, S. (TA)
;
Sheng, H. (TA)
;
Zhou, S. (TA)

## CS 236: Deep Generative Models

Generative models are widely used in many subfields of AI and Machine Learning. Recent advances in parameterizing these models using neural networks, combined with progress in stochastic optimization methods, have enabled scalable modeling of complex, high-dimensional data including images, text, and speech. In this course, we will study the probabilistic foundations and learning algorithms for deep generative models, including Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and flow models. The course will also discuss application areas that have benefitted from deep generative models, including computer vision, speech and natural language processing, and reinforcement learning. Prerequisites: Basic knowledge about machine learning from at least one of
CS 221, 228, 229 or 230. Students will work with computational and mathematical models and should have a basic knowledge of probabilities and calculus. Proficiency in some programming language, preferably Python, required.

Last offered: Autumn 2019

## CS 273B: Deep Learning in Genomics and Biomedicine (BIODS 237, BIOMEDIN 273B, GENE 236)

Recent breakthroughs in high-throughput genomic and biomedical data are transforming biological sciences into "big data" disciplines. In parallel, progress in deep neural networks are revolutionizing fields such as image recognition, natural language processing and, more broadly, AI. This course explores the exciting intersection between these two advances. The course will start with an introduction to deep learning and overview the relevant background in genomics and high-throughput biotechnology, focusing on the available data and their relevance. It will then cover the ongoing developments in deep learning (supervised, unsupervised and generative models) with the focus on the applications of these methods to biomedical data, which are beginning to produced dramatic results. In addition to predictive modeling, the course emphasizes how to visualize and extract interpretable, biological insights from such models. Recent papers from the literature will be presented and discussed. Students will be introduced to and work with popular deep learning software frameworks. Students will work in groups on a final class project using real world datasets. Prerequisites: College calculus, linear algebra, basic probability and statistics such as
CS 109, and basic machine learning such as
CS 229. No prior knowledge of genomics is necessary.

Terms: Aut
| Units: 3

## CS 325B: Data for Sustainable Development (EARTHSYS 162, EARTHSYS 262)

The sustainable development goals (SDGs) encompass many important aspects of human and ecosystem well-being that are traditionally difficult to measure. This project-based course will focus on ways to use inexpensive, unconventional data streams to measure outcomes relevant to SDGs, including poverty, hunger, health, governance, and economic activity. Students will apply machine learning techniques to various projects outlined at the beginning of the quarter. The main learning goals are to gain experience conducting and communicating original research. Prior knowledge of machine learning techniques, such as from
CS 221,
CS 229,
CS 231N,
STATS 202, or
STATS 216 is required. Open to both undergraduate and graduate students. Enrollment limited to 24. Students must apply for the class by filling out the form at
https://goo.gl/forms/9LSZF7lPkHadix5D3. A permission code will be given to admitted students to register for the class.

Last offered: Autumn 2019
| Repeatable
for credit

## CS 326: Topics in Advanced Robotic Manipulation

This course provides a survey of the most important and influential concepts in autonomous robotic manipulation. It includes classical concepts that are still widely used and recent approaches that have changed the way we look autonomous manipulation. We cover approaches towards motion planning and control using visual and tactile perception as well as machine learning. This course is especially concerned with new approaches for overcoming challenges in generalization from experience, exploration of the environment, and learning representation so that these methods can scale to real problems. Students are expected to present one paper in a tutorial, debate a paper once from the Pro and once from the Con side. They are also expected to propose an original research project and work on it towards a research paper. Recommended:
CS 131, 223A, 229 or equivalents.

Terms: Aut
| Units: 3-4

Instructors:
Bohg, J. (PI)

Filter Results: