## CS 231N: Convolutional Neural Networks for Visual Recognition

Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks. Prerequisites: Proficiency in Python; familiarity with C/C++;
CS 131 and
CS 229 or equivalents;
Math 21 or equivalent, linear algebra.

Terms: Spr
| Units: 3-4

Instructors:
Li, F. (PI)

## CS 331B: Representation Learning in Computer Vision

A representation performs the task of converting an observation in the real world (e.g. an image, a recorded speech signal, a word in a sentence) into a mathematical form (e.g. a vector). This mathematical form is then used by subsequent steps (e.g. a classifier) to produce the outcome, such as classifying an image or recognizing a spoken word. Forming the proper representation for a task is an essential problem in modern AI. In this course, we focus on 1) establishing why representations matter, 2) classical and moderns methods of forming representations in Computer Vision, 3) methods of analyzing and probing representations, 4) portraying the future landscape of representations with generic and comprehensive AI/vision systems over the horizon, and finally 5) going beyond computer vision by talking about non-visual representations, such as the ones used in NLP or neuroscience. The course will heavily feature systems based on deep learning and convolutional neural networks. We will hav
more »

A representation performs the task of converting an observation in the real world (e.g. an image, a recorded speech signal, a word in a sentence) into a mathematical form (e.g. a vector). This mathematical form is then used by subsequent steps (e.g. a classifier) to produce the outcome, such as classifying an image or recognizing a spoken word. Forming the proper representation for a task is an essential problem in modern AI. In this course, we focus on 1) establishing why representations matter, 2) classical and moderns methods of forming representations in Computer Vision, 3) methods of analyzing and probing representations, 4) portraying the future landscape of representations with generic and comprehensive AI/vision systems over the horizon, and finally 5) going beyond computer vision by talking about non-visual representations, such as the ones used in NLP or neuroscience. The course will heavily feature systems based on deep learning and convolutional neural networks. We will have several teaching lectures, a number of prominent external guest speakers, as well as presentations by the students on recent papers and their projects. nnRequired Prerequisites: CS131A,
CS231A,
CS231B, or
CS231N. If you do not have the required prerequisites, please contact a member of the course staff before enrolling in this course.

Last offered: Autumn 2017

## CS 335: Fair, Accountable, and Transparent (FAT) Deep Learning

Deep learning-based AI systems have demonstrated remarkable learning capabilities. A growing field in deep learning research focuses on improving the Fairness, Accountability, and Transparency (FAT) of a model in addition to its performance. Although FAT will be difficult to achieve, emerging technical approaches in this topic show promise in making better FAT AI systems. In this course, we will study the rigorous computer science necessary for FAT deep learning and dive into the technical underpinnings of topics including fairness, robustness, interpretability, common sense, AI deception, and privacy. These topics reflect state-of-the-art research in FAT, are socially important, and they have strong industrial interest due to government and other policy regulation. This course will focus on the algorithmic and statistical methods needed to approach FAT AI from a deep learning perspective. We will also discuss several application areas where we can apply these techniques. Prerequisites
more »

Deep learning-based AI systems have demonstrated remarkable learning capabilities. A growing field in deep learning research focuses on improving the Fairness, Accountability, and Transparency (FAT) of a model in addition to its performance. Although FAT will be difficult to achieve, emerging technical approaches in this topic show promise in making better FAT AI systems. In this course, we will study the rigorous computer science necessary for FAT deep learning and dive into the technical underpinnings of topics including fairness, robustness, interpretability, common sense, AI deception, and privacy. These topics reflect state-of-the-art research in FAT, are socially important, and they have strong industrial interest due to government and other policy regulation. This course will focus on the algorithmic and statistical methods needed to approach FAT AI from a deep learning perspective. We will also discuss several application areas where we can apply these techniques. Prerequisites: Intermediate knowledge of statistics, machine learning, and AI. Qualified students will have taken any one of the following, or their advanced equivalents:
CS224N,
CS230,
CS231N,
CS236,
CS273B. Alternatively, students who have taken CS229 or have equivalent knowledge can be admitted with the permission of the instructors.

Terms: Spr
| Units: 3

Instructors:
Landay, J. (PI)

## CS 375: Large-Scale Neural Network Modeling for Neuroscience (PSYCH 249)

Introduction to designing, building, and training large-scale neural networks for modeling brain and behavioral data, including: deep convolutional neural network models of sensory systems (vision, audition, somatosensation); variational and generative methods for neural interpretation; recurrent neural networks for dynamics, memory and attention; interactive agent-based deep reinforcement learning for cognitive modeling; and methods and metrics for comparing such models to real-world neural data. Attention will be given both to established methods as well as cutting-edge techniques. Students will learn conceptual bases for deep neural network models and will also implement learn to implement and train large-scale models in Tensorflow using GPUs. Requirements: Fluency in Unix shell and Python programming; familiarity with differential equations, linear algebra, and probability theory; priori experience with modern machine learning concepts (e.g.
CS229) and basic neural network training tools (eg. CS230 and/or
CS231n). Prior knowledge of basic cognitive science or neuroscience not required but helpful.

Terms: Aut
| Units: 1-3

Instructors:
Yamins, D. (PI)

## PSYCH 249: Large-Scale Neural Network Modeling for Neuroscience (CS 375)

Introduction to designing, building, and training large-scale neural networks for modeling brain and behavioral data, including: deep convolutional neural network models of sensory systems (vision, audition, somatosensation); variational and generative methods for neural interpretation; recurrent neural networks for dynamics, memory and attention; interactive agent-based deep reinforcement learning for cognitive modeling; and methods and metrics for comparing such models to real-world neural data. Attention will be given both to established methods as well as cutting-edge techniques. Students will learn conceptual bases for deep neural network models and will also implement learn to implement and train large-scale models in Tensorflow using GPUs. Requirements: Fluency in Unix shell and Python programming; familiarity with differential equations, linear algebra, and probability theory; priori experience with modern machine learning concepts (e.g.
CS229) and basic neural network training tools (eg. CS230 and/or
CS231n). Prior knowledge of basic cognitive science or neuroscience not required but helpful.

Terms: Aut
| Units: 1-3

Instructors:
Yamins, D. (PI)

Filter Results: