Results for CS231n

Since their introduction in 2017, Transformers have taken the world by storm, and are finding applications all over Deep Learning. They have enabled the creation of powerful language models like ChatGPT and Gemini, and are a critical component in other ML applications such as text-to-image and video generation (e.g. DALL-E and Sora). They have significantly elevated the capabilities and impact of Artificial Intelligence. In CS 25, which has become one of Stanford's hottest and most exciting seminars, we examine the details of how Transformers work, and dive deep into the different kinds of Transformers and how they're applied in various fields and applications. We do this through a combination of instructor lectures, guest lectures, and classroom discussions. Potential topics include LLM architectures, creative use cases (e.g. art and music), healthcare/biology and neuroscience applications, robotics and RL (e.g. physical tasks, simulations, or games), and so forth. We invite folks at the forefront of Transformers research for talks, which will also be livestreamed and recorded through YouTube/Zoom. Past speakers have included Andrej Karpathy, Geoffrey Hinton, Jim Fan, Ashish Vaswani, and folks from OpenAI, Google DeepMind, NVIDIA, etc. Our class includes social events and networking sessions and has a popular reception within and outside Stanford, with around 1 million total views on YouTube. This is a 1-unit S/NC course, where attendance is the only homework! Please enroll on Axess or audit by joining the livestream (or in person if seats are available). Prerequisites: basic knowledge of Deep Learning (should understand attention) or CS224N/CS231N/CS230. Course website: https://web.stanford.edu/class/cs25/

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 - All class assignments will be in Python (and use numpy) (we provide a tutorial here for those who aren't as familiar with Python). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine.College Calculus, Linear Algebra (e.g. MATH 19, MATH 51) -You should be comfortable taking derivatives and understanding matrix vector operations and notation. Basic Probability and Statistics (e.g. CS 109 or other stats course) -You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc.

This project-based course covers the iterative process for designing, developing, and deploying machine learning systems. It focuses on systems that require massive datasets and compute resources, such as large neural networks. Students will learn about data management, data engineering, approaches to model selection, training, scaling, how to continually monitor and deploy changes to ML systems, as well as the human side of ML projects. In the process, students will learn about important issues including privacy, fairness, and security. Pre-requisites: At least one of the following; CS229, CS230, CS231N, CS224N or equivalent. Students should have a good understanding of machine learning algorithms and should be familiar with at least one framework such as TensorFlow, PyTorch, JAX.

This course will provide an introduction to state-of-the-art ML methods designed to make AI more trustworthy. The course focuses on four concepts: explanations, fairness, privacy, and robustness. We first discuss how to explain and interpret ML model outputs and inner workings. Then, we examine how bias and unfairness can arise in ML models and learn strategies to mitigate this problem. Next, we look at differential privacy and membership inference in the context of models leaking sensitive information when they are not supposed to. Finally, we look at adversarial attacks and methods for imparting robustness against adversarial manipulation.Students will gain understanding of a set of methods and tools for deploying transparent, ethically sound, and robust machine learning solutions. Students will complete labs, homework assignments, and discuss weekly readings. Prerequisites: CS229 or similar introductory Python-based ML class; knowledge of deep learning such as CS230, CS231N; familiarity with ML frameworks in Python (scikit-learn, Keras) assumed.

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 (FAccT) of a model in addition to its performance. Although FAccT will be difficult to achieve, emerging technical approaches in this topic show promise in making better FAccT AI systems. In this course, we will study the rigorous computer science necessary foundations for FAccT deep learning and dive into the technical underpinnings of topics including fairness, robustness, interpretability, accountability, and privacy. These topics reflect state-of-the-art research in FAccT, 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 FAccT 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.

This course introduces deep learning methods and AI technologies applied to four main areas of Computer Graphics: rendering, geometry, animation, and imaging. We will study a wide range of problems on content creation for images, shapes, and animations, recently advanced by deep learning techniques. For each problem, we will understand its conventional solutions, study the state-of-the-art learning-based approaches, and critically evaluate their results as well as the impacts to researchers and practitioners in Computer Graphics. The topics include differentiable rendering/neural rendering, BRDF estimation, texture synthesis, denoising, procedural modeling, view synthesis, colorization, style transfer, motion synthesis, differentiable physics simulation, and reinforcement learning. Through programming projects and homework, students who successfully complete this course will be able to use neural rendering algorithms for image manipulation, apply neural procedural modeling for shape and scene synthesis, exploit data-driven methods for simulating physical phenomena, and implement policy learning algorithms for creating character animation. Recommended Prerequisites: CS148, CS231N

The last ten years has seen a watershed in the development of large-scale neural networks in artificial intelligence. At the same time, computational neuroscientists have discovered a surprisingly robust mapping between the internal components of these networks and real neural structures in the human brain. In this class we will discuss a panoply of examples of such "convergent man-machine evolution", including: feedforward models of sensory systems (vision, audition, somatosensation); recurrent neural networks for dynamics and motor control; integrated models of attention, memory, and navigation; transformer models of language areas; self-supervised models of learning; and deep RL models of decision and planning. We will also delve into the methods and metrics for comparing such models to real-world neural data, and address how unsolved open problems in AI (that you can work on!) will drive forward novel neural models. Some meaningful background in modern neural networks is highly advised (e.g. CS229, CS230, CS231n, CS234, CS236, CS 330), but formal preparation in cognitive science or neuroscience is not needed (we will provide this).

Most successful machine learning algorithms of today use either carefully curated, human-labeled datasets, or large amounts of experience aimed at achieving well-defined goals within specific environments. In contrast, people learn through their agency: they interact with their environments, exploring and building complex mental models of their world so as to be able to flexibly adapt to a wide variety of tasks. One crucial next direction in artificial intelligence is to create artificial agents that learn in this flexible and robust way. Students will read and take turns presenting current works, and they will produce a proposal of a feasible next research direction. Prerequisites: CS229, CS231N, CS234 (or equivalent).

Most successful machine learning algorithms of today use either carefully curated, human-labeled datasets, or large amounts of experience aimed at achieving well-defined goals within specific environments. In contrast, people learn through their agency: they interact with their environments, exploring and building complex mental models of their world so as to be able to flexibly adapt to a wide variety of tasks. One crucial next direction in artificial intelligence is to create artificial agents that learn in this flexible and robust way. Students will read and take turns presenting current works, and they will produce a proposal of a feasible next research direction. Prerequisites: CS229, CS231N, CS234 (or equivalent).

The last ten years has seen a watershed in the development of large-scale neural networks in artificial intelligence. At the same time, computational neuroscientists have discovered a surprisingly robust mapping between the internal components of these networks and real neural structures in the human brain. In this class we will discuss a panoply of examples of such "convergent man-machine evolution", including: feedforward models of sensory systems (vision, audition, somatosensation); recurrent neural networks for dynamics and motor control; integrated models of attention, memory, and navigation; transformer models of language areas; self-supervised models of learning; and deep RL models of decision and planning. We will also delve into the methods and metrics for comparing such models to real-world neural data, and address how unsolved open problems in AI (that you can work on!) will drive forward novel neural models. Some meaningful background in modern neural networks is highly advised (e.g. CS229, CS230, CS231n, CS234, CS236, CS 330), but formal preparation in cognitive science or neuroscience is not needed (we will provide this).