printer friendly pageCS 231N: Deep Learning for Computer Vision
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; CS131 and CS229 or equivalents; MATH21 or equivalent, linear algebra.
Terms: Spr
| Units: 3-4
Instructors:
Gao, R. (PI)
;
Li, F. (PI)
;
Wu, J. (PI)
;
Bansal, D. (TA)
;
Buch, S. (TA)
;
Dharan, G. (TA)
;
Gupta, A. (TA)
;
Huang, Z. (TA)
;
Kaul, D. (TA)
;
Kulal, S. (TA)
;
Patel, M. (TA)
;
Ren, H. (TA)
;
Sharma, M. (TA)
;
Shen, W. (TA)
;
Shi, H. (TA)
;
Su, S. (TA)
;
Zhang, Y. (TA)
MATH 21: Calculus
This course addresses a variety of topics centered around the theme of "calculus with infinite processes", largely the content of BC-level AP Calculus that isn't in the AB-level syllabus. It is needed throughout probability and statistics at all levels, as well as to understand approximation procedures that arise in all quantitative fields (including economics and computer graphics). After an initial review of limit rules, the course goes on to discuss sequences of numbers and of functions, as well as limits "at infinity" for each (needed for any sensible discussion of long-term behavior of a numerical process, such as: iterative procedures and complexity in computer science, dynamic models throughout economics, and repeated trials with data in any field). Integration is discussed for rational functions (a loose end from
Math 20) and especially (improper) integrals for unbounded functions and "to infinity": this shows up in contexts as diverse as escape velocity for a rocket, the pres
more »
This course addresses a variety of topics centered around the theme of "calculus with infinite processes", largely the content of BC-level AP Calculus that isn't in the AB-level syllabus. It is needed throughout probability and statistics at all levels, as well as to understand approximation procedures that arise in all quantitative fields (including economics and computer graphics). After an initial review of limit rules, the course goes on to discuss sequences of numbers and of functions, as well as limits "at infinity" for each (needed for any sensible discussion of long-term behavior of a numerical process, such as: iterative procedures and complexity in computer science, dynamic models throughout economics, and repeated trials with data in any field). Integration is discussed for rational functions (a loose end from
Math 20) and especially (improper) integrals for unbounded functions and "to infinity": this shows up in contexts as diverse as escape velocity for a rocket, the present value of a perpetual yield asset, and important calculations in probability (including the famous "bell curve" and to understand why many statistical tests work as they do). The course then turns to infinite series (how to "sum" an infinite collection of numbers), some useful convergence and divergence rests for these, and the associated killer app: power series and their properties, as well as Taylor approximations, all of which provide the framework that underlies virtually all mathematical models used in any quantitative field.
Terms: Aut, Win, Spr
| Units: 4
| UG Reqs: GER:DB-Math, WAY-FR
Instructors:
Dowlin, N. (PI)
;
Ho, W. (PI)
;
Jack, T. (PI)
;
Lai, Y. (PI)
;
Ma, C. (PI)
;
Wieczorek, W. (PI)
;
Ahmed, N. (TA)
;
Ho, W. (TA)
;
King, M. (TA)
;
Nuti, P. (TA)
;
Pagadora, J. (TA)
;
Ryzhik, A. (TA)
MATH 21A: Calculus, ACE
Students attend one of the regular
MATH 21 lectures with a longer discussion section of two hours per week instead of one. Active mode: students in small groups discuss and work on problems, with a TA providing guidance and answering questions. Application required:
https://forms.gle/ruykWBk6zJMgXRB49
Terms: Aut, Win, Spr
| Units: 5
| UG Reqs: WAY-FR
Instructors:
Lai, Y. (PI)
;
Ma, C. (PI)
;
Wieczorek, W. (PI)
;
Khu, D. (TA)
;
Nuti, P. (TA)
;
Taylor, L. (TA)
Filter Results: