CS 444: Topics in Computer Science (Deep Learning)

# CS 444: Topics in Computer Science (Deep Learning) --- ## News - Description on [project proposal](https://hackmd.io/@sungjin/rJ9qf0V-8) - Assignment 3 is posted (check out Canvas) - Assignment 2 is posted (check out Canvas) - ==[Assignment 1](https://hackmd.io/cb2hagPTTpCL8-LynmeE-w?view) is posted.== - Sep 8 (Tuesday) class is cancelled due to holiday shift - Aug 20: Syllabus Updated ## Canvas Site - https://rutgers.instructure.com/courses/65637 --- ## Overview The principal purpose of this course is to introduce deep learning through a comparative presentation of methodology. The course mainly focuses on the fundamentals of deep neural networks and its applications to natural language processing, computer vision, and deep generative modeling. The course is intended for CS students with an applied mathematics orientation and knowledge on essential machine learning, and also for students in other programs (computer and electrical engineering, statistics, mathematics, psychology) who are interested in this topic. The course will cover traditional neural networks architectures, including feed-forward neural networks, convolutional neural networks, recurrent neural networks as well as recent advances such as attention mechanisms, batch normalization, transformer, etc. An essential goal of the course is for the students to learn to build their own DL toolbox using PyTorch. The course will also cover some advanced topics like generative models and reinforcement learning if time allowed.  --- ## Pre-Requisites 1. CS 440 or CS 439 1. I encourage students to take [CS 445: Introduction to Machine Learning](http://karlstratos.com/teaching/cs445fall20/cs445fall20.html) together with this course for maximal learning for the topic of model machine learning. 5. Students must be familiar with **python** programming. The homework will be based on [**PyTorch**](https://pytorch.org/), a python framework for deep learning. Thus, some experience of PyTorch will be helpful although the course will provide short intro lecture on using PyTorch. Students should set up the PyTorch programming environment as well. - [Getting Started With Pytorch In Google Collab With Free GPU](https://hackernoon.com/getting-started-with-pytorch-in-google-collab-with-free-gpu-61a5c70b86a) --- ## Instructor & TA - Instructor - Sungjin Ahn (sungjin.ahn@cs.rutgers.edu) at CBIM-07 - A contact via email is usually responded within two business days. - TA - Yi-Fu Wu (yifuwu2@cs.rutgers.edu) --- ## Time and Location - When: Tuesday and Thursday at 5:00pm - 6:20pm - The course is remotely instructed via Zoom. Link for the Zoom meeting is posted on the course canvas site.  --- ## Office Hours - Instructor - Every Tuesday between 9 am - 10 am via Zoom. The Zoom link is posted on the course canvas site. - As there can be multiple students waiting for the office hour, making an appointment is required (please send an email to the instructor in advance and schedule a slot within the office hour.) - TA - Every Wednesday 11am-12pm   --- ## Technology Requirements - A computer, mic/audio system, and access to the Internet to participate in the lectures via Zoom - Please visit the Rutgers Student Tech Guide page for resources available to all students. If you do not have the appropriate technology for financial reasons, please email Dean of Students deanofstudents@echo.rutgers.edu for assistance. If you are facing other financial hardships, please visit the Office of Financial Aid at https://financialaid.rutgers.edu/. --- ## Computing Resources - Rutgers iLab Servers: https://report.cs.rutgers.edu/nagiosnotes/iLab-machines.html - Google Colab: https://colab.research.google.com/ --- ## Required Books and Materials - There is no required book for this course. The following books can be useful though as references on relevant topics. - Reference Books 1. Dive into Deep Learning (https://d2l.ai/), 1. Deep Learning (DL), Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron, MIT Press, 2016, ISBN: 9780262035613 1. Pattern Recognition and Machine Learning (PRML), Christopher C. Bishop, Springer, 2006, ISBN: 9780387310732 1. Natural Language Processing with Distributed Representations (NLP), Kyunghyun Cho, https://arxiv.org/abs/1511.07916 - Pytorch Tutorial - [DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ](https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html) - Reinforcement Learning - [Reinforcement Learning (2nd)](http://incompleteideas.net/book/RLbook2020.pdf) - [Lecture by David Silver](https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZBiG_XpjnPrSNw-1XQaM_gB&index=2&t=0s)  --- ## Course Structure and Requirement #### Grading - Attendance (15%) - Assignment 1 (15%) - Assignment 2 (15%) - Assignment 3 (15%) - Assignment 4 (15%) - Final Project (25%) #### Attendance policy - One absence is allowed and will not affect your score. From the second absence, a reasonable explanation with supporting evidence is required not to lose the attendance point. - Each absence without a reasonable explanation will lose 3% of the score. #### Check your [attendance sheet](https://docs.google.com/spreadsheets/d/1nmTOCTdemMRnGVm6dPJIm1pCWnyr7dbEBfDgkyiQcoA/edit?usp=sharing) here #### Late submission will lose 2% every day #### The final project is a 1~3 person team project. The project consists of (1) proposal writing, (2) final presentation, and (3) final report. More details will be explained in class. For more details see [final project](https://hackmd.io/@Tn97A1U0QG6gBtFPXRh4oQ/rJ9qf0V-8) --- ## Assignments - [Assignment 1](https://hackmd.io/cb2hagPTTpCL8-LynmeE-w?view) --- ## Lecture Slides - available in Canvas  --- ## Schedule Week 1 - 9/01 - Course Overview, ML Foundation - 9/03 - ML Foundation Week 2 - 9/08 - **No Class** (Due to Laborday Holiday Shift) - 9/10 - ML Foundation (HW1 Release) Week 3 - 9/15 - ML Foundation & Linear Models - 9/17 - Linear Models Week 4 - 9/22 - Multi-Layer Perceptrons (MLP) - 9/24 - MLP, Activation Functions, Backpropagation, Vanishing/Exploding Gradinent Week 5 - 9/29 - CNN - 10/01 - CNN Week 6 - 10/06 - Modern CNN - 10/08 - Modern CNN Week 7 - 10/13 - RNN - 10/15 - RNN (Gradient Explosion/Vanishing, LSTM, GRU) Week 8 - 10/20 - Attention, Transformer - 10/22 - Attention, Transformer Week 9 - 10/27 - BERT, GPT - 10/29 - Optimization for Deep Learning (HW3) Week 10 - 11/03 - Deep Reinforcement Learning (MDP, Dynamic Programming) - 11/05 - Deep Reinforcement Learning (Dynamic Programming) Week 11 - 11/10 - Deep Reinforcement Learning (Monte-Carlo, Temporal Difference, DQN) - 11/12 - Deep Reinforcement Learning (Policy Gradient, MB-RL, HW4) Week 12 - 11/17 - Deep Reinforcement Learning (Policy Gradient, MB-RL) - 11/19 - Deep Generative Models - VAE Week 13 - 11/24 - Deep Generative Models - VAE - 11/26 - No Class (Thanksgiving Recess) Week 14 - 12/01 - Deep Generative Models - VAE - 12/03 - Deep Generative Models - GAN (End of Regular Class)  Week 16 - 12/17 - Final Presentation - 12/18 - Final Report Due       --> -->