About OH Course Work Class Notes Lectures Recitations Assignments Docs & Tools Resources S22 F21
Menu
About
OH
Course Work
Class Notes
Lectures
Recitations
Assignments
Docs & Tools
Resources
S22 F21
11-785 Introduction to Deep Learning
Spring 2022
Class Streaming Link

In-Person Venue: TBA

Bulletin and Active Deadlines

Assignment Deadline Description Links
Quiz 0 Jan 23rd, 11:59 PM EST AWS Presemester Quiz Canvas Submission
HW0P1 Jan 23rd, 11:59 PM EST Homework 0 - Programming Autolab,
Handout (*.zip)
HW0P2 Jan 23rd, 11:59 PM EST Homework 0 - Programming Autolab,
Handout (*.zip)
Project Gallery
Here's an example of a successful project from Fall 2020.
The team developed an AI Limmerick generator,
and compiled a book from the AI Poet's creations.
Project Report, Project Video, Book (Amazon)
This piece is performed by the Chinese Music Institute at
Peking University (PKU) together with PKU's Chinese orchestra.
This is an adaptation of Beethoven: Serenade in D major, Op.25 - 1.
Entrata (Allegro),for Chinese transverse flute (Dizi), clarinet and flute.

CoVID-19 Related Announcement

In the event that the course is moved online due to CoVID-19, we will continue to deliver lectures via zoom. In the event that an instructor is unable to deliver a lecture in person, we will broadcast that lecture over zoom or, in extreme situations, expect you to view pre-recorded lectures from prior semesters. You will be notified through Piazza should any of these eventualities arise.

The Course

“Deep Learning” systems, typified by deep neural networks, are increasingly taking over all AI tasks, ranging from language understanding, and speech and image recognition, to machine translation, planning, and even game playing and autonomous driving. As a result, expertise in deep learning is fast changing from an esoteric desirable to a mandatory prerequisite in many advanced academic settings, and a large advantage in the industrial job market.

In this course we will learn about the basics of deep neural networks, and their applications to various AI tasks. By the end of the course, it is expected that students will have significant familiarity with the subject, and be able to apply Deep Learning to a variety of tasks. They will also be positioned to understand much of the current literature on the topic and extend their knowledge through further study.

If you are only interested in the lectures, you can watch them on the YouTube channel.

Course description from student point of view

The course is well rounded in terms of concepts. It helps us understand the fundamentals of Deep Learning. The course starts off gradually with MLPs and it progresses into the more complicated concepts such as attention and sequence-to-sequence models. We get a complete hands on with PyTorch which is very important to implement Deep Learning models. As a student, you will learn the tools required for building Deep Learning models. The homeworks usually have 2 components which is Autolab and Kaggle. The Kaggle components allow us to explore multiple architectures and understand how to fine-tune and continuously improve models. The task for all the homeworks were similar and it was interesting to learn how the same task can be solved using multiple Deep Learning approaches. Overall, at the end of this course you will be confident enough to build and tune Deep Learning models.

Prerequisites

  1. We will be using Numpy and PyTorch in this class, so you will need to be able to program in python3.
  2. You will need familiarity with basic calculus (differentiation, chain rule), linear algebra and basic probability.

Units

Courses 11-785 and 11-685 are equivalent 12-unit graduate courses, and have a final project and HW 5 respectively. Course 11-485 is the undergraduate version worth 9 units, the only difference being that there is no final project or HW 5.

Acknowledgments

Your Supporters

Instructors:

TAs:

Pittsburgh Schedule (Eastern Time)

Lecture: Tuesday and Thursday, 11:50 a.m. - 1:10 p.m.

Recitation: Friday, 11:50 a.m. - 1:10 p.m.

Office hours: We will be using OHQueue for the zoom related Office hours, others would be in-person. The OH schedule is given below.



Day Time (Eastern Time) TA Zoom/In Person Venue
Monday 10:00 - 11:00 am Soumya Empran Zoom
1:00 - 2:00 pm Urvil Kenia Zoom
3:00 - 4:00 pm Fuyu Tang Zoom
6:00 - 7:00 pm Amelia Kuang Zoom
6:00 - 7:00 pm Diksha Agarwal Zoom
7:00 - 9:00 pm Rucha Khopkar Zoom
7:00 - 9:00 pm Lavanya Gupta Zoom
Tuesday 2:00 - 3:00 pm Manasi Purohit Zoom
3:00 - 4:00 pm Ameya Mahabaleshwarkar Zoom
3:00 - 4:00 pm Diksha Agarwal Zoom
Wednesday 8:00 - 9:00 am Germann Atakpa Zoom / Room B209 (Kigali)
10:00 - 11:00 am Soumya Empran Zoom
2:00 - 3:00 pm Urvil Kenia Zoom
2:00 - 3:00 pm Bradley Warren Zoom
3:00 - 4:00 pm Fuyu Tang Zoom
6:00 - 8:00 pm Zhe Chen Zoom
Thursday 4:00 - 5:00 pm Shreyas Piplani Zoom
4:00 - 5:00 pm Wenwen Ouyang Zoom
5:00 - 7:00 pm David Park Zoom
6:30 - 8:30 pm Chaoran Zhang Zoom
Friday 8:00 - 9:00 am Germann Atakpa Zoom / Room B209 (Kigali)
1:00 - 3:00 pm Ameya Mahabaleshwarkar Zoom
1:00 - 3:00 pm Jeff Moore Zoom
2:00 - 3:00 pm Bradley Warren Zoom
3:00 - 5:00 pm Aparajith Srinivasan Zoom
Saturday 8:00 - 10:00 am Iffanice Houndayi Zoom / Room B209 (Kigali)
12:00 - 2:00 pm Ruoyu Hua Zoom
1:00 - 2:00 pm Amelia Kuang Zoom
2:00 - 3:00 pm Ameya Mahabaleshwarkar Zoom
2:00 - 3:00 pm Shreyas Piplani Zoom
Sunday 9:00 - 11:00 am Adebayo Oshingbesan Zoom
9:00 - 11:00 am John Jeong Zoom
11:00 am - 12:00 pm Iffanice Houndayi Zoom / Room B209 (Kigali)
3:00 - 5:00 pm Roshan Ram Zoom
5:00 - 6:00 pm Manasi Purohit Zoom

Course Work

Policy
Breakdown
Score Assignment      Grading will be based on weekly quizzes (24%), homeworks (50%) and a course project (25%). Note that 1% of your grade is assigned to Attendance.
Quizzes
Quizzes      There will be weekly quizzes.
  • We will retain your best 12 out of the remaining 14 quizzes.
  • Quizzes will generally (but not always) be released on Friday and due 72 hours later.
  • Quizzes are scored by the number of correct answers.
  • Quizzes will be worth 24% of your overall score.
Assignments
Assignments There will be five assignments in all. Assignments will include autolab components, where you must complete designated tasks, and a kaggle component where you compete with your colleagues.
  • Autolab components are scored according to the number of correctly completed parts.
  • We will post performance cutoffs for A (100%), B (80%), C (60%), D (40%) and F (0%) for Kaggle competitions. Scores will be interpolated linearly between these cutoffs.
  • Assignments will have a “preliminary submission deadline”, an “on-time submission deadline” and a “late-submission deadline.”
    • Early submission deadline: You are required to make at least one submission to Kaggle by this deadline. People who miss this deadline will automatically lose 10% of subsequent marks they may get on the homework. This is intended to encourage students to begin working on their assignments early.
    • On-time deadline: People who submit by this deadline are eligible for up to five bonus points. These points will be computed by interpolation between the A cutoff and the highest performance obtained for the HW. The highest performance will get 105.
    • Late deadline: People who submit after the on-time deadline can still submit until the late deadline. There is a 10% penalty applied to your final score, for submitting late.
    • Slack days: Everyone gets up to 7 slack days, which they can distribute across all their homework P2s only. Once you use up your slack days you will fall into the late-submission category by default. Slack days are accumulated over all parts of all homeworks, except HW0, to which no slack applies.
    • Kaggle scoring: We will use max(max(on-time score), max(slack-day score), .0.9*max(late-submission score)) as your final score for the HW. If this happens to be a slack-days submission, slack days corresponding to the selected submission will be counted.
  • Assignments carry 50% of your total score. HW0 is not graded (but is mandatory), while each of the subsequent four are worth 12.5%.
  • A fifth HW, HW5, will be released later in the course and will have the same weight as a course project. Please see Project section below for more details.
Project
Project
  • All students taking a graduate version of the course are required to do a course project. The project is worth 25% of your grade. These points are distributed as follows: 20% - Midterm Report; 35% - Project Video; 5% - Responding to comments on Piazza; 40% - Project report.
  • Note that a Project is mandatory for 11-785/18-786 students. In the event of a catastrophe (remember Spring 2020), the Project may be substititued with HW5. 11-685 Students may choose to do a Project instead of HW5. Either your Project OR HW5 will be graded.
Attendance
Attendance
  • If you are in section A you are expected to attend in-person lectures. We will track attendance.
  • If you are in any of the other (out-of-timezone) sections, you may either watch the real-time zoom lectures or the recorded lectures on mediatech
    • If viewed on mediatech, the lectures of each week must be viewed before 8AM of the Monday following the following week (Otherwise, it doesn’t count)
  • At the end of the semester, we will select a random subset of 50% of the lectures and tabulate attendance
  • If you have attended at least 70% of these (randomly chosen) lectures, you get the attendance point
Final grade
Final grade The end-of-term grade is curved. Your overall grade will depend on your performance relative to your classmates.
Pass/Fail
Pass/Fail Students registered for pass/fail must complete all quizzes, HWs and if they are in the graduate course, the project. A grade equivalent to B- is required to pass the course.
Auditing
Auditing Auditors are not required to complete the course project, but must complete all quizzes and homeworks. We encourage doing a course project regardless.
End Policy

Study groups

This semester we will be implementing study groups. It is highly recommended that you join a study group; see the forms on the bulletin.

Piazza: Discussion Board

Piazza is what we use for discussions. You should be automatically signed up if you're enrolled at the start of the semester. If not, please sign up here. Also, please follow the Piazza Etiquette when you use the piazza.

AutoLab: Software Engineering

AutoLab is what we use to test your understand of low-level concepts, such as engineering your own libraries, implementing important algorithms, and developing optimization methods from scratch.

Kaggle: Data Science

Kaggle is where we test your understanding and ability to extend neural network architectures discussed in lecture. Similar to how AutoLab shows scores, Kaggle also shows scores, so don't feel intimidated -- we're here to help. We work on hot AI topics, like speech recognition, face recognition, and neural machine translation.

Media Services/YouTube: Lecture and Reciation Recordings

CMU students who are not in the live lectures should watch the uploaded lectures at Media Services in order to get attendance credit. Links to individual videos will be posted as they are uploaded.

YouTube is where non-CMU folks can view all lecture and recitation recordings. Videos marked “Old“ are not current, so please be aware of the video title.

Books and Other Resources

The course will not follow a specific book, but will draw from a number of sources. We list relevant books at the end of this page. We will also put up links to relevant reading material for each class. Students are expected to familiarize themselves with the material before the class. The readings will sometimes be arcane and difficult to understand; if so, do not worry, we will present simpler explanations in class.

You can also find a nice catalog of models that are current in the literature here. We expect that you will be in a position to interpret, if not fully understand many of the architectures on the wiki and the catalog by the end of the course.

Academic Integrity

You are expected to comply with the University Policy on Academic Integrity and Plagiarism.
  • You are allowed to talk with and work with other students on homework assignments.
  • You can share ideas but not code. You should submit your own code.
Your course instructor reserves the right to determine an appropriate penalty based on the violation of academic dishonesty that occurs. Violations of the university policy can result in severe penalties including failing this course and possible expulsion from Carnegie Mellon University. If you have any questions about this policy and any work you are doing in the course, please feel free to contact your instructor for help.

Class Notes

A book containing class notes is being developed in tandem with this course; check it out.

Schedule of Lectures

Quiz
Lecture Date Topics Slides and Video Additional Materials Quiz
0 -
  • Course Logistics
  • Learning Objectives
  • Grading
  • Deadlines
Slides (*.pdf)
Video (YT)
Quiz 0
1 Tuesday
Jan  18
  • Introduction
Slides (*.pdf)
Video (YT)
Video (MT)
The New Connectionism (1988)
On Alan Turing's Anticipation of Connectionism
Quiz 1
2 Thursday
Jan  20
  • Neural Nets as Universal Approximators
Slides (*.pdf)
Video (MT)
Video (YT)
Shannon (1949)
Boolean Circuits
3 Tuesday
Jan  25
  • Modelling a specified input-output relationship: the problem of learning a Neural Net
  • Learning from data: Empirical risk minimization
Widrow and Lehr (1992)
Adaline and Madaline
Convergence of perceptron algorithm
Quiz 2
4 Thursday
Jan 27
  • Empirical risk minimization and gradient descent
  • Training the network: Setting up the problem
Werbos (1990)
Rumelhart, Hinton and Williams (1986)
5 Tuesday
Feb  1
  • Backpropagation
  • Calculus of backpropagation
Werbos (1990)
Rumelhart, Hinton and Williams (1986)
Quiz 3
6 Thursday
Feb 3
  • Convergence issues
  • Loss Surfaces
  • Momentum
Backprop fails to separate, where perceptrons succeed, Brady et al. (1989)
Why Momentum Really Works
7 Tuesday
Feb 8
  • Optimization
  • Batch Size, SGD, Minibatch, second-order methods
Momentum, Polyak (1964)
Nestorov (1983)
Derivatives and Influences
Quiz 4
8 Thursday
Feb 10
  • Optimizers and Regularizers
    • Choosing a divergence (loss) function
    • Batch normalization
    • Dropout
ADAGRAD, Duchi, Hazan and Singer (2011)
Adam: A method for stochastic optimization, Kingma and Ba (2014)
9 Tuesday
Feb 15
  • Shift invariance and Convolutional Neural Networks
Quiz 5
10 Thursday
Feb 17
  • Models of vision, Convolutional Neural Networks
11 Tuesday
Feb 22
  • Learning in Convolutional Neural Networks
CNN Explainer Quiz 6
12 Thursday
Feb 24
  • Learning in CNNs, transpose Convolution
13 Tuesday
March 1
  • Time Series and Recurrent Networks
Fahlman and Lebiere (1990)
How to compute a derivative, extra help for HW3P1 (*.pptx)
Quiz 7
14 Thursday
March 3
  • Stability and Memory, LSTMs
Bidirectional Recurrent Neural Networks
- Tuesday
March 8
  • No Class - Spring Break
Quiz 8
- Thursday
March 10
  • No Class - Spring Break
15 Tuesday
March 15
  • Loss Functions in RNNs, Sequence Prediction
LSTM Quiz 8
16 Thursday
March 17
  • Connectionist Temporal Classification
  • Sequence prediction
17 Tuesday
March 22
  • Connectionist Temporal Classification (CTC)
  • Sequence To Sequence Prediction
Labelling Unsegmented Sequence Data with Recurrent Neural Networks Quiz 9
18 Thursday
March 24
  • Sequence To Sequence Methods
  • Attention

19 Tuesday
March 29
  • Transformers and GNNs
Attention Is All You Need
A comprehensive Survey on Graph Neural Networks
Quiz 10
20 Thursday
March 31
  • Learning Representations, AutoEncoders
21 Tuesday
April 5
  • Variational Auto Encoders
Tutorial on VAEs (Doersch)
Autoencoding variational Bayes (Kingma)
Quiz 11
- Thursday
April 7
  • No Class - Spring Break
22 Tuesday
April 12
  • Generative Adversarial Networks, 1
Quiz 12
23 Thursday
April 14
  • Generative Adversarial Networks, 2
24 Tuesday
April  19
  • Hopfield Nets
Quiz 13
25 Thursday
April 21
  • Boltzmann Machines
26 Tuesday
April 26
  • Guest Lecture (Not Mandatory)
Quiz 14
27 Thursday
April 28
  • Guest Lecture 2 (Not Mandatory)

Schedule of Recitations

Recitation Date Topics Materials Videos Instructor
0A Jan 10, 2022 Python & OOP Fundamentals

Video (YT): 1, 2

Chaoran, Roshan
0B Jan 10, 2022 Fundamentals of NumPy

Video (YT): 1, 2, 3, 4, 5, 6, 7, 8

Rucha, Shreyas
0C Jan 10, 2022 PyTorch Tensor Fundamentals Notebook + Cheatsheet (*.zip)

Video (YT): 1, 2,

Lavanya, Aparajith
0D Jan 10, 2022 Dataset & DataLoaders Video (YT)
Fuyu, Soumya
0E Jan 10, 2022 Introduction to Google Colab Video (YT)
Ameya, Rucha
0F Jan 10, 2022 AWS Fundamentals Video (YT): 1, 2, 3, 4

Roshan, Ameya
0G Jan 10, 2022 Debugging, Monitoring

Video (YT): 1, 2

Rukayat, Brad
0H Jan 10, 2022 Remote Notebooks Notebook + Markdown (*.zip)

Video (YT): 1, 2

Zhe, Manasi
0I Jan 10, 2022 What to do if you're struggling Slides (*.pdf) Video (YT)
Brad, Urvil
0J Due: Jan. 23 Data Preprocessing Chaoran, Diksha
1 Jan 21, 2022 Your first MLP Code Slides (*.zip) Video (YT)
Lavanya, Roshan, Amelia
2 Jan 28, 2022 Optimizing the Networks, Ensembles Rucha, Urvil
HW1 Bootcamp TBA How to get started with HW1 TBA
3 Feb 4, 2022 Computing Derivatives & Autograd Chaoran, John
4 Feb 11, 2022 CNN: Basics & Backprop Aparajith, Amelia
5 Feb 18, 2022 CNNs: Classification & Verification Rucha, Roshan
HW2 Bootcamp TBA How to get start with HW2 TBA
6 Feb 25, 2022 Hyperparameters Tuning Urvil, Brad
7 Mar 4, 2022 Paper Writing Workshop TBA
8 Mar 11, 2022 RNN Basics (Pre-recorded) Aparajith, Soumya
HW3 Bootcamp TBA How to get start with HW3 TBA
9 Mar 18, 2022 CTC, Beam Search Ameya, Soumya
10 Mar 25, 2022 Attention, MT, LAS Ameya, Lavanya
HW4 Bootcamp TBA How to get start with HW4 TBA
11 Apr 1, 2022 Transformers Ameya, Zhe
12 Apr 8, 2022 Autoencoders, VAEs (Pre-recorded) TBA
13 Apr 15, 2022 Generative Adversarial Networks (GANs) Zhe, Fuyu
14 Apr 22, 2022 Graph Neural Networks John
15 Pre-recorded YOLO Chaoran, Manasi

Assignments and Quizzes

∑ Ongoing, ∏ Upcoming

Assignment Release Date Due Date Related Materials / Links
HW0p1 Winter Break Jan 23rd, 2022
11:59 PM EST
AutolabHandout
(see recitation 0s)
HW0p2 Winter Break Jan 23rd, 2022
11:59 PM EST
AutolabHandout
(see recitation 0s)
HW1p1 Jan 23rd, 2022 Feb 17th, 2022
11:59 PM EST
Autolab (TBA), Handout(*.zip) (TBA)
HW1p2 Jan 23rd, 2022 Early Submission: Jan 30th, 2022
11:59 PM EST
Autolab (TBA), Writeup (*.pdf) (TBA)
Final: Feb 17th, 2022
11:59 PM EST
Project Proposal - TBA Canvas Submission (TBA)
HW2p1 Feb 17th, 2022 Mar 17th, 2022
11:59 PM EST
Autolab (TBA), Handout (*.zip) (TBA)
HW2p2 Feb 17th, 2022 Early Submission: Feb 24th, 2022
11:59 PM EST
Face Classification: Autolab (TBA),
Face Verification: Autolab (TBA),
Writeup (*.pdf) (TBA)
Final: Mar 17th, 2022
11:59 PM EST
Project Midterm Report - TBA Canvas Submission (TBA)
HW3p1 Mar 17th, 2022 Apr 7th, 2022
11:59 PM EST
Autolab (TBA),
handout (*.zip) (TBA),
Writeup (*.pdf) (TBA)
HW3p2 Mar 17th, 2022 Early Submission: Mar 24th, 2022
11:59 PM EST
Autolab (TBA),
Kaggle (TBA),
Writeup (*.pdf) (TBA)
Final: Apr 7th, 2022
11:59 PM EST
HW4p1 Mar 31st, 2022 Apr 28th, 2022
11:59 PM EST
Writeup (TBA) (*.pdf),
HW4p2 Mar 31st, 2022 Early Submission: Apr 6th, 2022
11:59 PM EST
Writeup (TBA) (*.pdf)
Final: Apr 28th, 2022
11:59 PM EST
Final Project Video Presentation & Preiliminary Project Report Apr 28th, 2022
11:59 PM EST
Apr 30th, 2022
11:59 PM EST
Preliminary Report: Canvas Submission (TBA)
Project Peer reviews TBA TBA -
Final Project Report Submission - May 5th, 2022
11:59 PM EST
Canvas Submission (TBA)

Documentation and Tools

Textbooks

This is a selection of optional textbooks you may find useful

Deep Learning
Dive Into Deep Learning By Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola PDF, 2020
Deep Learning
Deep Learning By Ian Goodfellow, Yoshua Bengio, Aaron Courville Online book, 2017
Neural Networks and Deep Learning
Neural Networks and Deep Learning By Michael Nielsen Online book, 2016