About OH Course Work Class Notes Lectures Recitations Assignments Docs & Tools Resources F22 S22
Menu
About
OH
Course Work
Class Notes
Lectures
Recitations
Assignments
Docs & Tools
Resources
F22 S22
11-785 Introduction to Deep Learning
Fall 2022

In-Person Venue: TBA

Bulletin and Active Deadlines

Assignment Deadline Description Links
HW0 TBA TBA Autolab, Writeup, Handouts - TBA
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: TBD/TBA

Recitation: TBD/TBA

Office hours: We will be using OHQueue for 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 TBD/TBA TBD/TBA TBD/TBA
Tuesday TBD/TBA TBD/TBA TBD/TBA
Wednesday TBD/TBA TBD/TBA TBD/TBA
Thursday TBD/TBA TBD/TBA TBD/TBA
Friday TBD/TBA TBD/TBA TBD/TBA
Saturday TBD/TBA TBD/TBA TBD/TBA
Sunday TBD/TBA TBD/TBA TBD/TBA
To be added: Google Calendar of latest OHs

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 HIGH (90%), MEDIUM (70%), LOW (50%), and VERY LOW (30%) 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 substituted 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 TBA. Also, please follow the Piazza Etiquette when you use the piazza.

AutoLab: Software Engineering

AutoLab TBA 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 - Link TBA in order to get attendance credit. Links to individual videos will be posted as they are uploaded.

Our YouTube Channel 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

You can watch the recorded lectures on Mediatech.
Lecture Date Topics Slides and Video Additional Materials Quiz
0 -
  • Course Logistics
  • Learning Objectives
  • Grading
  • Deadlines
 TBA:
1 TBA
  • Introduction
 TBA:

2 TBA
  • Neural Nets as Universal Approximators
 TBA:
3 TBA
  • Modelling a specified input-output relationship: the problem of learning a Neural Net
  • Learning from data: Empirical risk minimization
 TBA:
4 TBA
  • Empirical risk minimization and gradient descent
  • Training the network: Setting up the problem
 TBA:
5 TBA
  • Backpropagation
  • Calculus of backpropagation
 TBA:
6 TBA
  • Convergence issues
  • Loss Surfaces
  • Momentum
 TBA:
7 TBA
  • Optimization
  • Batch Size, SGD, Minibatch, second-order methods
 TBA:
8 TBA
  • Optimizers and Regularizers
    • Choosing a divergence (loss) function
    • Batch normalization
    • Dropout
 TBA:
9 TBA
  • Shift invariance and Convolutional Neural Networks
 TBA:
10 TBA
  • Models of vision, Convolutional Neural Networks
 TBA:
11 TBA
  • Learning in Convolutional Neural Networks
 TBA:
12 TBA
  • Learning in CNNs, transpose Convolution
 TBA:
13 TBA
  • Time Series and Recurrent Networks
 TBA:
14 TBA
  • Stability and Memory, LSTMs
 TBA:
15 TBA
  • Loss Functions in RNNs, Sequence Prediction
 TBA:
16 TBA
  • Connectionist Temporal Classification
  • Sequence prediction
 TBA:
17 TBA
  • Connectionist Temporal Classification (CTC)
  • Sequence To Sequence Prediction
 TBA:
18 TBA
  • Sequence To Sequence Methods
  • Attention
 TBA:
19 TBA
  • Transformers and GNNs
 TBA:
20 TBA
  • Learning Representations, AutoEncoders
 TBA:
21 TBA
  • Variational Auto Encoders
 TBA:
22 TBA
  • Generative Adversarial Networks, 1
 TBA:
23 TBA
  • Generative Adversarial Networks, 2
 TBA:
24 TBA
  • Guest Lecture: Adversarial Robustness
 TBA:
25 TBA
  • Guest Lecture: Deep Reinforcement Learning
 TBA:
26 TBA
  • Hofield Nets and Auto Associators
 TBA:
27 TBA
  • Boltzmann Machines
 TBA:

Schedule of Recitations

Recitation Date Topics Materials Videos Instructor
0A TBA Python & OOP Fundamentals

TBA

TBA
0B TBA Fundamentals of NumPy

TBA
0C TBA PyTorch Tensor Fundamentals

TBA

TBA
0D TBA Dataset & DataLoaders TBA
0E TBA Introduction to Google Colab TBA
0F TBA AWS Fundamentals TBA
0G TBA Debugging, Monitoring

TBA
0H TBA Remote Notebooks

TBA
0I TBA What to do if you're struggling TBA
0J Due: TBA Data Preprocessing TBA
1 TBA Your first MLP Code TBA
2 TBA Optimizing the Networks, Ensembles TBA
HW1 Bootcamp TBA How to get started with HW1 TBA
3 TBA Computing Derivatives & Autograd TBA
4 TBA Hyperparameters Tuning TBA
5 TBA CNN: Basics & Backprop TBA
HW2 Bootcamp TBA How to get started with HW2 TBA
6 TBA CNNs: Classification & Verification TBA
7 TBA Paper Writing Workshop TBA
8 TBA RNN Basics (Pre-recorded) TBA
9 TBA CTC, Beam Search TBA
HW3 Bootcamp TBA How to get started with HW3 TBA
10 TBA Attention, MT, LAS TBA
11 Apr 1, 2022 Transformers TBA
HW4 Bootcamp April 6, 2022 How to get started with HW4 TBA
12 TBA Generative Adversarial Networks (GANs) + HW5 Bootcamp TBA
13 TBA Graph Neural Networks TBA
14 Pre-recorded YOLO TBA

Assignments and Quizzes

∑ Ongoing, ∏ Upcoming

Assignment Release Date Due Date Related Materials / Links
HW0p1 TBA TBA
TBA
(see recitation 0s)
HW0p2 TBA TBA
TBA
(see recitation 0s)
HW1p1 TBA TBA
TBA
HW1p2 TBA Early Submission: TBA
TBA
Final: TBA
TBA
HW1 Bonus TBA TBA
TBA
Project Proposal - TBA
HW2p1 TBA TBA
TBA
HW2p2 TBA Early Submission: TBA
TBA
Final: TBA
TBA
Project Midterm Report - TBA
HW3p1 TBA TBA
TBA
HW3p2 TBA Early Submission: TBA
TBA
Final: TBA
TBA
HW4p1 TBA TBA
TBA
HW4p2 TBA Early Submission (Bonus): TBA
TBA
Final: TBA
TBA
Final Project Video Presentation & Preiliminary Project Report TBA
TBA
TBA
Project Peer reviews TBA
TBA
TBA
 -
Final Project Report Submission - TBA
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
Deep Learning Step by Step with Python
Deep Learning Step by Step with Python: A Very Gentle Introduction to Deep Neural Networks for Practical Data Science By N. D. Lewis
Parallel Distributed Processing
Parallel Distributed Processing, Volume 1 By Rumelhart and McClelland
Parallel Distributed Processing
Parallel Distributed Processing, Volume 2 By Rumelhart and McClelland