About OH Course Work Class Notes Lectures Recitations Assignments Docs & Tools Resources F23 S23
Menu
About
OH
Course Work
Class Notes
Lectures
Recitations
Assignments
Docs & Tools
Resources
S23 F22
11-785 Introduction to Deep Learning
Fall 2023
Class Streaming Link

In-Person Venue: Giant Eagle Auditorium, Baker Hall (A51)

Bulletin and Active Deadlines

Assignment Deadline Description Links
TBA TBA
 TBA 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.

The Course

“Deep Learning” systems, typified by deep neural networks, are increasingly taking over all the AI tasks, ranging from language understanding, 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: Monday and Wednesday, 8:00 a.m. - 9:20 a.m. - Good times :)

Recitation: Friday, 8:00 a.m. - 9:20 a.m.

Event Calendar: The Google Calendar below ideally contains all events and deadlines for student's convenience. Please feel free to add this calendar to your Google Calendar by clicking on the plus (+) button on the bottom right corner of the calendar below. Any adhoc changes to the schedule will be visible on the calendar first.

TBA

OH Calendar: The Google Calendar below contains the schedule for Office Hours. Please feel free to add this calendar to your Google Calendar by clicking on the plus (+) button on the bottom right corner of the calendar below. Any adhoc changes to the schedule, including extra OH, will be visible on the calendar first.

TBA


Office hours: This is the schedule for this semester. We will be using OHQueue(11-785) for both zoom and in-person Office hours. Please refer the OH calendar/ Piazza for updated information on OH hours.

Day Time (Eastern Time) TA Zoom/In Person
TBA TBA TBA TBA

Homework Hackathon: During 'Homework Hackathons', students will be assisted with homework by the course staff. It is recommended to come as study groups.
Location: TBA
Time: TBA

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 48 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 10 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 must watch lectures live on zoom. Real-time viewing is mandatory unless you are in inconvenient time zones. Others are required to obtain specific permission to watch the pre-recorded lectures (on MediaServices).
  • If viewed on MediaServices, 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; Check piazza for further updates.

    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 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.

    MediaServices/YouTube: Lecture and Reciation Recordings

    CMU students who are not in the live lectures should watch the uploaded lectures at MediaServices 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 MediaServices.
    Lecture Date Topics Slides and Video Additional Materials Quiz
    0 -
    • Course Logistics
    • Learning Objectives
    • Grading
    • Deadlines
    		 TBA Quiz 0A
    Quiz 0B
    1 TBA
    • Introduction
    		 TBA The New Connectionism (1988)
    On Alan Turing's Anticipation of Connectionism
    McCullogh and Pitts paper
    Rosenblatt: The perceptron
    Bain: Mind and body
    Hebb: The Organization Of Behaviour
    		 Quiz 1
    2 TBA
    • Neural Nets As Universal Approximators
    		 TBA Shannon (1949)
    Boolean Circuits
    On the Bias-Variance Tradeoff
    3 TBA
    • The problem of learning, Empirical Risk Minimization
    		 TBA Widrow and Lehr (1992)
    Adaline and Madaline
    Convergence of perceptron algorithm
    Threshold Logic
    TC (Complexity)
    AC (Complexity)     		Quiz 2
    4 TBA
    • Empirical risk minimization and gradient descent
    • Training the network: Setting up the problem
    		 TBA Werbos (1990)
    Rumelhart, Hinton and Williams (1986)
    5 TBA
    • Backpropagation
    • Calculus of Backpropagation
    		 TBA Werbos (1990)
    Rumelhart, Hinton and Williams (1986)     		Quiz 3
    5.5 TBA
    • Backpropagation (Extra Lecture)
    • Calculus of Backpropagation
    		 TBA
    6 TBA
    • Convergence issues
    • Loss Surfaces
    • Momentum
    		 TBA Backprop fails to separate, where perceptrons succeed, Brady et al. (1989)
    Why Momentum Really Works
    7 TBA
    • Optimization
    • Batch Size, SGD, Mini-batch, second-order methods
    		 TBA Momentum, Polyak (1964)
    Nestorov (1983)
    Derivatives and Influences
    		 Quiz 4
    8 TBA
    • Optimizers and Regularizers
      • Choosing a divergence (loss) function
      • Batch normalization
      • Dropout
    		 TBA Derivatives and Influence Diagrams
    ADAGRAD, Duchi, Hazan and Singer (2011)
    Adam: A method for stochastic optimization, Kingma and Ba (2014)
    9 TBA
    • Shift invariance and Convolutional Neural Networks
    		 TBA Quiz 5
    10 TBA
    • Models of vision, Convolutional Neural Networks
    		 TBA
    11 TBA
    • Learning in Convolutional Neural Networks
    		 TBA CNN Explainer Quiz 6
    12 TBA
    • Learning in CNNs
    • Transpose Convolution
    • CNN Stories
    		 TBA
    13 TBA
    • Time Series and Recurrent Networks
    		 TBA Fahlman and Lebiere (1990)
    How to compute a derivative, extra help for HW3P1 (*.pptx)
    		 Quiz 7
    14 TBA
    • Stability and Memory, LSTMs
    		 TBA Bidirectional Recurrent Neural Networks
    - TBA
    • No Class - Spring Break
    		- Quiz 8
    - TBA
    • No Class - Spring Break
    		-
    15 TBA
    • Sequence Prediction
    • Alignments and Decoding
    		 TBA LSTM Quiz 9
    16 TBA
    • Sequence prediction
    • Connectionist Temporal Classification (CTC) - Blanks and Beam-search
    		 TBA
    17 TBA
    • Language Models
    • Sequence To Sequence Prediction
    		 TBA Labelling Unsegmented Sequence Data with Recurrent Neural Networks Quiz 10
    18 TBA
    • Sequence To Sequence Methods
    • Attention
    		 TBA Attention Is All You Need
    The Annotated Transformer - Attention is All You Need paper, but annotated and coded in pytorch!
    19 TBA
    • Transformers and GNNs
    		 TBA A comprehensive Survey on Graph Neural Networks Quiz 11
    20 TBA
    • Learning Representations
    • AutoEncoders
    		 TBA
    21 TBA
    • Variational Auto Encoders
    		 TBA Tutorial on VAEs (Doersch)
    Autoencoding variational Bayes (Kingma)     		Quiz 12
    22 TBA
    • Variational Auto Encoders II
    		 TBA
    23 TBA
    • Generative Adversarial Networks, 1
    		 TBA Quiz 13
    - TBA
    • No Class - Spring Carnival
    		- -
    24 TBA
    • Generative Adversarial Networks, 2
    		 TBA Quiz 14
    25 TBA
    • Hopfield Nets and Auto Associators
    		 TBA
    26 TBA
    • Hopfield Nets and Boltzmann Machines
    		 TBA
    		No Quiz
    27 TBA
    • Boltzmann Machines
    		 TBA

    Schedule of Recitations

    Recitation Date Topics Materials Videos Instructor
    TBA TBA TBA TBA

    TBA

    		TBA

    Assignments

    ∑ Ongoing, ∏ Upcoming

    Assignment Release Date (EST) Due Date (EST) Related Materials / Links
    TBA TBA 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