# 11-785 Deep Learning https://deeplearning.cs.cmu.edu/ About Events OH Syllabus Lectures Recitations & Bootcamps Assignments Projects Page F26 [S26](https://deeplearning.cs.cmu.edu/S26/index.html) [F25](https://deeplearning.cs.cmu.edu/F25/index.html) Menu About OH Events Syllabus Lectures Recitations & Bootcamps Assignments Projects Page F26 [S26](https://deeplearning.cs.cmu.edu/S26/index.html) [F25](https://deeplearning.cs.cmu.edu/F25/index.html) **11-785** Introduction to Deep Learning _Fall 2026_ [ Class Streaming Link ](https://cmu.zoom.us/j/98857399276?pwd=ems3MzMvMjNQYkZzdTAyWGdVRGZSUT09) In-Person Venue: Giant Eagle Auditorium, Baker Hall (A51) ## Active Deadlines and Bulletin | Assignment | Deadline | Description | Links | | --- | --- | --- | --- | | HW1 P1 | Early Submission: Friday, Sep 4, 11:59 PM Final Submission: Friday, Sep 18, 11:59 PM | Implementing and training an MLP from scratch | [Gradescope Submission](https://www.gradescope.com/courses/1315509/assignments/8463000/review_grades) [HW1P1 Piazza](https://piazza.com/class/mo4ko44arnc3sg/post/111) | | HW1 P2 | Checkpoint Submission: Friday, Sept 4, 11:59 PM Final Submission: Friday, Sep 18, 11:59 PM | Phoneme state labelling using MLPs | [Gradescope Submission](https://www.gradescope.com/courses/1315509/assignments/8455147/review_grades) [HW1P2 Piazza](https://piazza.com/class/mo4ko44arnc3sg/post/83) | | HW1 Bonus | December, 4th, 11:59 PM | Implementing Adam, AdamW, BatchNorm and Dropout | [Gradescope Submission](https://www.gradescope.com/courses/1315509/assignments/8457950/submissions) [Piazza](https://piazza.com/class/mo4ko44arnc3sg/post/68) | | HW1 Autograd | December, 4th, 11:59 PM | Building the Autograd Engine - I | [Gradescope Submission](https://www.gradescope.com/courses/1315509/assignments/8475747) [Piazza](https://piazza.com/class/mo4ko44arnc3sg/post/68) | | **[ Important Piazza Posts Finder ](https://piazza.com/class/mo4ko44arnc3sg/post/38) ** | | **[ Projects Page ](https://deeplearning.cs.cmu.edu/shared/project.html) ** | ## About ### 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](https://www.youtube.com/channel/UC8hYZGEkI2dDO8scT8C5UQA). ### Course Description from a Student's Perspective 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 use 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 a guided project respectively. Course 11-485 is the undergraduate version worth 9 units, the only difference being that there is no final project nor guided project. ### Your Supporters **Instructors:** * **Bhiksha Raj** : bhiksha@cs.cmu.edu * **Rita Singh** : rsingh@cs.cmu.edu **Shadow Instructor:** * **Massa Baali** : mbaali@andrew.cmu.edu **Head TA:** * **Bradley Warren** : bwarren2@andrew.cmu.edu **Core Instruction TAs:** * **Miya Sylvester** : nsylvest@andrew.cmu.edu * **Mengchun Zhang** : mengchuz@andrew.cmu.edu * **Ahmed Safwat Abouhashem** : A.S.A@pitt.edu * **Ahmed Tahiru Issah** : aissah@andrew.cmu.edu * **Akshara Nadayanur Sathis Kanna** : anadayan@andrew.cmu.edu * **Anurag Aryal** : aaryal@andrew.cmu.edu * **Bradley Warren** : bwarren2@andrew.cmu.edu * **delphine nyaboke** : delphinenyaboke@gmail.com * **En Zheng** : enzheng@andrew.cmu.edu * **Euijin Hong** : ehong@andrew.cmu.edu * **Kangping Liu** : kangpinl@andrew.cmu.edu * **Nayesha Gandotra** : nayeshag@andrew.cmu.edu * **Ron Sarma** : rsarma@andrew.cmu.edu * **Hrishikesh Bhagwat** : hbhagwat@andrew.cmu.edu * **Hunter Lin** : hunterl@andrew.cmu.edu * **Shrirang Dabir** : sddabir@andrew.cmu.edu * **Yara Yao** : yuanyao3@andrew.cmu.edu * **Sneha Saravanan** : snehasar@andrew.cmu.edu * **George Lundgren** : glundgre@andrew.cmu.edu * **Devansh Jonnalagadda** : djonnala@andrew.cmu.edu * **Dhiksha Rathis** : drathis@andrew.cmu.edu * **Joshua Nee** : joshuatn@andrew.cmu.edu * **Bruno Payang** : bpayang@andrew.cmu.edu * **Uwimana Lowami** : ulowami@andrew.cmu.edu * **Boniface Godwin** : bgodwin@andrew.cmu.edu * **Aryan Chandel** : achandel@andrew.cmu.edu * **Ayush Morbar** : amorbar@andrew.cmu.edu * **Dinesh Varun Shankar Kandiyappan** : dkandiya@andrew.cmu.edu * **Felix Hirwa Nshuti** : fhirwans@andrew.cmu.edu * **Pengyu Chang** : pengyuch@andrew.cmu.edu * **Yixiong Fang** : yixiongf@andrew.cmu.edu * **Garima Tomar** : garimat@andrew.cmu.edu * **Lucky Gurjar** : lgurjar@andrew.cmu.edu * **Cédric Manouan** : cmanouan@alumni.cmu.edu ![S26 TAs](https://deeplearning.cs.cmu.edu/F26/images/TA_F26_2.png) Most of the IDL F26TAs who were present when the image was taken ![S26 TAs](https://deeplearning.cs.cmu.edu/F26/images/missing_TAs.png) This image remembers the TAs who were missing when the previous image was taken, represented by our mascot HIPPOPARAMETERS. ### Acknowledgments [ Past TA Acknowledgments](https://deeplearning.cs.cmu.edu/shared/TAs.html) - check out our TA hall of fame! ## Events Lectures: **Monday and Wednesday, 8:00 a.m – 9:20 a.m** Eastern Standard Time (EST). More information in the **Event Calendar** below. Recitations/Labs: **Friday, 8:00 a.m – 9:20 a.m** Eastern Standard Time (EST). More information in the **Event Calendar** below. Office Hours: Please refer to the **OH Calendar** below for up-to-date information. Homework Hackathons: During 'Homework Hackathons', students will be assisted with homework by the course staff. It is recommended to come as study groups. * Location: **Rashid Auditorium, GHC 4401** * Time: **Saturdays 2:00 p.m – 5:00 p.m** Eastern Standard Time (EST) **Event Calendar:** This Google Calendar contains all course events and deadlines. Feel free to add the entire calendar or any individual event to your personal Google Calendar. Ad-hoc changes to the schedule will be reflected in this calendar first. **OH Calendar:** This Google Calendar is dedicated only for Office Hours. Instruction on how to access an OH can be found in the description of the respective OH. Any ad-hoc changes to OHs will reflect in this calendar first. ## Syllabus | **Policy** | | --- | | **Breakdown** | | **Grading** | | Grading will be based on weekly quizzes (24%), homeworks (50%) and a course project (25%). 1% of your grade is for attendance. | | **Quizzes** | | **Quizzes** | | There will be weekly quizzes. * We will retain your best 12 out of the 14 quizzes you take. * Quizzes will generally (but not always) be released on Fridays and due 48 hours later, on Sundays. * **Quizzes will be worth 24% of your overall score.** | | **Homeworks** | | **Homeworks** | | There will be four homework assignments in total. Each homework (other than HW4) will include two parts, P1 and P2. For HWxP1, you will implement low-level operations in a deterministic setting. HWxP2 is more open-ended, you will compete with your classmates in a _Kaggle_ competition for the best performing model for a given task. * All homework materials will be released on **[Canvas](https://canvas.cmu.edu/courses/53621/assignments)** and submitted on **[Gradescope](https://www.gradescope.com/courses/1315509)**. * Each HWxP1 has a "on-time" deadline. HWxP1s are evaluated based on the number of correctly completed parts submitted to Gradescope by this deadline. * Each HWxP2 has 3 deadlines: "early", "on-time" and "late/slack". * **Early submission deadline:** You are required to make at least one submission to Kaggle by this deadline to receive a 3 % bonus points. This is intended to encourage students to begin their work early. * **On-time deadline:** This is the usual deadline for HWxP2 submissions. * **Late/Slack deadline:** Submissions after the on-time deadline will have to be made on a separate slack competition using slack days * **Slack days:** Everyone gets 10 slack days for the semester. They can distribute them across all their **HWxP2 only**. You will not be able to make any more submissions once you use up all your slack days. * **Kaggle scoring:** We will use _max(max(on-time score | given early submission), max(slack-day score))_ as your final score for HWxP2. * HWxP2 will have cutoffs based on the Kaggle leaderboard, and the exact value for each cutoff will be announced eventually depending on the class performance. **HIGH (90%), MEDIUM (70%), LOW (50%), and VERY LOW (30%)**. Scores will be interpolated linearly between these cutoffs. * There are bonus assignments for each HW. Bonus points (5% total) contribute to the final score by adding on top of the base score. Notice that bonus scores for 11485 and 11685/785 are different. 11485 Base Score = Assignments (50%) + Quiz (24%) + Attendance (1%) = 75% and 11685/785 Base Score = 11485 Base Score (75%) + Project (25%) = 100%. | | **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 students. In the event of a catastrophe (remember Spring 2020), the project may be substituted with the guided project. 11-685 Students may choose to do an open project instead of the guided project. * Detailed information regarding project reports and video presentations can be found **[HERE](https://docs.google.com/spreadsheets/d/1nguV-Z45QJkQUambJ4dv-SijA_ttsDQnwUYlbBOzicw/edit#gid=0)**. * The Peer Review of project videos is required of all students, 11-485/685/785. The task is for all students to review and grade 4-6 project videos that are assigned to them. It has to be completed over the last weekend, after classes finish (but before finals week). Each review takes around ~15-20 minutes. You must post at least one comment to the corresponding Piazza post of your reviewee. This comment must be a meaningful question or concern that demonstrates you have understood the material. More details will be shared over Piazza. | | **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](https://mediaservices.cmu.edu/channel/Introduction+to+Deep+Learning_Spring+2026/397642153)**). If viewed on MediaServices, the lectures of each week must be viewed before **Monday 8AM EST** of the following week (otherwise, it doesn’t count). * At the end of the semester, we will select a random subset of lectures and tabulate attendance. If you have attended at least **70%** of these (randomly chosen) lectures, you get the attendance credit. | | **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. | | **Academic Integrity** | | **Academic Integrity** | | You are expected to comply with the **[University Policy on Academic Integrity and Plagiarism](https://www.cmu.edu/policies/student-and-student-life/academic-integrity.html)** at all times. * You are allowed to talk with and work with other students on homework assignments. * You can share ideas but not code. You must 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. | | | | **End Policy** | ## Resources ### Study groups We believe that effective collaboration can greatly enhance learning. Thus, this course employs study groups for both quizzes and homeworks. It is highly recommended that you join a study group. ### Piazza **[Piazza](https://www.piazza.com)** is what we use for discussions, on pretty much everything. You should be automatically signed up if you are enrolled. If not, please reach out to a TA. ### Canvas **[Canvas](https://canvas.cmu.edu/courses/53621/assignments)** is where all the homework assignments and the weekly quizzes are posted. Please note that HWs are submitted on Gradescope, not Canvas. ### Gradescope **[Gradescope](https://www.gradescope.com/courses/1315509)** is where all the homework assignments are submitted and evaluated. You can make multiple submissions for each assignment. ### Hohum - IDL HW Platform **[NEW]** We have developed a new web-based platform, lead by TA Ahmed Issah, **[Hohum](https://hohum.andrew.cmu.edu/login)**. This is where all the homework part 1, bonus homeworks and the autograd homework assignments live. This is intended to reimagine the homework experience for IDL students, given the times we live in now. Every enrolled student will receive an invite over email to Hohum, please contact a TA in case you don't receive an invite. ### Kaggle **[Kaggle](https://kaggle.com/)** is where we test your understanding and ability to extend neural network architectures discussed in the lectures, particularly for the Part 2s of the homework assignments. Each Kaggle competition has a leaderboard where you can evaluate your model performance compared to your classmates. You can make upto 10 submissions each day for every assignment, the highest score will be used for grading. ### MediaServices/YouTube CMU students who are not in the live lectures should watch the uploaded lectures at **[MediaServices](https://mediaservices.cmu.edu/channel/Introduction+to+Deep+Learning_Spring+2026/397642153)** in order to get attendance credit. Links to individual videos will be available in the Schedule of Lectures table as they are uploaded. **[Our YouTube Channel](https://www.youtube.com/channel/UC8hYZGEkI2dDO8scT8C5UQA)** is where non-CMU folks can view all lectures and recitation recordings. ### Books and Other Resources Given the explosive development of the field, this course does not follow any specific book. We list some pioneering and relevant books at the bottom of this page. We will also share links to relevant reading material(s) for each class. Students are expected to familiarize themselves with the material before the class. You can also find some popular reading materials for deep learning: * [Distill](https://distill.pub/) * [Lil'Log](https://lilianweng.github.io/) * [Sebastian Raschka's Blog](https://magazine.sebastianraschka.com/) * [3Blue1Brown](https://www.3blue1brown.com/?topic=neural-networks) We expect that you will be in a position to interpret, if not fully understand, everything in these sources by the end of the course. ## Schedule of Lectures You can watch the recorded lectures on **[MediaServices](https://mediaservices.cmu.edu/channel/Introduction+to+Deep+Learning_Spring+2026/397642153)**. ## Recitations/Labs & Bootcamps ## Assignments ## Documentation and Tools ### Textbooks This is a selection of optional textbooks you may find useful ![Deep Learning](https://deeplearning.cs.cmu.edu/F26/images/dive.png) [**Dive Into Deep Learning**](http://d2l.ai) By Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola _PDF, 2020_ ![Deep Learning](https://deeplearning.cs.cmu.edu/F26/images/Goodfellow.jpg) [**Deep Learning**](https://www.deeplearningbook.org/) By Ian Goodfellow, Yoshua Bengio, Aaron Courville _Online book, 2017_ ![Neural Networks and Deep Learning](https://deeplearning.cs.cmu.edu/F26/images/Nielsen.jpg) [**Neural Networks and Deep Learning**](http://neuralnetworksanddeeplearning.com/) By Michael Nielsen _Online book, 2016_ ![Deep Learning Step by Step with Python](https://deeplearning.cs.cmu.edu/F26/images/Lewis.jpg) [**Deep Learning Step by Step with Python: A Very Gentle Introduction to Deep Neural Networks for Practical Data Science**](https://www.amazon.com/Deep-Learning-Step-Python-Introduction/dp/1535410264) By N. D. Lewis ![Parallel Distributed Processing](https://deeplearning.cs.cmu.edu/F26/images/Rumelhart1.jpg) [**Parallel Distributed Processing, Volume 1**](https://mitpress.mit.edu/books/parallel-distributed-processing-volume-1) By Rumelhart and McClelland ![Parallel Distributed Processing](https://deeplearning.cs.cmu.edu/F26/images/Rumelhart2.jpg) [**Parallel Distributed Processing, Volume 2**](https://mitpress.mit.edu/books/parallel-distributed-processing-volume-2) By Rumelhart and McClelland **Supported by** ![Google](https://deeplearning.cs.cmu.edu/F26/images/google-logo-transparent.png) 11-785 Introduction to Deep Learning | Carnegie Mellon University