![Title image: An Introduction To Deep Learning](images/title.png) ## Course Information ## A survey class of neural network implementation and applications. Topics include: optimization - stochastic gradient descent, adaptive and 2nd order methods, normalization; convolutional neural networks - image processing, classification, detection, segmentation; recurrent neural networks - semantic understanding, translation, question-answering; cross-domain applications - image captioning, vision and language. ### Instructor ### Joseph Redmon - Email: pjreddie@cs.washington.edu - Class: Tu/Thur 10:00-11:20 am, [CSE2](https://www.washington.edu/maps/#!/cse2) G20 ### TAs ### ### Office Hours ### Monday: - 3-4pm with Yifan on [Zoom](https://washington.zoom.us/j/4601411492?pwd=Ym81d1FSNzlsa3R4RXFCY2xndzN4Zz09) Tuesday: - 1-2pm with Kuo-Hao in CSE 2 276 Wednesday: - 3-4pm with Luyang on [Zoom](https://washington.zoom.us/j/97744830803) Thursday: - 9-10am with Rehaan on [Zoom](https://washington.zoom.us/j/99771827088) - 4-5pm with Joe on [Zoom](https://washington.zoom.us/j/3362756951) ### Resources ### - Ed Discussion Board: https://edstem.org/us/courses/29863/discussion/ - Canvas: https://canvas.uw.edu/courses/1578967 - Zoom: https://washington.zoom.us/j/97448158981 ## Homeworks ## - [Homework 0](https://github.com/pjreddie/dubnet/blob/main/hw0.md) - [Homework 1](https://github.com/pjreddie/dubnet/blob/main/hw1.md) - [Homework 2](https://github.com/pjreddie/dubnet/blob/main/hw2.md) ## Final Project: ## There will be a final project worth 20% of your final grade. The project can be done individually or in teams. For your final project you should explore any topic you are interested in related to deep learning. This could involve training a model for a new task, building a new dataset, improving deep models in some way and testing on standard benchmarks, etc. You project should probably involve some implementation, some data, and some training. The amount of effort and time should be approximately 2 homework assignments. Your final project presentation will be a website describing your project, and a 2-3 minute video. This summary should mention the problem setup, data used, techniques, etc. It should include a description of which components were from preexisting work (i.e. code from github) and which components were implemented for the project (i.e. new code, gathered dataset, etc). ## Lectures ## #### Lecture 0: Introduction - [Slides](https://docs.google.com/presentation/d/1ing0aXHxc62iNGCcOFR4zXD9y6lLhEQN-Zl0uw_GXag/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/JNpF30HUxEubVGFAUfn3zCa7saUP9-4bBaBjd5lEvmeChZTEf3XjDzr62qXvaXsOLh8iHZPuvOS5-8UE.4Ko3BgnJbe6LmOoJ) -------- #### Lecture 1: Machine Learning Review - [Slides](https://docs.google.com/presentation/d/1yNdiNJjPz6cvlBPWDUySYSkL9fvfY44hvoAvnQZfmjQ/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/sl-BFQ45RQUxRdJcw9nfVD67xQGnRYI4TZg538SbDbvgbWskQw_75g9skK99tcVz_PRW2YOrPKXVpjg.E7epW9KCkArqaUBi) - [Tensors](https://pjreddie.github.io/uwnet/slides/tensors.html) #### Lecture 2: Tensors and Classification in PyTorch - [Tensors iPynb](https://colab.research.google.com/drive/1ica1ZwMTLug_Qveoh68sGCptTfUaQerb?usp=sharing) - [Logistic Regression iPynb](https://colab.research.google.com/drive/1pKjEo_KFnoWmgPg0o8Zxr0x_JVU0JFAA?usp=sharing) - [Video](https://washington.zoom.us/rec/play/S5W9lofoI2aIJBNLkbYB3dT5IBXU_BYxiIvq3OO6z8KPRx1Chl8Ro7pwGYjFFmFb_5QRE5fiUsOqsxk.04BhGoo6VNwS67WT) --------- #### Lecture 3: Neural Networks and Optimization - [Slides](https://docs.google.com/presentation/d/1ktTiLEPLnG4jr1MFpk0qczdfXyA3rDBu2Sv7v1YAAQ0/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/muxZooS8pinY2pjWuzAPvGoS56JUIf-LO-2lNIasEWuK__Ap1emaSJmSuRM07ux1OmmWvTeVqG0ohHHJ.mfMmMzkml33PAB9n) #### Lecture 4: Training Neural Networks - [Slides](https://docs.google.com/presentation/d/1wvz_SrFdFf0PV53ZVNxoz1dGDWU3dWrQoZQvoW_-ZHc/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/_2uhvzD4K0-B_e5Zr8a-YEx_TWSGAdzmgWnHeoEV8ndj8oahbLg7fdrR5h9TZTwOIkz-kMu7VzaRAQE.1Oe6glfYo2Vi4KKZ) ------- Weekly Reading: [ImageNet Classification with Deep Convolutional Neural Networks](https://papers.nips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf) #### Lecture 5: Convolutional Neural Networks - [Slides](https://docs.google.com/presentation/d/1nhqXbYITrKeW_m1y-aEl7kPunhtxD2dtVosfkzGGA6k/edit?usp=sharing) - [Binary Classification iPynb](https://colab.research.google.com/drive/1NARbN9kniByK_loutD7Dy1uzJMHqkeV5?usp=sharing) - [Multiclass Classification iPynb](https://colab.research.google.com/drive/1c3laGaocFSIwVQsiPuzRLpAUtAUiAfCc?usp=sharing) - [Video](https://washington.zoom.us/rec/play/HNTVjUUf8Wp-PDIBPpwbfINuP7Pm5h4TzyDLHwLdotSDeqpuNg2Q7EYL-74qIT5EQEpmtGL9EBz-CPxP.MghKlIZlyhzD3HZ7) #### Lecture 5: Image Classification - [Slides](https://docs.google.com/presentation/d/1L_v6K2ZxibIfWwJj7R7OcGyo3EPX6w3F5Ph-UV1lswI/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/5x6iLSORQVepREWNMm5rkE0Ax9UvgjygYCIA5oU8Jaj4EGMeKx-gr3wMQKi_5oHmU1vSr1AH7RxfXeeg.jrXbLjgu4nbDCC57) ------ #### Lecture 6: Convolutional Network Architectures - [Slides](https://docs.google.com/presentation/d/1_WfkFr4U6w6GHcnA6qMMNWBnpBwmqSywxxTIj6uU_7E/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/q_KjA0KdeCi3w3WP2oJ2mDVhpQAheymI5p-UNb3v2Zy8ND2Ivwvu4hZd3t6nTa-MWUA2J3oJw_HRug.l2mnvq2eYIX60j07) #### Lecture 7: Segmentation and Detection - [Slides](https://docs.google.com/presentation/d/1ex-h5l0Oz-dtzphK-mP-XLGP6_pLc94oNYKtDvcwdQo/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/ZOC_E7vxEDvsNP-zgihKyNCRz5ZTZ5kS3tTqCA9pRxxo8x6hWdomC29kgPTjUl87ImW2WIy1wjjYa7sg.NRyhV6CXZvckOVm8) ------- #### Lecture 8: Segmentation and Detection Continued - [Slides](https://docs.google.com/presentation/d/1ex-h5l0Oz-dtzphK-mP-XLGP6_pLc94oNYKtDvcwdQo/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/TqtGmyPWTDDJejgQo0LvDSgYMJciFMvioSFBPS9MOXxm-R9HtEU9tV2WSeF-oFc9v9r9PXqJmh-U23ae.GSHdv0kvJgWhJKx8) #### Lecture 9: Detection and Instance Segmentation - [Slides](https://docs.google.com/presentation/d/1ChKuWTzEywx9VFdbCEYZX-PccGNa4jyiTsRqMVgLlP8/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/aKZh7y_khfXyalvtI0J7wpKMoOiK2KQ97USmNdTWiFOWTI3UrfTH9x0xQ3pN9tmgitrKOWc6pndAkzx_.5Alr72tvnP-crgB4) ------- #### Lecture 10: Vision and Language - [Slides](https://docs.google.com/presentation/d/1i9QlZ03R4zGwiydQDx1UMClQMXmxPVgRXq-qrojBjIg/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/54MNuNvCQ0NnuCEKwaGAB5HXXeVGT_JayiaNLA4A3KRvRpVy1Cf1Z6oG-ptC6nhV6Qx6GAN26BjE0cw.HxEJK5UOYEl4PicN) #### Lecture 11: Vision and Language Continued - [Slides](https://docs.google.com/presentation/d/1i9QlZ03R4zGwiydQDx1UMClQMXmxPVgRXq-qrojBjIg/edit#slide=id.g189bda7dd77_1_0) - [Video](https://washington.zoom.us/rec/play/AjF5tGMER0R3zlrpajW6_CKuMRRTTGxJDpOSryQC7BSXlDA5jLVwK2he5J45dCon0cbEsJhRnOyqEgWa.NY18F3V9Ik_491ol) ------- #### Lecture 12: Transformers - [Slides](https://pjreddie.github.io/uwnet/slides/10#1) - [Video](https://washington.zoom.us/rec/play/eNek-q8msatDieH831RwhQ7BIvDs9VsO7-uGnlKr03mRkvWfjA5DrbSGqUW6_hmdpcpfFZTyiWByFy8M.92VLi3XKEaSPa-es) #### Lecture 13: Transformers and Advanced Optimization - [Slides](https://pjreddie.github.io/uwnet/slides/10#1) - [Optimization Slides](https://docs.google.com/presentation/d/1XVf5lNIIthqLGWPH9_XdzYDfvcMwyVR9N5KHXIEfloQ/edit?usp=sharing) - [Video](./lecture13.zip) -------- #### Lecture 14: Sampling from RNNs - [Slides](https://pjreddie.github.io/uwnet/slides/11#2) - [Video](https://washington.zoom.us/rec/play/DBhACKNyck6iMv-plY5NtPXb5jXcS_gNw8ynQaVljh9NT8xOp_k-CwDqIbtnl9o1vZ__v50uh1Jb00iG.fLY_Dm-pWylQP5Gq) #### Lecture 15: GANs - [Slides](https://pjreddie.github.io/uwnet/slides/13#1) - [Video](https://washington.zoom.us/rec/play/70P_GZvxNEGWo-YIntfHPewwAZR7OPHQo5JwGO69xR27Haum2v2NQ6XIzRmduHpK7TBkVq38ED-onROz._UIeiqJai513PSsb) -------- #### Lecture 16: Diffusion Models - [Slides](https://docs.google.com/presentation/d/155m-4kMEhk0AeEqeVLObKSFxuXNaHPsjyL24GS_-y5I/edit?usp=sharing) - [Video](https://washington.zoom.us/rec/play/xrBg6edQ7t_YzG48LoHwNJSvzaEefdq9FojNXHt1IXxLHLNxmXz2VRGjsdKLbFvTzH8Ynj_Vmn75G_XS.uIEofKb2JDxYGw9V) #### Lecture 17: Alpha Go - [Slides](https://docs.google.com/presentation/d/13YJPp72XCW1OSC0vDOmiFjrcZlmJz3y-DlH_RZ8oVfs/edit#slide=id.p) - [Video](https://washington.zoom.us/rec/play/8jign7OlN78rCmDXgM4hoKJsMmz5U8lk7jAQlqJuwg2dfniw-u2IQW1BvNcos5RnetGEyZkM9NRAlPkM.0j-Yhc7l4HEx6dXG) ## Course Policies ## - Collaboration is encouraged! Feel free to discuss howemork and class material with other students. However, make sure you understand the concepts. Each student will complete and submit their own work. Do not directly or indirectly copy other students' work. - If you are working together or helping another student, work on teaching them concepts and answering general questions, not directly telling them what code to write. You're all smart; you should understand the line between productive collaboration and giving someone answers. - **For homeworks you may work with one other student in full collaboration** (i.e. sharing code, etc). Both students should still understand and contribute approximately equally to the solution and please note who you work with on your homework submission either as a comment in the code or in canvas. - Each student has 8 penalty-free late days for the whole quarter. Beyond that, late submissions are penalized up to 10% per day late.