MIT Introduction to Deep Learning 6.S191: Lecture 3
Convolutional Neural Networks for Computer Vision
Lecturer: Alexander Amini
** New 2025 Edition **

For all lectures, slides, and lab materials: http://introtodeeplearning.com​

Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

Learn how to talk Machine Learning with the best of them. I demystify the magic of deep learning and explain the buzz words

Deep learning is essential to developing cutting-edge AI, including image recognition, sound and voice recognition, and complex generative learning models - to name a few. Using Python within Anaconda, the process of building these models is easier with updated packages, security concerns mitigated, clean and clear notebooks, and multiple platforms installed at once.

Deep learning has shown remarkable success in processing and understanding unstructured data like text and images. In this module, we will explore how deep neural networks can be leveraged to build intelligent systems in the domains of natural language processing and computer vision. Get ready to dive into the exciting world of deep learning on text and images!

We will start with the agenda and course overview. Then, we will review some key machine learning concepts, including regression, optimization, regularization, and text and data representation.

--------------------

This video is part of Machine Learning University’s open-source "Application of Deep Learning to Text and Image Data" series, part of our Fundamentals of Machine Learning content. Access the full set of lessons, hands-on labs, and Jupyter Notebooks here:

🔗 GitHub Repository: https://github.com/aws-mlu/aws....-mlu-eep-traditional
🔗 Watch More MLU Videos: https://www.youtube.com/@machinelearninguniversity

Machine Learning University provides free, open-source AI/ML educational content for educators. New content is released regularly — subscribe to stay updated.

An overview of Deep Learning, including representation learning, families of neural networks and their applications, a first look inside a deep neural network, and many code examples and concepts from TensorFlow. This talk is part of a ML speaker series we recorded at home. You can find all the links from this video below. I hope this was helpful, and I'm looking forward to seeing you when we can get back to doing events in person. Thanks everyone!

Chapters:
0:00 - Intro and outline
1:42 - TensorFlow.js demos + discussion
3:58 - AI vs ML vs DL
7:55 - What’s representation learning?
8:40 - A cartoon neural network (more on this later)
9:20 - What features does a network see?
10:47 - The “deep” in “deep learning”
12:48 - Why tree-based models are still important
13:38 - How your workflow changes with DL
14:02 - A couple illustrative code examples
17:59 - What’s a hyperparameter?
19:44 - The skills that are important in ML
20:48 - An example of applied work in healthcare
21:58 - Families of neural networks + applications
28:55 - Encoder-decoders + more on representation learning
32:45 - Families of neural networks continued
35:50 - Are neural networks opaque?
38:29 - Building up from a neuron to a neural network
49:11 - A demo of representation learning in TF Playground
53:24 - Importance of activation functions
54:36 - What’s a neural network library?
58:43 - Overfitting and underfitting
1:02:38 - Autoencoders (and anomaly detection) screencast and demo
1:12:13 - Book recommendations

Here are three helpful classes you can check out to learn more:

Intro to Deep Learning from MIT → http://goo.gle/3sPj8To
MIT Deep Learning and Artificial Intelligence Lectures → https://goo.gle/3qh7H54
Convolutional Neural Networks for Visual Recognition from Stanford → http://goo.gle/3bbC34I

And here are all the links to demos and code from the video, in the order they appeared:

Face and hand tracking demos → http://goo.gle/2WTCwSc
Teachable machine demo → https://goo.gle/3bSCzCi
What features does a network see? → http://goo.gle/3e2zpA5
DeepDream tutorials → http://goo.gle/3bYIBTp and http://goo.gle/384B6JC
Hyperparameter tuning with Keras Tuner → http://goo.gle/2InBK7J
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs → http://goo.gle/309pMY5
Linear (and deep) regression tutorial → http://goo.gle/3sKxkN7
Image classification with a CNN tutorial → http://goo.gle/3qdD2Wb
Audio recognition tutorial → http://goo.gle/3kFpl1j
Transfer learning tutorial → http://goo.gle/3bV7D60
RNN tutorial (sentiment analysis / text classification) → http://goo.gle/3bVM1X7
RNN tutorial (text generation with Shakespeare) → http://goo.gle/3qmnrnz
Timeseries forecasting tutorial (weather) → http://goo.gle/3ecdYg9
Sketch RNN demo (draw together with a neural network) → http://goo.gle/3bbHTTy
Machine translation tutorial (English to Spanish) → http://goo.gle/3e7IJme
Image captioning tutorial → http://goo.gle/3sKFNQz
Autoencoders and anomaly detection tutorial → http://goo.gle/30aD0UA
GANs tutorial (Pix2Pix) → http://goo.gle/3kI1ZrB
A Deep Learning Approach to Antibiotic Discovery → https://goo.gle/3e7ivQD
Integrated gradients tutorial → http://goo.gle/2PxfRtq and http://goo.gle/3sE0bmq
TensorFlow Playground demos → http://goo.gle/2Px6rhB
Introduction to gradients and automatic differentiation → http://goo.gle/3sFVybo
Basic image classification tutorial → http://goo.gle/3c2AF3o
Overfitting and underfitting tutorial → http://goo.gle/3cdA9Qv
Keras early stopping callback → http://goo.gle/308XQUj
Interactive autoencoders demo (anomaly detection) → http://goo.gle/3kPfW7q
Deep Learning with Python, Second Edition → http://goo.gle/3qcQ5Y5
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition → http://goo.gle/386DKP4
Deep Learning book → http://goo.gle/3c2VQmd

Find Josh on Twitter → https://goo.gle/308Ve8P

Subscribe to TensorFlow → https://goo.gle/TensorFlow

This video introduces the fundamentals of protein design and summarizes the trajectory of the course with a focus on (1) the foundational biochemistry that protein structure prediction and design hinge on and (2) deep learning / machine learning principles overview.

Video from the Rosetta Commons PPI Workshop (February 2025)
Video Instructor: Amrita Nallathambi (UNC Chapel Hill)

Credits:
Instructor: Amrita Nallathambi
Teaching Assistants: Yehlin Cho, Cyrus Haas, and Matthew Hvasta,
RC Leadership and NSF Sponsor Grant PIs: Julia Koehler Leman & Jeffrey Gray
RC Education Director: Ashley Vater
Videographer: Canyon Florey
Rosetta Workshop Participants

00:00 - Introduction
00:20 - Deep Learning Revolution for Proteins
01:50 - The Transformer
03:38 - AlphaFold2 Overview
06:22 - AlphaFold2 Inputs
09:48 - AlphaFold2 Outputs
13:29 - Graph Neural Networks
16:24 - ProteinMPNN Loss
17:35 - Diffusion models
18:30 - RFDiffusion
19:52 - Inputs and Outputs
20:43 - Potentials

In this video, we'll go through data preprocessing steps for 3 different datasets. We'll also go in depth on a dimensionality reduction technique called Principal Component Analysis.

Coding challenge for this video:
https://github.com/llSourcell/....How_to_Make_Data_Ama

Charles-David's Winning Code:
https://github.com/alkaya/earthquake-cotw

Siby Jack Grove's Runner-up code:
https://github.com/sibyjackgro....ve/Earthquake_predic

Please subscribe. And like. And comment. That's what keeps me going.

More Learning Resources:
http://www.cs.ccsu.edu/~markov..../ccsu_courses/datami
http://www.slideshare.net/jaso....nrodrigues/data-prep
http://iasri.res.in/ebook/win_....school_aa/notes/Data
http://staffwww.itn.liu.se/~ai....dvi/courses/06/dm/le
http://ufldl.stanford.edu/wiki..../index.php/Data_Prep
http://machinelearningmastery.....com/how-to-prepare-d
https://plot.ly/ipython-notebo....oks/principal-compon

Public datasets:
https://github.com/caesar0301/....awesome-public-datas
https://aws.amazon.com/public-datasets/
http://archive.ics.uci.edu/ml/index.html
https://dreamtolearn.com/ryan/1001_datasets

Join us in our Slack channel:
http://wizards.herokuapp.com/

And please support me on Patreon:
https://www.patreon.com/user?u=3191693
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: http://chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available): https://www.wagergpt.xyz

Lets Make a Question Answering chatbot using the bleeding edge in deep learning (Dynamic Memory Network). We'll go over different chatbot methodologies, then dive into how memory networks work, with accompanying code in Keras.

Code + Challenge for this video:
https://github.com/llSourcell/....How_to_make_a_chatbo

Nemanja's Winning Code:
https://github.com/Nemzy/langu....age-translation/blob

Vishal's Runner up code:
https://github.com/erilyth/Dee....pLearning-Challenges

Web app to run the code yourself:
https://ethancaballero.pythonanywhere.com

Please subscribe! And like. And comment. That's what keeps me going.

More Learning resources:
https://www.youtube.com/watch?v=FCtpHt6JEI8&t=643s
https://www.youtube.com/watch?v=Qf0BqEk5n3o&t=637s
https://yerevann.github.io/201....6/02/05/implementing
https://www.youtube.com/watch?v=2A5DKPA5lAw
http://www.wildml.com/2016/01/....attention-and-memory
https://github.com/domluna/memn2n

Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/

And please support me on Patreon:
https://www.patreon.com/user?u=3191693
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: http://chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available): https://www.wagergpt.xyz

One-shot learning! In this last weekly video of the course, i'll explain how memory augmented neural networks can help achieve one-shot classification for a small labeled image dataset. We'll also go over the architecture of it's inspiration (the neural turing machine).

Code for this video (with challenge):
https://github.com/llSourcell/....How-to-Learn-from-Li

Please subscribe! And like. And comment. That's what keeps me going.

More learning resources:
https://www.youtube.com/watch?v=CzQSQ_0Z-QU
https://arxiv.org/abs/1605.06065
https://futuristech.info/posts..../differential-neural
https://thenewstack.io/googles....-deepmind-ai-now-cap

Join us in the Wizards Slack Channel:
http://wizards.herokuapp.com/

And please support me on Patreon:
https://www.patreon.com/user?u=3191693
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: http://chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available): https://www.wagergpt.xyz

Sebastian's books: https://sebastianraschka.com/books/
The lecture slides are available at: https://github.com/rasbt/stat4....53-deep-learning-ss2

Covers some of the basics of recurrent neural networks. In particular, this lecture covers

RNNs and Sequence Modeling Tasks: 00:00
Backpropagation Through Time: 20:23
Long-short term memory (LSTM): 31:42
Many-to-one Word RNNs: 45:16
Generating Text with Character RNNs: 50:45
Attention Mechanisms and Transformers: 1:00:09

https://github.com/aamini/introtodeeplearning

Lab Materials for MIT 6.S191: Introduction to Deep Learning - aamini/introtodeeplearning

Powered by VoiceFeed.
https://voicefeed.web.app?utm_source=youtube_githubtrenddaily&utm_medium=podcast

This video introduces the syllabus and organization of the "Introduction to Deep Learning and Generative Modeling" course.

Link to the slides: https://sebastianraschka.com/p....df/lecture-notes/sta

-------

This video is part of my Introduction of Deep Learning course.

Next video: https://youtu.be/6VbtJ9nn5ng

The complete playlist: https://www.youtube.com/playli....st?list=PLTKMiZHVd_2

A handy overview page with links to the materials: https://sebastianraschka.com/b....log/2021/dl-course.h

-------

If you want to be notified about future videos, please consider subscribing to my channel: https://youtube.com/c/SebastianRaschka

In this lecture, we highlight the course logistics and give a brief overview of the course.

The imagedeep.io series serves to bridge the knowledge gap between medical imaging and AI education.

It was co-founded and is co-instructed by:

Mazen Zawaideh, MD. Chief Radiology Resident and imagedeep.io co-instructor.

David Haynor, MD, Ph.D. Professor of Neuroradiology and imagedeep.io co-instructor.

Nathan Cross, MD. Assistant Professor of Neuroradiology and imagedeep.io co-instructor.

To learn more, visit www.imagedeep.io