salmankh47/Blogs

Website

Awesome Curated List 📛

🔴 https://aman.ai/
🔴 https://aman.ai/read/ (READING MATERIALS)
🔴 https://aman.ai/papers/ (PAPERS)
🔴 https://aman.ai/watch/ (Video Lectures)
🔵 https://github.com/heejkoo/Awesome-Diffusion-Models
🔴 https://huyenchip.com/2023/10/10/multimodal.html (multimodal)
💙 https://nn.labml.ai : For annotated papers and implementation

A detailed description and coding samples for core and advanced concepts

1. https://d2l.ai/index.html
2. Dive into Deep learning https://d2l.ai/
3. uvadlc-notebooks.readthedocs.io/en/latest/index.html UvA Deep Learning Tutorials! CODE also
4. Full Stack deep learning youtube lecture
5. CMU Deep learning recitation lectures.

A compiled list of free video-lecutres

1. https://www.marktechpost.com/free-ai-ml-deep-learning-video-lectures/

2. MIT brain and computing lab
   https://cbmm.mit.edu/knowledge-transfer/workshops-conferences-symposia/learning-disentangled-representations-perception

3. Blog on disentanglement
   http://jkimmel.net/disentangling_a_latent_space/

Curated list, DL/ML/NLP/CV/RL
https://deep-learning-drizzle.github.io/index.html#bcss

MUST READ A Commentary on the Unsupervised Learning of Disentangled Representations. Yet to be published in AAAI 2020
https://research.google/pubs/pub48962/

Blogs

1. https://jacobbuckman.com/#about
2. http://bamos.github.io/
3. http://inference.vc/
4. http://ruishu.io/
5. https://deeplearning.mit.edu/
6. https://www.jeremyjordan.me/
7. https://medium.com/tensorflow/mit-introduction-to-deep-learning-4a6f8dde1f0c
8. https://dmitryulyanov.github.io/deep_image_prior : Deep Image Priors. Random NN. Works for everything
9. https://hollobit.github.io/All-About-the-GAN/
10. https://github.com/pliang279/multimodal-ml-reading-list : Multi-model ML
11. https://github.com/nashory/gans-awesome-applications : Awesome GAN
12. https://sauln.github.io/blog/tda_explanations/ : Topology and Machine Learning
13. https://github.com/yenchenlin/awesome-adversarial-machine-learning : curated list of adversarial learning papers
14. https://github.com/floodsung/Deep-Learning-Papers-Reading-Roadmap : Roadmap for DL papers
15. https://www.cs.toronto.edu/~duvenaud/courses/csc2541/index.html : Course page of Differentiable Inference and Generative Models
16. https://www.themtank.org/a-year-in-computer-vision
17. https://colah.github.io/
18. https://thegradient.pub/
19. https://distill.pub/
20. https://fabiandablander.com/ :- Causal Inference and variational bais
21. https://github.com/salmankh47/machine-learning-notes CV ML Notes (Advanced Math)
22. https://jalammar.github.io/ :- Visualization of sequence models, NLP, transformers
23. https://ermongroup.github.io/cs228-notes/ : Blog on Graphical model, VAE, inference. Its nice, elegant with flow
24. https://wiseodd.github.io/ generative models
25. https://www.groundai.com/ domain specific papers
26. https://ml.berkeley.edu/blog/ ML Berkley Blog
27. https://ml.berkeley.edu/blog/posts/vq-vae/ VQ-VAE (DALL-E)
28. https://karpathy.github.io/ Andrej Karpathy
29. /www.casualganpapers.com papers explained
30. https://ai.stanford.edu/blog/ Stanford AI Blog
31. https://cohere.ai/ (A Good company for NLP)
32. https://bjlkeng.github.io/ Author focuses on autoregressive and autoencoder based models
33. uvadlc-notebooks.readthedocs.io/en/latest/index.html UvA Deep Learning Tutorials! CODE also
34. vaclavkosar.com blog for disentangled representation also vaclavkosar.com/ml/manipulate-item-attributes-via-disentangled-representation
35. Yordan Histrov: University of Edinburgh, https://yordanh.github.io/ Vaclav Kosar's: https://vaclavkosar.com/
    https://vaclavkosar.com/ml/manipulate-item-attributes-via-disentangled-representation
    works in disentangled representation
36. Representation Learning : https://ift6135h18.wordpress.com/category/lectures/page/2/
37. Transformer blog : https://sebastianraschka.com/blog/2023/llm-reading-list.html

Paper implimentation

1. nn.labml.ai Annotated paper implimentation

Classical AI

• https://www.cse.wustl.edu/~garnett/cse511a/
• UC-Berkley: https://www.youtube.com/results?search_query=artificial+intelligence+uc+berkeley
• MIT : https://www.youtube.com/playlist?list=PLUl4u3cNGP63gFHB6xb-kVBiQHYe_4hSi

Other Blogs to check

1. Weights and Biases
2. Hugging face
3. Microsoft
4. FB AI
5. Google Brain
6. Deep mind blog
7. Open AI
8. Stanford AI Blog

Online text

1. neuralnetworksanddeeplearning.com/

NYU Machine learning/Deeplearning course

1. Prob and Stat for Data science : https://cims.nyu.edu/~cfgranda/pages/DSGA1002_fall17/index.html
   

2. Machine learning : https://davidrosenberg.github.io/ml2017/#home
   : https://www.youtube.com/watch?v=U6M0m9c9_Js&list=PL9gLVsLmOO8oq4vB1BYxIsl6z6Zf71PC8
   

3. Deeplearning : https://atcold.github.io/pytorch-Deep-Learning/
   : https://www.youtube.com/watch?v=0bMe_vCZo30&list=PLLHTzKZzVU9eaEyErdV26ikyolxOsz6mq
   : https://cds.nyu.edu/deep-learning/ (Yann LeCun's Course, Priority 1)
   

4. Inference and Representation : https://inf16nyu.github.io/home/
   

5. Mathematics of ML : https://www.youtube.com/watch?v=3wbLr-NnIKI&list=PLTPQEx-31JXhguCush5J7OGnEORofoCW9

Stanford

Representation learning in CV

https://web.stanford.edu/class/cs331b/schedule.html

AI Lab Courses/Notes/Papers

https://ai.stanford.edu/courses/

CS228 - Probabilistic Graphical Models

https://cs228.stanford.edu/#other-resources

☑️ Speech and Language Processing ⚠️

https://web.stanford.edu/~jurafsky/slp3/ (currently reading for NLP)

Caltech

Learning from data

http://www.work.caltech.edu/telecourse.html

University of sunny buffallo

ML and DL (simple and Concise)

https://cedar.buffalo.edu/~srihari/CSE676/

Cornel

Machine learning for Intelligent Systems

https://www.youtube.com/watch?v=MrLPzBxG95I&list=PLl8OlHZGYOQ7bkVbuRthEsaLr7bONzbXS

FAU Germany: Andreas Maier

PR and DL

https://www.youtube.com/c/AndreasMaierTV/playlists

University of Waterloo

ML + DL (Basic + Intro)

https://www.youtube.com/playlist?list=PLdAoL1zKcqTW-uzoSVBNEecKHsnug_M0k

University of Tuebingen

Playlist ML, DL, Stat learning

https://www.youtube.com/channel/UCupmCsCA5CFXmm31PkUhEbA

Probabilistic ML

https://uni-tuebingen.de/en/180804

Coursera course on Latent Variable Models

https://www.coursera.org/learn/bayesian-methods-in-machine-learning/home/welcome

Udemy courses on Computer vision

University of Maryland

Foundations and Advanced DL

https://www.cs.umd.edu/class/fall2020/cmsc828W/

Youtube link

https://www.youtube.com/playlist?list=PLHgjs9ncvHi80UCSlSvQe-TK_uOyDv_Jf

CMU

Deep learning course page

https://deeplearning.cs.cmu.edu/F23/index.html (S23/F22/S22 also available in link)

Tom Mitchell - ML Course

http://www.cs.cmu.edu/~tom/
http://www.cs.cmu.edu/~ninamf/courses/601sp15/lectures.shtml
(Masters level) http://www.cs.cmu.edu/~tom/10701_sp11/lectures.shtml (Ph.D level) https://www.youtube.com/watch?v=U1xIBLLzP1g&list=PLzVF1nAqI9VmydeMepM2pJxf-TAIJv6p-

Probabilistic Graphical models

https://www.cs.cmu.edu/~epxing/Class/10708/lecture.html

Multi-modal ML ⚠️

https://www.youtube.com/playlist?list=PLki3HkfgNEsKPcpj5Vv2P98SRAT9wxIDa
https://www.youtube.com/playlist?list=PLTLz0-WCKX616TjsrgPr2wFzKF54y-ZKc

UC Berkley

Deep Learning

https://www.youtube.com/watch?v=Va8WWRfw7Og&list=PLZSO_6-bSqHQHBCoGaObUljoXAyyqhpFW
https://cs182sp21.github.io/
https://inst.eecs.berkeley.edu/~cs182/sp23/

University of Amsterdam

DL with coding

site : uvadlc.github.io
code : uvaldc-notebooks.readthedocs.io/en/latest/index.html

University of Toronto

1. https://www.cs.utoronto.ca/kr/ : Knowledge Representation Group
2. https://www.cs.utoronto.ca/compling/people.html : NLP Group
3. https://web.cs.toronto.edu/research/artificial-intelligence : AI Group
4. http://www.cs.toronto.edu/~erdogdu/
5. http://www.cs.toronto.edu/~duvenaud/

Statistics

---

1. (easy) Student guide to Bayesian Statistics for ML : https://www.youtube.com/playlist?list=PLwJRxp3blEvZ8AKMXOy0fc0cqT61GsKCG

2. Bayesian Stat, Virgina Tech : https://www.youtube.com/playlist?list=PLLG1JiumJDku-znWg0WYRfTr9gF2HsNkl

3. Intro Bayesian Stat : https://www.youtube.com/playlist?list=PLuRpZIQQRQedb2GM2WhKSEzojGN-BIIR9

4. Stat and Application MIT : https://ocw.mit.edu/courses/mathematics/18-650-statistics-for-applications-fall-2016/index.htm

5. Deep Bayes : https://www.youtube.com/playlist?list=PLe5rNUydzV9QHe8VDStpU0o8Yp63OecdW

6. Stat Harvard (going on) : https://www.youtube.com/playlist?list=PL2SOU6wwxB0uwwH80KTQ6ht66KWxbzTIo

7. NPTEL (IIT-Khag)(Very Nice): https://www.youtube.com/playlist?list=PLbRMhDVUMngeD_vOeveVE-3b7wu_AZph9

AUDIO

• The Sound of AI: https://www.youtube.com/c/ValerioVelardoTheSoundofAI/playlists
• Audio signal processing: https://www.youtube.com/playlist?list=PL-wATfeyAMNqIee7cH3q1bh4QJFAaeNv0

Graphical Model & DL

CMU

1. https://www.cs.cmu.edu/~epxing/Class/10708-20/lectures.html

Optimization

1. https://www.youtube.com/watch?v=9hToSoZXM9s&list=PL7y-1rk2cCsDOv91McLOnV4kExFfTB7dU

Math for ML and DL

1. https://www.youtube.com/watch?v=ssWr6Q0mGIA&list=PL7y-1rk2cCsAqRtWoZ95z-GMcecVG5mzA

Channels

1. Scalable Machine Learning (CS281B) - Alex Smola
   https://www.youtube.com/playlist?list=PLOxR6w3fIHWzljtDh7jKSx_cuSxEOCayP

2. CMU Deep Learning
   https://deeplearning.cs.cmu.edu/F23/index.html (Course page) https://www.youtube.com/channel/UC8hYZGEkI2dDO8scT8C5UQA
   https://www.youtube.com/playlist?list=PLp-0K3kfddPwJBJ4Q8We-0yNQEG0fZrSa
   https://www.youtube.com/watch?v=oqvdH_8lmCA&list=PLoZgVqqHOumTqxIhcdcpOAJOOimrRCGZn

3. Berkley, Unsupervised Deep Learning
   https://sites.google.com/view/berkeley-cs294-158-sp19/home
   https://www.youtube.com/watch?v=V9Roouqfu-M&list=PLwRJQ4m4UJjPiJP3691u-qWwPGVKzSlNP
   https://www.youtube.com/watch?v=Va8WWRfw7Og&list=PLZSO_6-bSqHQHBCoGaObUljoXAyyqhpFW DL

4. University of Utah, Machine learning and Deeplearning course https://www.youtube.com/channel/UCDUS80bdunpmvWVPyFRPqFQ

5. Stanford CS230 (Deep learning)
   https://cs230.stanford.edu/lecture/

6. Stanford CS231n (Conv Neural Network)
   https://www.youtube.com/playlist?list=PLkt2uSq6rBVctENoVBg1TpCC7OQi31AlC (Winter 2016)
   https://www.youtube.com/playlist?list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk (2017)

7. Stanford CS224n (NLP)
   https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z

8. Stanford CS234 (Reinforcement learning)
   https://www.youtube.com/playlist?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u

9. Anima Ananda Kumar Foundation of ML. Stat inference
   https://www.youtube.com/playlist?list=PLVNifWxslHCDlbyitaLLYBOAEPbmF1AHg

10. Representation learning by Simons Institute
    https://www.youtube.com/watch?v=ACdjYP0-cMw&list=PLgKuh-lKre13UNV4ztsWUXciUZ7x_ZDHz

11. Bayesian lecture series, DeepBayes, Variational inference etc
    https://www.youtube.com/channel/UC9KcwaZ9gSvcYNs7Jx3oNaQ

12. Deep mind Deeplearning lecture
    https://www.youtube.com/channel/UCP7jMXSY2xbc3KCAE0MHQ-A

13. Deep learning MIT 6.S191
    https://www.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI

14. CMU (Alex Smola)
    https://www.youtube.com/playlist?list=PLZSO_6-bSqHTTV7w9u7grTXBHMH-mw3qn
    https://www.youtube.com/watch?v=U1xIBLLzP1g&list=PLzVF1nAqI9VmydeMepM2pJxf-TAIJv6p-

15. Linear Algebra for ml
    https://www.youtube.com/playlist?list=PLiiljHvN6z1_o1ztXTKWPrShrMrBLo5P3

16. Max Planck Institute of Intelligent Systems. https://www.youtube.com/c/MaxPlanckInstituteforIntelligentSystems/playlists

17. DeepMind: Unsupervised Representation Learning https://www.youtube.com/channel/UCf4SX8kAZM_oGcZjMREsU9w/videos

18. Data Science ML/DL, Ali ghodsi
    https://www.youtube.com/c/DataScienceCoursesUW/playlists

19. Basics of Information theory must watch https://www.youtube.com/channel/UCciVrtrRR3bQdaGbti9-hVQ/videos

20. Jeremy Howard Fast AI (good for practical coding) https://www.youtube.com/user/howardjeremyp/playlists

21. Full Stack Deep Learning For end-to-end deployment and coding https://www.youtube.com/c/FullStackDeepLearning/playlists

22. University of Tubingen https://www.youtube.com/channel/UCupmCsCA5CFXmm31PkUhEbA

23. Soheil Feizi https://www.youtube.com/user/soheilfeiz/videos

24. Florian Marquard (ML and Physics) https://www.youtube.com/watch?v=B2Jnurp-OkU&list=PLemsnf33Vij4-kv-JTjDthaGUYUnQbbws

25. Information Theory, Advanced inference in Graphical models https://www.youtube.com/channel/UCvPnLF7oUh4p-m575fZcUxg/videos

26. Maziar Raissi : Audio, Language, RL models https://www.youtube.com/channel/UCxEiGqJ2e-Mg9oQMjVv6poQ/playlists

27. Statistical Rethinking
    https://www.youtube.com/watch?v=oy7Ks3YfbDg&list=PLDcUM9US4XdM9_N6XUUFrhghGJ4K25bFc
    https://www.youtube.com/watch?v=6AWZS4Ho2Z8&list=PLyGKBDfnk-iDj3FBd0Avr_dLbrU8VG73O (MIT)
    

28. Transformers United (Assorted) https://www.youtube.com/watch?v=P127jhj-8-Y&list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM
    

29. Ian GoodFellow, DL Book companion video https://www.youtube.com/watch?v=vi7lACKOUao&list=PLsXu9MHQGs8df5A4PzQGw-kfviylC-R9b

Fantastic Misc Lecture channel

Jordan Boyd

• https://www.youtube.com/c/JordanBoydGraber/playlists

London Machine Learning Meetup

• https://www.youtube.com/channel/UCpwC9QC0lWaEJ85MoMRFvrA/videos

Simons Institute
* https://www.youtube.com/user/SimonsInstitute/playlists

ML Papers explained

• https://www.youtube.com/user/amirfzpr/playlists

DL Paper explained

The AI Epiphany
* https://www.youtube.com/c/TheAIEpiphany/playlists

Yannic Kilcher
* https://www.youtube.com/c/YannicKilcher/playlists

AI Pursuit
* https://www.youtube.com/channel/UCe_QLqna7cFtTCfZ0a8pycg/playlists

AI Socratic circle
* https://www.youtube.com/channel/UCfk3pS8cCPxOgoleriIufyg

Disentangled Representation * https://www.youtube.com/watch?v=XNGo9xqpgMo&list=PLnCYZ7raesezWmCO4WZ4zF5uMPB_QHQZ5 * https://ustcnewly.github.io/2018/12/25/deep_learning/Disentangled%20Representation/ * https://towardsdatascience.com/disentangling-disentanglement-in-deep-learning-d405005c0741 * https://medium.com/swlh/learning-disentangled-representations-with-variational-autoencoders-b1bfe237fffb * https://towardsdatascience.com/disentangling-disentanglement-in-deep-learning-d405005c0741 * https://towardsdatascience.com/what-a-disentangled-net-we-weave-representation-learning-in-vaes-pt-1-9e5dbc205bd1

Books

Optimization For Machine Learning, Suvrit Sra, Sebastin Nowozin, Stephen J. Wright
Bayesian stat https://github.com/fdabl/Intro-Stats
Datamining DL/ML Book - Harvard : http://www.mmds.org/

LISP & Structure and interpretation of programs (Wizard book)

• https://www.youtube.com/playlist?list=PLE18841CABEA24090