Reading List

Reading List

 

Course Notes

https://cs231n.github.io/

http://web.stanford.edu/class/cs224n/

https://cs230.stanford.edu/

http://cs229.stanford.edu/

https://deepgenerativemodels.github.io/notes/

https://stanford-cs329s.github.io/syllabus.html

http://vision.stanford.edu

https://cmu-multicomp-lab.github.io/mmml-course/

https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-034-artificial-intelligence-spring-2005/lecture-notes/

 

Classic Book

DL: https://www.deeplearningbook.org/

CV: https://www.amazon.com/Pattern-Recognition-Learning-Information-Statistics/dp/0387310738

NLP: Speech and Language Processing by Dan Jurafsky and James Martin

 

Interviews

DL: https://huyenchip.com/2019/07/21/machine-learning-interviews.htmlhttps://arxiv.org/abs/2201.00650

NLP: https://media-exp1.licdn.com/dms/document/C561FAQFtjvvg3C4I1g/feedshare-document-pdf-analyzed/0/1641345932333?e=1641499200&v=beta&t=NX5CA9WEfEK2igVmYZBCZKu6nEyfrg_6cjG929D24ec

DS:  https://github.com/kojino/120-Data-Science-Interview-Questions

 

CV

List of CV resources: https://github.com/kjw0612/awesome-deep-vision

 

NLP

List of NLP resources: https://github.com/keon/awesome-nlp

List of must-read NLP papers:  https://github.com/amanchadha/100-nlp-papers

NLP progress: https://github.com/sebastianruder/NLP-progress

NLP Testing Tool:  https://towardsdatascience.com/checklist-behavioral-testing-of-nlp-models-491cf11f0238

About decoding:
https://huggingface.co/blog/how-to-generate

Brain

Learn basics of deep learning for fMRI and EEG

EEG Datasets: https://github.com/meagmohit/EEG-Datasets

Electrophysiology Datasets: https://github.com/openlists/ElectrophysiologyData

fMRI: https://openfmri.org

Review of EEG ERP: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3016705/

EEG classic book - https://www.amazon.com/Niedermeyers-Electroencephalography-Principles-Clinical-Applications/dp/0781789427

 

Coding

- Python for ML/DL (beginner to advanced) (by myself)

- EEG Emotion Recognition (by myself)

- NLP Code (by myself)

-  RapidMiner (by myself)

 

Imbalance:  https://www.analyticsvidhya.com/blog/2020/07/10-techniques-to-deal-with-class-imbalance-in-machine-learning/
 

Model Compressionhttps://rachitsingh.com/deep-learning-model-compression/
 

Autoregressive modelshttps://eigenfoo.xyz/deep-autoregressive-models/

 

Misc

Explainable AI
https://christophm.github.io/interpretable-ml-book/

State of the art AI/ML paper: https://paperswithcode.com/sota

AI conference deadlines: https://aideadlin.es/

Acceptance rates: https://github.com/amanchadha/Conference-Acceptance-Rate

Current state of industry AI:  https://huyenchip.com/2020/06/22/mlops.htmlhttps://huyenchip.com/2022/01/02/real-time-machine-learning-challenges-and-solutions.htmlhttps://ai.googleblog.com/2022/01/google-research-themes-from-2021-and.html?m=1

Tool to track soda:  https://huyenchip.com/2018/10/04/sotawhat.html

 

Fun Engaging Educational Tools

Conv: https://cs.stanford.edu/people/karpathy/convnetjs/index.html

Statistics: https://seeing-theory.brown.edu/

Pandas: https://pandastutor.com/

LInear Algebra: http://matrixmultiplication.xyz/

Step by Step DL learning with digit:  https://cs.stanford.edu/people/karpathy/convnetjs/intro.html