Resources

RESOURCES

I generally spend time a lot of time searching for relevant resources to broaden my knowledge and learn new things. Hence, as a habit, I always pool the links in an excel sheet to keep the assortment handy. It’s always good to have the resources around to quickly read important concepts and troubleshoot problems.

Thought of listing down some material that I keep a track of and which I felt was extremely useful :)

• Good Reads
• Good Books
• Good Blogs

Good Reads

• Interesting Language Rhetorics - “Mistakes were made”, Non-Apology Apology, Weasel Word, Non-Denail Denail.
• What Every Programmer Absolutely, Positively Needs To Know About Encodings And Character Sets To Work With Text. Detailed blog on the vision behind text encoding styles.
• Docker E2E blogs by Prakhar Srivastav A topic wise clustering of docker technology.
• Embedding Projector by Google. Interactive word embedding visualizer by Google. It projects high dimensional data through different dimensionality reduction techniques.
• MLOps concepts for busy engineers: Model Serving. Overview about various model deployment strategies.
• Diversity in AI is not your problem, it’s hers. Talks about the prevailing “hers” VS “his” pronoun bias in many language technologies.
• Losing languages, losing worlds by CNN Interactives. Audio interactive news report on why language is more central to human survival than just mere communication.
• Why You Should Do NLP Beyond English by Sebastian Ruder. Outlines how NLP ≠ English only, but should be studied for all 7000+ languages spoken around the world.
• Buffalo buffalo Buffalo buffalo buffalo buffalo Buffalo buffalo. This is a grammatically correct sentence in English where the word “Buffalo” has different semantic meanings as Proper Noun, Verb and Common Noun.
• Tokenizers: How machines read. A detailed blog on how tokenizers work.
• Why are GPUs well-suited to deep learning? - Quora. High-level explanation by Tim Detters on why GPU are so fast and effective.
• What is the No Free Lunch Theorem?
• Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning. Provides different levels of in-depth understanding on how GPUs and Tensor Core work.
• Choosing the right GPU for deep learning on AWS. Advice on choosing GPU instances on AWS.
• BERT Explained – A list of Frequently Asked Questions by Yashu Seth. A concise blog summarizing the important aspects related to BERT.
• Are Chess Discussions Racist? An Adversarial Hate Speech Data Set by Ashiqur R. KhudaBukhsh, et al.
• Resources to understand REST APIs - [1] [2] [3] [4] [5] [GET/POST/PUT] [WSGI]
• References blogs to understand JSON : JavaScript Object Notation - [1] [2]

Good Books

• The Language Instinct by Steven Pinker
  Read Kaustubh Dhole’s summary blog on this book.
• Practical Natural Language Processing by Sowmya Vajjala, et al.
  Bridges the gap between NLP research and practical applications.
• Linguistic Fundamentals for Natural Language Processing by Emily M. Bender
  Explains core linguistic principles succinctly.
• Speech and Language Processing by Dan Jurafsky & James H. Martin
  Comprehensive book to understand theoretical aspects of ML/NLP
• Interpretable Machine Learning by Christoph Molnar
  Great read to understand Machine Learning Interpretability or Explainable AI
• NLP: A Paninian Perspective by Akshar Bharat, et al.
  Provides a Paninian perspective of NLP on Indian Languages.
• Linguistics for the Age of AI by Marjorie McShane and Sergei Nirenburg
  Extremely rich and detailed description around Natural Language Understanding in today’s age.
• The Mayfield Handbook of Technical & Scientific Writing by Leslie C. Perelman, et al.
  A comprehensive advice on writing scientific / technical documents.

Good Blogs

• vsupalov. Rich blogs on anything related to Docker. [Docker Learning Roadmap]
• Pratik Bhavsar
  Great blogs on NLP, ML and Data Science in general. He also runs a Data Science Slack community maxpool.club that holds some great discussions!
• Chris McCormick and Jay Alammar
  Perhaps the best articles to understand inner workings of Language Models, Transformers, BERT, etc.
• Eugene Yan
  Actively blogs about ML, Career Growth & Productivity
• Kaustubh Dhole
  Comprehensive blogs on niche topics in NLP, ML
• Rahul Agarwal
  His blogs explain deep basics of Python programming and ML.
• Ajit Rajasekharan
  Super blogs on Deep Learning, BERT models, and Embeddings.
• Sebastian Ruder
  Frequently blogs on Computational Linguistics, Transfer Learning
• Chip Huyen
  Elaborate blogs on best engineering practices for ML in Production.
• Shashank Prasanna
  Deeply informative medium articles regarding AWS GPU & Cloud Computing.
• Amit Chaudhary
  Explains ML concepts with clean, intuitive visual diagrams. [Machine Learning Toolbox] [Resources by Amit]
• Tim Dettmers
  Exhaustive blogs on inner workings of GPU, neuroscience and hardware-optimization. [1].
• Martin Thoma
  Writes short blogs on ML, Efficient Coding, Web.
• Robert (Munro) Monarch
  Blogs on depths of Linguistics, ML and Human Intelligence.
• Edward Ma [NLP Progress Tracker]
  Writes short blogs on all aspects of NLP Systems on [Medium]