Kranthi Kumar Rachavarapu

I have compiled a collection of resources that I have found helpful over the years. While some of the content may be outdated, I hope it is still useful.

Must read for research

  1. Novelty in Science - A guide to reviewers by Michael Black [Blog]

  2. How to Avoid the Pitfalls of Machine Learning: A Guide for Academic Researchers by Michael Lones [PDF]

  3. Some of the Best Advice You'll Ever Receive by Alemi [Blog]

    "What one fool can do, so can another, and the fact that some other fool beat you to it shouldn't disturb you: you should get a kick out of having discovered something." - Richard Feynman

  4. On why science writing can’t be separated from science doing by Michael Black (03-Dec 2022) [Tweet-thread]

  5. On Rebuttals

    • How we write rebuttals By Devi Parikh, Dhruv Batra, Stefan Lee [Blog]

    • How to ML Rebuttal – A Brief Guide [Tweet] [Doc]

  6. On Paper Writing

    • Notes on writing, by Fredo Durand [PDF]

    • How to write a great research paper, by Simon Peyton Jones [PDF][video]

    • How to write a paper in collaboration by Felix Hill (09-May 2023) [Tweet-thread]

    • Writing advice about writing on the internet [Tweet#1][Tweet#2]

  7. On Presentations

    • Small Guide To Giving Presentations, by Markus Püschel [PDF]

    • Giving an effective presentation: Using Powerpoint and structuring a scientific talk, by Susan McConnell [PDF][video]

    • Writing papers and giving talks, by Bill Freeman [PDF][Notes]

Blogs / Tutorials / GoodReads

  1. Mutual Information-based objectives in unsupervised learning (Aug 2019) [Blog]

  2. The Bandwagon by Claude E. Shannon (IRE Transactions - Information Theory 1959): [Blog]

  3. Semi-Supervised Learning (July 2020): [Blog]

  4. Excerpts from Mathematical Writing by Knuth, Larrabee, Roberts (1989): [PDF]

  5. Unpredictable Black Boxes are Terrible Interfaces by Maneesh Agrawala [Blog]

  6. The Bitter Lesson by Rich Sutton (March 13, 2019) [Blog]

    - The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin.
    - We want AI agents that can discover like we can, not which contain what we have discovered.
    - The “bitter lesson” of machine learning research argues that general methods that can leverage additional computation ultimately win out against methods that rely on human expertise from Sec 3.6 Scaling [PDF]

  7. Diffusion language models by Sander Dieleman (Jan 09, 2023) [Blog]

Pytorch

Courses

Some Courses (with videos) that I found useful.

  1. 6.008 Introduction to Inference MIT Tutorial Videos [Link]
    Topics: Graphical Models; HMM; Junction tree; MLE; Sampling (Metropolics & gibbs)

  2. STA 4273H: Large Scale Machine Learning Slides and Videos [Link]
    Prof. Russ Salakhutdinov
    Winter 2015
    Topics: Covers Ch.1,3,4,8,9,10,11,12,13 of CM Bishop Book
    Missing: Ch.5,6,7 (Neural nets, Kernel methods, Sparse Kernel methods)

  3. Machine Learning for Intelligent Systems - CS4780 - [Webpage] [Youtube]
    Prof. Kilian Weinberger Cornell
    Fall semester 2018
    Topics: SVM, Kernels, Bias-Variance decomposition, Gaussian Process, Bagging, Boosting

  4. Learning Theory - 580.691/491 - [Webpage] [Youtube]
    Prof. Reza Shadmehr JHU
    Spring semester 2014/2017

  5. Computer Vision (2021) [Webpage]
    Prof. Dr. Andreas Geiger

  6. Multiview 3D Geometry in Computer Vision [Website]
    Prof. Hyun Soo Park UMN
    Spring semester 2018
    Good Coverage & Good Homeworks

  7. CMSC 828W: Foundations of Deep Learning [Webpage] [Youtube] [Colab programming modules]
    Prof. Soheil Feizi University of Maryland, College Park
    Fall 2022
    Good intro to theoretical aspects of deep learning. Excellent videos.

Books

Link

Misc Reading

CC BY-SA 4.0 Kranthi. Last modified: September 01, 2023. Website built with Franklin.jl.