yellow brick road to MrLd city

Documenting my journey in Machine Learning and Data Science. Follow me on my adventure to become a ML wizard!

Input, corrections and recommendations are welcome, send them to [email protected]!

This travel is best enjoyed using a LaTeX rendering addon for Chrome like Github-with-mathjax

Image Source: https://upload.wikimedia.org/wikipedia/commons/c/cb/Cowardly_lion2.jpg (PUBLIC DOMAIN)

 

#TODO in ML and Data Science

 

Papers:

• ❗ Understanding Deep Learning Requires Rethinking Generalization (Zhang et. al 2016); URL: https://arxiv.org/pdf/1611.03530.pdf

• Sharp Minima Can Generalize For Deep Nets (Dinh et. al 2017); URL: https://arxiv.org/abs/1703.04933

 - On the Complexity of Learning Neural Networks (Song, Vempala, Wilmes, Xie 2017); URL: https://arxiv.org/pdf/1707.04615.pdf

• ❗ Statistical Query Framework (Feldman 1993); URL: http://researcher.watson.ibm.com/researcher/files/us-vitaly/Kearns93-2017.pdf

Books:

• ❗ Deep Learning by Ian Goodfellow (http://www.deeplearningbook.org/)

• Grokking Deap Learning (https://www.manning.com/books/grokking-deep-learning)

 

Online Courses:

• ❗ Stanford: CS224 NLP with Deep Learning (https://www.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6)

• Udacity:

  • ❗ Deep Learning with Google (https://classroom.udacity.com/courses/ud730)

  • Reinforcement Learning (https://www.udacity.com/course/reinforcement-learning--ud600)

• Coursera:

  • Applied Text Mining in Python (https://www.coursera.org/learn/python-text-mining)

• MITx: Minds and Machines (https://courses.edx.org/courses/course-v1:MITx+24.09x+3T2017)

• DAT294x: Ethics and Law in Analytics and AI

 

Projects:

• ❗ kaggle: datasets

• NN from scratch, see:

  • https://theblog.github.io/category/neural-network/

  • Grokking Deep Learning

  • https://machinelearningmastery.com/implement-backpropagation-algorithm-scratch-python/

   

Tools:

• Tensorflow

• Theano

• Pytorch

 

Repetition:

• Probability Foundations (material from Social Computing & CS229)

 

Topics:

• Bayesian methods