Machine Learning & Deep Learning
Loose path:
- Math
- Programming
- Machine Learning concepts
- Specializations
Math
Understanding Math is pivotal. You can never be a good Machine Learning Scientistby skipping the Math.
Probability & StatisticsBasic Probability and Stats will be helpful in understanding ML algorithms like Naive Bayes.
Statistics 101 - UdacityTaught by the founder of GoogleX it's full of exercises in Python so you won't get bored.
MIT 18.06 Linear AlgebraProf. Strang is terrific! Not only he'll make you fall in love in Linear Algebra but you'll learnimportant concepts like SVD and matrix algebra. You might wanna grab this PDFas well. Be sure to also solve the exam question papers from here: link
MIT Single Variable CalculusThis is my personal favorite book, use it for SVC + MVC linkAmazing course but it gets quite tedious in the middle, you might wanna skim some geometry, but the key isto understand how optimization works. Be sure to solve questions from here: link
MIT Multi Variable CalculusUnderstanding vector calculus is necessary for algorithms like SVM, you might wanna skim some partswhich are purely theoretical. Be sure to solve questions from here: link
(Optional) Stanford Convex OptimizationWARNING: Do this course only if you're very good at math. Convex Optimization will teach you numerousfunctions used in Machine Learning. But this course is extremely heavy on Math!
The Book Probability Theory: The Logic of Science is very promising
Introduction to Programming & Algorithms
Python - Any one, both courses are equally good
Algorithms
Since you'll be coding a lot of algorithms yourself basic understanding is necessary
In case you want to go deeper
Introduction to Machine Learning
Machine Learning by Andrew NgA must do course, best course of Introduction to Machine Learning so far, light on Math and focuses more on concepts.
Amazing Course Highly Recommended - mlcourse.aiA must do course, best course of Introduction to Machine Learning so far, light on Math and focuses more on conceptsand is In Python and is supported by an International community of 15k+ Members..
Complete one out of two:
Machine Learning A-ZIntroductory course on ML focusing on not only Python but also R, one of the best sellers on Udemy.
Introduction to Machine Learning - UdacitySebastian Thrun does an awesome job explaining various approaches in ML. It gets a little boring in the middlebut overall it's very good.
Introduction to Machine Learning (Crash-Course By Berkeley and others)
Machine Learning Crash Course: Part 2 Perceptrons, logistic regression, and SVMs
Machine Learning Crash Course: Part 4 - The Bias-Variance Dilemma The Bias Variance Dilemma
Machine Learning Crash Course: Part 5 - Decision Trees and Ensemble Models Decision Trees
Applied Machine Learning
Two quick courses on applying the theory you learnt. They're short so I recommend doing both of them.
Specializations
Deep Learning
Neural Networks by Geofrrey HintonThis guy is the creator of backpropagation algorithm! Warning: very heavy on Math.
Must read book on Deep Learning: Free HTML book by GoodFellow
Must Read book on Deep Learning: Dive into Deep Learning An Interactive Deep Learning Book for students, engineers and researchers
Big Data & Large Scale Machine Learning
Natural Language Processing
Self Driving Car
Scientific Computing
Bonus Material
General Neural Network References:
Books/Guides on Deep/Machine Learning: (all excellent)
Hacker’s Guide to Neural Nets by karpathy(My Favourite)
Tutorials/Videos:
Youtube Playlist on “Deep Learning”, t from Oxford U. by Nando de Freitas
Andrew Ng’s online course on ML at Stanford comes highly recommended
Concepts in NN/Deep Learning:
Backpropagation, chapter 2 especially
Recurrent Neural Networks (RNN) (which mostly feature LSTM nowadays):
Traditional RNNs suffer from vanishing/exploding gradient. Hence LSTM & others…
Long Short-Term Memory (LSTM):
Zach Lipton post, “Demystifying LSTM” (with Tutorial theano code)
LSTM Forward And Backward Pass Understanding(Very Good!!)
Understanding LSTM's(Pretty Awesome!)
Attention Is All Your Need's
Issues In Keras Github explaining Attention (Very Very Important to read!)
Time Series Analysis (Py and R)
Awesome Blogs Explaining Decision Trees-:
Transformers Notes
- Lilianweng Attention Notes
- Actual Paper
- Notes from MLExplained
- Notes from NLP Harvard
- Notes from Mchromiak
- Slides from a Talk by the Authors
BertViz
Other Random Stuffs
System Design Distributed Systems
- https://learning.oreilly.com/videos/distributed-systems-in/9781491924914/9781491924914-video215265
- https://wiki.nikitavoloboev.xyz/distributed-systems
Decorators
- python - Making decorators with optional arguments - Stack Overflow
- https://stackoverflow.com/questions/9204671/pythonic-use-of-dict-in-the-function-self-init-of-a-class/
Asynchronous Messaging (rabbitMQ etc)
- https://medium.com/better-programming/rabbitmq-vs-kafka-1ef22a041793 (Kafka vs mq P1)
- https://medium.com/better-programming/rabbitmq-vs-kafka-1779b5b70c41 (Kafka vs mq P2)
Algos (DSA)
- https://algotree.org/algorithms/tree_graph_traversal/depth_first_search/
- https://docs.google.com/document/d/1wUCqhVHydWiDk6FJdFLSMpgigNrGcs4OFZg0Wa7JGEw/preview?pru=AAABcwi3bWI*FmXAKBN6rtACnzkERXBguA#
Load Testing
Stats
Multi-Processing
- https://stackoverflow.com/questions/16181121/a-very-simple-multithreading-parallel-url-fetching-without-queue/27986480#27986480
- https://medium.com/@bfortuner/python-multithreading-vs-multiprocessing-73072ce5600b
Asyncio
- https://skipperkongen.dk/2016/09/09/easy-parallel-http-requests-with-python-and-asyncio/
- https://medium.com/@cgarciae/making-an-infinite-number-of-requests-with-python-aiohttp-pypeln-3a552b97dc95
Tmux
Hope it’s Useful...
Thanks For Passing By!!!