- pythonprogramming.net
- towardsdatascience.com
- machinelearningmastery.com
- Image Search Engines and Basic Computer Vision
- https://brohrer.github.io/blog.html
- Articles and blogs
- Understanding CNNs - https://medium.freecodecamp.org/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050
- Introduction to Recurrent Networks - http://karpathy.github.io/2015/05/21/rnn-effectiveness/
- Introduction to Generative Models - https://blog.openai.com/generative-models/
- One Cycle Policy: https://sgugger.github.io/the-1cycle-policy.html
- Deep learning book - Ian Goodfellow
- Machine learning: A probabilistic perspective - P Murphy, 2012.
- Practical Statistics for Data Scientists - Peter Bruce, Andrew Bruce
- Dan Jurafsky and James H. Martin. Speech and Language Processing (3rd ed. draft)
- Yoav Goldberg. (A Primer on Neural Network Models for Natural Language Processing
- Machine Learning by Tom Mitchell.
- YouTube channels:
- Siraj Raval
- Two minute papers
- Coursera
- Andrew NG's Course on Machine Learning
- Andrew NG's Deep Learning Specialisation
- You can apply for Financial Support (access to the course for free for a period of time)
- Free for a week. ~Rs. 3000 per month to access assigments after that
- Contains 5 courses
- Neural Networks and Deep Learning
- Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
- Structuring Machine Learning Projects
- Convolutional Neural Networks
- Sequence Models
- Stanford’s CS231n: Convolutional Neural Networks for Visual Recognition. http://cs231n.github.io
- Stanford's CS229: Machine Learning Course. http://cs229.stanford.edu/
- Syllabus and Notes: http://cs229.stanford.edu/syllabus.html
- Stanford's CS224n: Natural Language Processing with Deep Learning. http://web.stanford.edu/class/cs224n/
- fast.ai
- Deep Learning Part 1: Practical Deep Learning for Coders
- Deep Learning Part 2: Cutting Edge Deep Learning for Coders
- Computational Linear Algebra: Online textbook and Videos
- Natural Language Processing
- Computer Vision
- Data Analysis
- Data Visualisation
- General Purpose Machine Learning
- scikit-learn
- Most ML Algorithms
- Cannot be used for Deep Learning
- Uniform API and generic functions.
- Doesn't support cuda
- keras
- Conceived to be an interface rather than a standalone ML framework
- Hence Uses Tensorflow, CNTK or Theano as backend (requires either to be pre-installed)
- Has helper functions for Sequence, Text and Image processing
- Recommended for beginners
- Supports cuda
- PyTorch (Facebook's)
- Usage similar to numpy
- Can be used to create Dynamic neural networks
- Backprop is automatically handled
- Supports cuda
- Simpler that Tensorflow
- Tensorflow (Google's)
- Most popular
- Not recommended for beginners
- Availabale for C++, Java, Android and JavaScript
- Theano
- Caffe
- CNTK
- scikit-learn
- [Installing python]
- [Anaconda] (https://www.anaconda.com/download/)
- [Instructions] (https://conda.io/docs/user-guide/install/windows.html)
- [RStudio] (https://www.rstudio.com/products/rstudio/download/)
- [Installing Jupyter notebooks] (http://jupyter.org/install)
- [Good Practices for Machine Learning] (https://developers.google.com/machine-learning/guides/rules-of-ml/)