Awesome ML Resources

Curated list of resources on various ML topics found after browsing through lots and lots of materials over the years.

Pre requisites for ML:

• Linear Algebra refresher: http://cs229.stanford.edu/section/cs229-linalg.pdf
• Python numpy refresher: https://cs231n.github.io/python-numpy-tutorial/

Machine Learning Topics:

• Optimizers: https://ruder.io/optimizing-gradient-descent/
• SVM and kernel functions: https://www.youtube.com/watch?v=XUj5JbQihlU
• Xgboost: https://youtu.be/Vly8xGnNiWs
• All topics revision: http://cs229.stanford.edu/syllabus.html

Deep Learning Topics:

• Neural networks : http://karpathy.github.io/neuralnets/

• Backprop: https://cs231n.github.io/optimization-2/

• CNN: https://cs231n.github.io/convolutional-networks/

• RNN: http://karpathy.github.io/2015/05/21/rnn-effectiveness/

• LSTM : http://karpathy.github.io/2015/05/21/rnn-effectiveness/ accompanied with CS231n lecture 10

• Sequence to sequence models: https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html or https://www.youtube.com/watch?v=XXtpJxZBa2c&list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z&index=8

• Attention: https://jalammar.github.io/visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/

• Transformers: Maths/implementation: http://nlp.seas.harvard.edu/2018/04/01/attention.html and https://www.tensorflow.org/tutorials/text/transformer or if you're looking for an overview: http://jalammar.github.io/illustrated-transformer/

• Gaussian processes/ bayesian optimization: https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/lecturenote15.html

Particular to computer vision

• Faster rcnn : https://tryolabs.com/blog/2018/01/18/faster-r-cnn-down-the-rabbit-hole-of-modern-object-detection/ and flow with code: https://medium.com/@fractaldle/guide-to-build-faster-rcnn-in-pytorch-95b10c273439
• Yolo: Entertaining paper- https://pjreddie.com/media/files/papers/YOLOv3.pdf
• Centernet: https://medium.com/visionwizard/centernet-objects-as-points-a-comprehensive-guide-2ed9993c48bc

Reinforcement learning

• UCL course by David Silver: https://www.davidsilver.uk/teaching/
• Hands on: https://pythonprogramming.net/q-learning-algorithm-reinforcement-learning-python-tutorial/

NLP

• Tokenizers: https://blog.floydhub.com/tokenization-nlp/

GNNs:

• https://www.youtube.com/watch?v=8owQBFAHw7E
• https://twitter.com/PetarV_93/status/1306689702020382720

Top conferences:

• ICLR: https://iclr.cc/
• Neurips: https://nips.cc/
• ICML: https://icml.cc/
• ICCV: http://iccv2019.thecvf.com/

Practical/ hands on:

• Kaggle (for ML contests/ Data Science kernels): https://www.kaggle.com/
• Google Colab (with free GPU/ TPU): https://colab.research.google.com/
• AIcrowd: https://www.aicrowd.com/