MLAI_Basics

Here are some YouTube video links:

It is advised that you watch these at atleast 1.25x playback speed, as most of them are quite slow.

Level 0 (Youtube)

• How Machines Learn: https://www.youtube.com/watch?v=R9OHn5ZF4Uo
• Supervised Learning: Crash Course AI: https://www.youtube.com/watch?v=4qVRBYAdLAo
• Supervised Learning explained: https://youtu.be/Quh6x4kG6VY
• Unsupervised Learning explained: https://youtu.be/lEfrr0Yr684
• Neural Networks and Deep Learning: https://www.youtube.com/watch?v=oV3ZY6tJiA0
• Training Neural Networks: Crash Course: https://www.youtube.com/watch?v=lgKrup5oi_A

Level 1 (Youtube + Blogs)

• Math behind neural networks by 3Blue1Brown : link
• Gradient descent (how NNs train) by StatQuest : link
• Basics of traditional machine learning by StatQuest : Link
• how neural networks are trained link

---

Useful links:

Kaggle competitions

• 2 beginner level competitions:
  • https://www.kaggle.com/c/digit-recognizer
  • https://www.kaggle.com/c/titanic

Other Links:

• Want to find the code for a paper: Papers with code

Languages

• Learning pytorch with examples
• what is torch.nn

Advanced Overview of RL, NLP and AI

Deep Learning State of the Art (2020) https://youtu.be/0VH1Lim8gL8

List of conferences

https://waset.org/intelligent-systems-conferences

Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these awesome lectures!

https://deep-learning-drizzle.github.io/

Over 200 of the Best Machine Learning, NLP, and Python Tutorials — 2018 Edition

https://medium.com/machine-learning-in-practice/over-200-of-the-best-machine-learning-nlp-and-python-tutorials-2018-edition-dd8cf53cb7dc As suggested by the MIT course.

Languages

• Learning pytorch with examples
• what is torch.nn

Other Links

• Top 20 APIs for ml/ai
• Online Papers with code
• Awesome Gans Applications GitHub

Unexplored links

• If anyone is interested in intuitive understanding of learning you could skim through the blogs(https://www.offconvex.org/)

Papers

• Deep learning papers reading roadmap
• Visualizing and Understanding Convolutional Networks
• How transferable are features in deep neural networks?
• Applied ML RL DL problem papers
• Multimodal ML

---

Topic wise

Reinforcement Learning

• DeepLizard RL

NLP - DL

• CS224N NLP with DL
• TF-IDF Medium
• Language Learning with BERT - TensorFlow and Deep Learning Singapore

Computer Vision - DeepLearning

• DeepLizard
• Types of CNNs for CV
• nature blog by Yann LeCun on deep learning

DeepLearning

• CS230 deep learning stanford
• Deep Learning Lectures MIT

---

Competitive ML

• Pretarined models for pytorch (https://github.com/Cadene/pretrained-models.pytorch)
• CNN Architectures and How to Use Them with fastai (https://github.com/PPPW/deep-learning-random-explore/blob/master/CNN_archs/cnn_archs.ipynb)
• Efficient Net in fastAI Vision (https://forums.fast.ai/t/adding-efficientnet-to-fastai-vision/53371/4)
• How I won the Flipkart ML challenge (https://towardsdatascience.com/how-i-won-the-flipkart-ml-challenge-fcf1fcc9e06a)