Welcome! Teaching myself ML

Hey all,

This is my first blog post ever.

My main goal for this blog is to track my progress in teaching myself Machine Learning and hopefully make it easier for others to see that it’s possible and not as daunting as they may think.

My initial plan is to follow most of the outline Jason Benn (@jasoncbenn) provided for becoming a Machine Learning Engineer while adding resources I find useful or think I need more practice in along the way.

P.S if any of these below interest you please reach out by either email or twitter as I’d love to have people to bounce ideas off of and discuss papers with.

• Go through Hands-On Machine Learning with Scikit-Learn & TensorFlow
• Read about Text feature extraction
• Fast.ai part 1 & 2
• Deep Learning Book
• Take CS231n, CS224n and CS229n and do all the homeworks
• Participate in some Kaggle competitions
• Start reading academic papers and implementing them (some papers I could start off with.
• Review Linear Algebra
• Go through Computational Linear Algebra course
• Review Calculus
• Implement softmax, the sigmoid function, backprop, and other neural net components
• Implement a basic neural net, a CNN, an RNN, and a GAN (Examples here)
• Do some Depth First Learning tutorials
• Read Neural Networks and Deep Learning
• (Bonus) Take CS294-Deep Unsupervised Learning

Things I’ll do over the course of this plan

• Read papers aggregated by Andrej Karpathy
• Read posts from Paper Club
• Interesting blogs to read
  • https://distill.pub (Most highly recommended)
  • https://thegradient.pub
  • https://www.inference.vc
  • https://blog.acolyer.org
  • https://openai.com/blog/
  • https://ruder.io

Inspired by these blog posts

• Everything you need to become self taught machine learning engineer
• How I learned to code