README.md

Machine Learning

In this repo, you will find all the resources to learn machine learning based on my ML course at my university and what I have found useful to share.

To render equations on Chrome, please use GitHub with MathJax.

Phase 0: Requirements

• Basic python experience
• Basic probability understanding
• Basic vector calculus and linear algebra understanding

Phase 1: Supervised Learning

• Linear Regression
• Logistic Regression
• Project
  • Linear Regression: Housing Pricing
  • Logistic Regression: Handwritten Digit

Phase 2: Unsupervised Learning

• K-Nearest Neighbors (KNN)
• Decision Trees
• Project: Cancer Diagnosis

Phase 3 (Soon):

• Multi-layer Perceptron (MLP)
• Project: Classifying Images [CIFAR-10]

Phase 4 (Soon):

• K-Means
• Principal Component Analysis
• Project: Handwritten Digits

Phase Final (Soon):

• Outliers Detection
• Ensemble
• Project: Type I diabetes: Hypoglycemia Prediction

General Resources:

• Books:
  • Old book, easy to understand Machine Learning by Tom M. Mitchell
  • Covers everything in Machine Learning, more in-depth understanding, uses a lot of mathematical terms and equations Pattern Recognition and Machine Learning by Christopher M. Bishop
  • Covers everything in Deep Learning with fundamentals Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
  • Studenmund: Using Econometrics (7th Edition)
• Online Courses:
  • Free:
    • Machine Learning by Andrew Ng (Stanford University)
    • Deep Learning by fast.ai (CNN, RNN, CV, NLP, recommendation systems, Pytorch, time seies, and much more)
    • Intro to Machine Learning
    • Machine Learning by Georgia Tech
    • Introduction to Machine Learning by Vinod Venkatraman
  • Paid:
    • Become a Machine Learning Engineer
    • Deep Learning A-Z™: Hands-On Artificial Neural Networks by Kirill Eremenko
• Links:
  • Machine Learning Glossary by Google
  • MACHINE LEARNING 501 by Intel
  • Learn Python, Machine Learning, Pandas, Data Visualisation, SQL, R, and Deep Learning