Resources for Self-Study

The content on this guide touches concepts that we go through on our AI Maker Sessions.

Practical Courses on Kaggle Learn

Kaggle offers a series of free, practical courses that are especially valuable. We recommend doing them in the following order:

1. Python: Course Link
2. Pandas: Course Link
3. Intro to SQL: Course Link
4. Advanced SQL: Course Link
5. Intro to Machine Learning: Course Link
6. Intermediate Machine Learning: Course Link
7. Data Cleaning: Course Link
8. Feature Engineering: Course Link
9. Intro to Deep Learning: Course Link
10. Time Series: Course Link
11. Computer Vision: Course Link
12. Transfer Learning: Course Link
13. Reinforcement Learning: Course Link

Machine Learning Fundamentals and Deep Learning Theory

We also recommend reviewing these collection of videos regarding machine learning theory:

1. Linear Regression:

   • Fitting a Line to Data
   • Linear Regression Clearly Explained
   • Explanation of R-Squared

2. Logistic Regression:

   • Logistic Regression
   • Entropy Explained
   • Coefficients of Logistic Regression
   • Maximum Likelihood

3. Decision Trees:

   • Decision Trees Video

4. K-Nearest Neighbors:

   • K-NN Explained

5. Cross Validation:

   • Cross Validation Explained

6. Confusion Matrices:

   • Confusion Matrices Explained

7. Bias vs Variance

   • Bias and Variance Video

8. Regularization:

   • Intro to Regularization
   • Ridge Regression (L2 Regularization)
   • Lasso Regression (L1 Regularization)

9. Neural Networks:

   • Neural Networks and Deep Learning Playlist
   • Regularization for Neural Networks:
     • Regularizing Neural Networks
     • Why Regularization Reduces Overfitting
     • Dropout Regularization

10. Random Forests:

• Random Forests Playlist

11. Bagging and Boosting:
    • Bagging
    • Boosting
    • AdaBoost Explained
12. Gradient Boosting:
    • Gradient Boosting for Regression
13. XGBoost:
    • XGBoost Playlist
14. Principal Component Analysis (PCA):
    • PCA Overview
    • PCA Step-by-Step
15. Clustering with K-Means:
    • K-Means Clustering Video
16. Word Embeddings and Word2Vec:
    • Word2Vec Explained
17. Transformer Neural Networks:
    • Transformer Neural Networks
18. Naive Bayes:
    • Naive Bayes Explained
19. Support Vector Machines (SVM):

• Support Vector Machines - Part 1
• Support Vector Machines - Part 2
• Support Vector Machines - Part 3

To delve deeper on these topics, we recommend “An Introduction to Statistical Learning with Applications in Python” (Download PDF). This book has been made freely available by Springer and its authors. It also has an accompanying MOOC on EdX.

Self-Study Content for our Deep Learning AI Maker Sessions

Most of our workshops are taught in PyTorch and we recommend getting familiar with its syntax.

• PyTorch Basics
• Backpropagation
• Multilayer Perceptrons
• Convolutional Networks
• Transformers

We highly recommend the following resources:

• Jeremy Howard’s FastAI Book and online course

• Andrej Karpathy’s Deep Learning Series

• Udacity’s Deep Learning with PyTorch Course

• HuggingFace’s Transformers Course

• Goodfellow’s Deep Learning Book

• The Matrix Cookbook

Self-Study Content on Object Oriented Programming in Python

• Object Oriented Programming in Python

Self-Study Content for Model Deployment through REST APIs

We encourage candidates to go through the content of our workshop on deploying models with Docker and FastAPI to prepare for this topic.

• Building FastAPI endpoints for serving ML models - Tutorial by Sebastian Ramirez and Abhishek Thakur
• Building a FastAPI endpoint for language detection
• Our Handout for the Docker workshop

Self-Study Content on Docker

• Docker for Data Science

Self-Study Content on CRISP-DM

• What is CRISP-DM?

Self-Study Content on the No-Free-Lunch Theorems

• No-free-lunch.org
• Lack of A-Priori Distinction on Learning Algorithms by David Wolpert
• An Overview of the No-Free-Lunch Theorems for Machine Learning