Foundations for AI & ML

The math and code every AI/ML career stands on.

Build the four pillars of machine learning from the ground up: linear algebra, probability, calculus, and Python. Then put them to work training a neural network and touring the core ML algorithms, one hand-illustrated chapter at a time.

beginneraimlfoundationslinear-algebrapython

31 capsules114 figures~6 hoursby Dr. Raj Dandekar

Read on your Kindle or e-reader

Download the EPUB and read offline — perfect for the train. Works on Kindle, Kobo, Apple Books & more.

Send to Kindle →

00Getting Started3 capsules

Getting Started — 3 chapters.

01Why Foundations Matterconceptfree12 min 02The Map: AI, ML, and Deep Learningconceptfree12 min 03How a Model Learns: The Big Pictureintuition🔒11 min

01Linear Algebra for ML6 capsules

Linear Algebra for ML — 6 chapters.

04Matrix-Vector Multiplication as a Transformationmath🔒10 min 05The Dot Product as a Linear Transformationmath🔒10 min 06Linear Transformations in 3D and Dimensionality Changemath🔒11 min 07The Determinant: What It Measuresintuition🔒10 min 08Determinants Deeper: Invertibility and Collapsedeep-dive🔒10 min 09Eigenvalues and Eigenvectors, Intuitivelyintuition🔒11 min

02Probability & Statistics4 capsules

Probability & Statistics — 4 chapters.

10Conditional Probability and Bayes' Theoremmath🔒10 min 11Probability Distributions for MLconcept🔒11 min 12The Naive-Bayes Classifiercode🔒11 min 13Evaluating a Model: Accuracy, Precision, Recallconcept🔒11 min

03Calculus for Optimization3 capsules

Calculus for Optimization — 3 chapters.

14Differential Calculus: Derivatives and Gradientsmath🔒11 min 15The Chain Rule and Backpropagationdeep-dive🔒11 min 16Integral Calculus Foundations for MLmath🔒11 min

04Python & the ML Toolkit7 capsules

Python & the ML Toolkit — 7 chapters.

17Introduction to Python for MLcode🔒12 min 18Classes and Objects in Pythoncode🔒11 min 19NumPy: Arrays and Vectorized Computationcode🔒12 min 20Pandas for Data Wranglingcode🔒11 min 21Data Visualization for Machine Learningcode🔒10 min 22Scikit-learn: The ML Workhorsecode🔒11 min 23Deep Learning Libraries: TensorFlow and PyTorchcode🔒12 min

05Optimization & Neural Networks6 capsules

Optimization & Neural Networks — 6 chapters.

24A Neural Network from Scratchproject🔒9 min 25Gradient Descent and Backpropagationmath🔒12 min 26Stochastic Gradient Descentconcept🔒12 min 27Momentum-Based Gradient Descentconcept🔒11 min 28RMSprop and Adamdeep-dive🔒12 min 29Core ML Algorithms: A Tourconcept🔒13 min

06Putting It Together2 capsules

Putting It Together — 2 chapters.

30The Evolution and Future of AI/MLconcept🔒10 min 31Capstone: From Foundations to a First Modelproject🔒11 min

Ratings & reviews

724 readers

4.8

250 ratings

5 ★60%

4 ★25%

3 ★8%

2 ★4%

1 ★3%

Rate this book

Noah Kim

6 days ago

A few sections moved fast for me, but re-reading with the figures open made everything land. Highly recommend.

Rahul Verma

last month

This is the resource I wish I had when I started. Clear mental models, zero fluff.

Omar Haddad

4 months ago

Concise capsules I can finish over coffee, yet each one taught me something I actually use.