MB
Marcus Bell
2 weeks ago
Loved the from-first-principles approach. It rebuilt my intuition rather than just handing me formulas.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · beginner
Mathematical Foundations for Machine Learning
The linear algebra, probability, and calculus that make ML work.
See the math behind machine learning as geometry and code: matrices as transformations, determinants and eigenvectors, probability and distributions, and the calculus of gradient descent. Every idea is built by hand and drawn out, ending in a neural network trained from scratch.
42 capsules159 figures~8 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.
00Why Math for Machine Learning3 capsules
Why Math for Machine Learning — 3 chapters.
01The Math Under the Modelintuitionfree12 min02How to Read This Bookconceptfree12 min03Vectors as Arrows and as Listsconcept🔒11 min01Linear Algebra as Transformations7 capsules
Linear Algebra as Transformations — 7 chapters.
04Linear Combinations and Spanconcept🔒10 min05The Dot Product, Two Waysmath🔒10 min06The Dot Product as a Linear Transformationdeep-dive🔒10 min07A Matrix Is a Transformationintuition🔒12 min08Matrix Multiplication as Compositionconcept🔒11 min09The Identity and the Inversemath🔒11 min10Transformations in 3Dconcept🔒12 min02Determinants and the Shape of Space5 capsules
Determinants and the Shape of Space — 5 chapters.
11What the Determinant Measuresintuition🔒12 min12Computing 2x2 and 3x3 Determinantsmath🔒10 min13Zero Determinant and Collapsedeep-dive🔒11 min14Eigenvalues and Eigenvectorsconcept🔒14 min15Eigen-Intuition and Why It Matters for MLintuition🔒11 min03Probability and Statistics Foundations5 capsules
Probability and Statistics Foundations — 5 chapters.
16Reasoning Under Uncertaintyconcept🔒12 min17Conditional Probability and Bayes' Rulemath🔒11 min18Random Variables and Expectationconcept🔒12 min19Variance, Standard Deviation, and Spreadmath🔒11 min20Covariance and Correlationdeep-dive🔒13 min04Probability Distributions5 capsules
Probability Distributions — 5 chapters.
21Distributions as Shapes of Chanceconcept🔒12 min22Bernoulli and Binomial Distributionsmath🔒11 min23The Normal Distributiondeep-dive🔒10 min24Likelihood and Maximum Likelihoodconcept🔒12 min25From Likelihood to Loss Functionsintuition🔒12 min05Python and Numerical Computing6 capsules
Python and Numerical Computing — 6 chapters.
26Python for Math: A Fast Startcode🔒11 min27Objects, Classes, and Building Blockscode🔒12 min28NumPy Arrays and Vectorizationcode🔒12 min29Linear Algebra in NumPycode🔒12 min30Pandas for Datacode🔒10 min31Visualizing Data and Distributionscode🔒11 min06Calculus and the Engine of Learning7 capsules
Calculus and the Engine of Learning — 7 chapters.
32Derivatives as Rates of Changeconcept🔒11 min33Integrals and the Area Under a Curvemath🔒12 min34Partial Derivatives and the Gradientconcept🔒11 min35The Chain Rule and Backpropagationdeep-dive🔒11 min36Gradient Descentconcept🔒12 min37Momentum and RMSPropmath🔒11 min38The Adam Optimizerdeep-dive🔒13 min07Putting It Together4 capsules
Putting It Together — 4 chapters.
39Deep Learning Libraries in Pythoncode🔒11 min40A Neuron from Scratchcode🔒10 min41A Neural Network from Scratchproject🔒13 min42The Math You Now Ownintuition🔒11 minRatings & reviews
1,107 readersRate this book
NK
Noah Kim
4 months ago
Beautifully produced and genuinely deep. The reader experience makes it easy to keep going for hours.
TA
Tomás Alvarez
5 months ago
Concise capsules I can finish over coffee, yet each one taught me something I actually use.