NK
Noah Kim
last week
Best explanation of this topic I have found anywhere. The sidenotes fill in exactly the gaps I had.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · beginner
Machine Learning Fundamentals
The core of ML, built from scratch.
A hands-on tour of classical machine learning, from perceptrons and logistic regression to linear regression and your first neural network. Every model is built by hand in Python with the math, the intuition, and the code, so nothing stays a black box.
37 capsules143 figures~7 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.
00Foundations of Machine Learning6 capsules
Foundations of Machine Learning — 6 chapters.
01What Is Machine Learning?conceptfree11 min02Types of ML Models: Supervised, Unsupervised, and Beyondconceptfree11 min03The Six Steps of Any ML Projectconcept🔒11 min04Setting Up Python and Running Your First Codecode🔒11 min05Jupyter Notebooks, NumPy, and Scikit-learncode🔒12 min06How a Model Learns from Dataintuition🔒13 min01Linear Classifiers and the Perceptron7 capsules
Linear Classifiers and the Perceptron — 7 chapters.
07Linear Classifiers, Part 1: Drawing a Decision Boundaryconcept🔒12 min08Linear Classifiers, Part 2: Weights, Bias, and Geometrymath🔒11 min09The Random Linear Classification Algorithmintuition🔒11 min10The Perceptron Explainedconcept🔒11 min11Coding the Perceptron from Scratchcode🔒12 min12The Perceptron Convergence Theoremmath🔒12 min13When a Line Is Not Enough: The XOR Problemdeep-dive🔒13 min02Features and Representation3 capsules
Features and Representation — 3 chapters.
14The Magic of Featuresintuition🔒11 min15Feature Representation: Turning the World into Numbersconcept🔒11 min16One-Hot Encoding for Categorical Datacode🔒12 min03Logistic Regression and Optimization8 capsules
Logistic Regression and Optimization — 8 chapters.
17From Scores to Probabilities: The Sigmoidmath🔒11 min18Logistic Regression from the Ground Upconcept🔒12 min19Cross-Entropy Loss: Measuring Wrongnessmath🔒11 min20The Gradient Descent Algorithmconcept🔒14 min21Gradient Descent in Code: 1D and 2Dcode🔒12 min22Training Logistic Regression from Scratchproject🔒12 min23Introduction to Regularizationconcept🔒12 min24Implementing Regularization for Logistic Regressioncode🔒12 min04Linear Regression6 capsules
Linear Regression — 6 chapters.
25Linear Regression: Fitting a Line to Dataconcept🔒10 min26Ordinary Least Squares: The Closed-Form Solutionmath🔒14 min27Ridge Regression: Regularizing the Fitmath🔒12 min28When Least Squares Breaks: Non-Invertible Matricesdeep-dive🔒13 min29Stochastic Gradient Descentconcept🔒11 min30Regression Recap for Interviewsconcept🔒11 min05Neural Networks7 capsules
Neural Networks — 7 chapters.
31Neural Network Architecture: Neurons and Layersconcept🔒12 min32Activation Functions: Where Nonlinearity Comes Frommath🔒12 min33Backpropagation, Intuitivelyintuition🔒11 min34Backpropagation: The Math Worked Throughmath🔒12 min35Momentum in Gradient Descentconcept🔒12 min36Hands-On: Training a Neural Network in Pythonproject🔒13 min37Putting It All Together: From Perceptron to Deep Learningdeep-dive🔒10 minRatings & reviews
1,651 readersRate this book
RV
Rahul Verma
3 months ago
Dense but never confusing. Every chapter builds cleanly on the last — you can feel the care in the structure.
OH
Omar Haddad
4 months ago
A few sections moved fast for me, but re-reading with the figures open made everything land. Highly recommend.
TA
Tomás Alvarez
8 months ago
This is the resource I wish I had when I started. Clear mental models, zero fluff.
JB
Jonas Bergström
9 months ago
Concise capsules I can finish over coffee, yet each one taught me something I actually use.