FZ
Fatima Zahra
last week
This is the resource I wish I had when I started. Clear mental models, zero fluff.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · intermediate
Machine Learning & Deep Learning Mastery
ML and deep learning, built by hand from scratch.
A ground-up tour of machine learning and deep learning, from ordinary-least-squares regression to a neural network you code and backpropagate yourself. Every algorithm is derived on paper, implemented in Python, and illustrated with hand-drawn figures.
44 capsules164 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.
00Foundations of Machine Learning4 capsules
Foundations of Machine Learning — 4 chapters.
01What Is Machine Learning?conceptfree9 min02AI vs ML vs Deep Learningintuitionfree11 min03Types of Machine Learningconcept🔒13 min04Supervised vs Unsupervised, Explained Simplyintuition🔒11 min01Regression5 capsules
Regression — 5 chapters.
05Regression Theory and the Line of Best Fitconcept🔒13 min06The OLS Formula, Derivedmath🔒12 min07Ridge Regression Theorymath🔒14 min08Regression in Codecode🔒11 min09Ridge Regression: A Hands-On Democode🔒11 min02Overfitting, Features & Generalization4 capsules
Overfitting, Features & Generalization — 4 chapters.
10The Overfitting Problemconcept🔒11 min11K-Fold Cross-Validationconcept🔒12 min12Feature Engineering Basicsconcept🔒10 min13A Regression Case Studyproject🔒11 min03Linear Classifiers & the Perceptron6 capsules
Linear Classifiers & the Perceptron — 6 chapters.
14Introduction to Linear Classifiersconcept🔒12 min15The Perceptron: Theory and Codecode🔒11 min16Linear Separability and Marginmath🔒10 min17The Perceptron Convergence Theoremdeep-dive🔒10 min18Feature Encoding Theoryconcept🔒12 min19The Perceptron in Codecode🔒10 min04Logistic Regression4 capsules
Logistic Regression — 4 chapters.
20Logistic Regression Fundamentalsconcept🔒11 min21The Sigmoid and Cross-Entropy Lossmath🔒12 min22Logistic Regression, End to Endcode🔒13 min23Logistic Regression in Codecode🔒13 min05Neural Networks: The Forward Pass5 capsules
Neural Networks: The Forward Pass — 5 chapters.
24Neurons, Layers, and Batchesconcept🔒12 min25Activation Functionsconcept🔒12 min26Building Layers with Python Classescode🔒10 min27Loss Functions and the Full Forward Passmath🔒11 min28The Forward Pass in Codecode🔒12 min06Neural Networks: Backpropagation5 capsules
Neural Networks: Backpropagation — 5 chapters.
29The Backward Pass Through a Single Neuronmath🔒11 min30The Backward Pass Through a Layermath🔒12 min31Backpropagation: The Complete Theorydeep-dive🔒13 min32Backpropagation Recap and Codecode🔒13 min33The Entire Backward Pass in Codeproject🔒12 min07Optimizers & Training5 capsules
Optimizers & Training — 5 chapters.
34Gradient Descent and Momentummath🔒11 min35AdaGrad, RMSProp, and Adammath🔒12 min36Optimizers in Codecode🔒12 min37Regularization and Dropout in Neural Netsconcept🔒10 min38Project: Build Your Own Neural Networkproject🔒10 min08CNNs & Decision Trees6 capsules
CNNs & Decision Trees — 6 chapters.
39CNN Fundamentalsconcept🔒12 min40Build Your Own CNN Applicationproject🔒11 min41Introduction to Decision Treesconcept🔒10 min42Gini Impurity: Choosing the Best Splitmath🔒10 min43Splitting on Numerical Datamath🔒10 min44Project: Code a Decision Tree from Scratchproject🔒12 minRatings & reviews
1,157 readersRate this book
SR
Sofia Reyes
2 months ago
Beautifully produced and genuinely deep. The reader experience makes it easy to keep going for hours.
HW
Hannah Weiss
4 months ago
Loved the from-first-principles approach. It rebuilt my intuition rather than just handing me formulas.
EP
Elena Petrova
8 months ago
Concise capsules I can finish over coffee, yet each one taught me something I actually use.
ML
Mei Lin
11 months ago
Dense but never confusing. Every chapter builds cleanly on the last — you can feel the care in the structure.