Foundations of Data Science
Avrim Blum, John Hopcroft, Ravindran Kannan
- License
- Free author draft (later published by Cambridge University Press)
- Source
- Cornell University (author's page)
Description
The mathematical and algorithmic underpinnings of data science: high-dimensional geometry, singular value decomposition, random graphs, clustering, and machine-learning theory, aimed at readers who want to understand why the methods work.
Book information
- Language
- English
- Category
- Machine Learning
- Level
- Advanced
- Published
- 2018
- Format
- License
- Free author draft (later published by Cambridge University Press)
- Source
- Cornell University (author's page)
Topics
License
Official Free Distribution — Free author draft (later published by Cambridge University Press) (license text ↗)
This resource is listed with a link to its official source; TLP does not host the file.
An earlier draft is hosted free by the authors; the finished book is also sold by Cambridge University Press. TLP links to the free author draft only.
Related books
View all →
Mathematics for Machine Learning
Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
The mathematical foundations behind machine learning, taught for ML rather than in the abstract: linear algebra, analytic geometry, matrix decompositions, vector calculus, probability, and optimization, connected to real ML models.
Machine LearningAdvancedOfficial Free DistributionPDF · 17 MB
Python Data Science Handbook
Jake VanderPlas
A practical guide to the core Python data-science stack: IPython/Jupyter, NumPy, Pandas, Matplotlib, and Scikit-Learn, with real workflows for cleaning, transforming, visualizing, and modeling data.
Machine LearningIntermediateMITHTMLMachine Learning Crash Course
Google
Google's practical, example-driven introduction to machine learning: loss and gradient descent, classification, neural networks, embeddings, fairness, and production ML systems, with interactive exercises using TensorFlow.
Machine LearningBeginnerAPACHE 2.0HTML