Master your path
To become an expert in machine learning, you first need a strong foundation in four learning areas: coding, math, ML theory, and how to build your own ML project from start to finish.
Begin with TensorFlow’s curated curriculums to improve these four skills, or choose your own learning path by exploring our resource library below.
The four areas of machine learning education
When beginning your educational path, it’s important to first understand how to learn ML. We’ve broken the learning process into four areas of knowledge, with each area providing a foundational piece of the ML puzzle. To help you on your path, we’ve identified books, videos, and online courses that will uplevel your abilities, and prepare you to use ML for your projects. Start with our guided curriculums designed to increase your knowledge, or choose your own path by exploring our resource library.
TensorFlow curriculums
Start learning with one of our guided curriculums containing recommended courses, books, and videos.
Learn the basics of ML with this collection of books and online courses. You will be introduced to ML with scikit-learn, guided through deep learning using TensorFlow 2.0, and then you will have the opportunity to practice what you learn with beginner tutorials.
Once you understand the basics of machine learning, take your abilities to the next level by diving into theoretical understanding of neural networks, deep learning, and improving your knowledge of the underlying math concepts.
Learn the basics of developing machine learning models in JavaScript, and how to deploy directly in the browser. You will get a high-level introduction on deep learning and on how to get started with TensorFlow.js through hands-on exercises.
Educational resources
Choose your own learning path, and explore books, courses, videos, and exercises recommended by the TensorFlow team to teach you the foundations of ML.
Books
Reading is one of the best ways to understand the foundations of ML and deep learning. Books can give you the theoretical understanding necessary to help you learn new concepts more quickly in the future.
This book is a practical, hands-on introduction to Deep Learning with Keras.
Using concrete examples, minimal theory, and two production-ready Python frameworks—Scikit-Learn and TensorFlow—this book helps you gain an intuitive understanding of the concepts and tools for building intelligent systems.
This Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general, and deep learning in particular.
This book provides a theoretical background on neural networks. It does not use TensorFlow, but is a great reference for students interested in learning more.
Written by the main authors of the TensorFlow library, this book provides fascinating use cases and in-depth instruction for deep learning apps in JavaScript in your browser or on Node.
Multi-part online courses
Taking a multi-part online course is a good way to learn the basic concepts of ML. Many courses provide great visual explainers, and the tools needed to start applying machine learning directly at work, or with your personal projects.
You've learned how to build and train models. Now learn to navigate various deployment scenarios and use data more effectively to train your model in this four-course Specialization.
Developed in collaboration with the TensorFlow team, this course is part of the TensorFlow in Practice Specialization and will teach you best practices for using TensorFlow.
In this online course developed by the TensorFlow team and Udacity, you'll learn how to build deep learning applications with TensorFlow.
In this four-course Specialization taught by a TensorFlow developer, you'll explore the tools and software developers use to build scalable AI-powered algorithms in TensorFlow.
In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects and build a career in AI. You will master not only the theory, but also see how it is applied in industry.
This course is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for computer vision tasks, particularly image classification. Explore lecture videos, slides, and past syllabus notes from previous iterations of the course.
In this course from MIT, you will gain foundational knowledge of deep learning algorithms and get practical experience in building neural networks in TensorFlow.
Other resources
For mobile and web developers and users wanting to build production pipelines, we’ve gathered our favorite resources to help you get started including our TensorFlow libraries and frameworks specific to your needs.
Using deeplearn.js, find out how deep learning systems learn and examine how they think.
A 3-part series that explores both training and executing machine learned models with TensorFlow.js, and shows you how to create a machine learning model in JavaScript that executes directly in the browser.
Part of a larger series on machine learning and building neural networks, this video playlist focuses on TensorFlow.js, the core API, and how to use the JavaScript library to train and deploy ML models.
This series introduces the concept of client-side artificial neural networks. Learn about client-server deep learning architectures, converting Keras models to TFJS models, serving models with Node.js, training and transfer learning in the browser and more.
A five part series from the TensorFlow team on using TensorFlow Extended (TFX) to create your own production ML pipelines.
This session from Google I/O will demystify the various options available for using machine learning to enhance mobile apps and edge devices. Learn how TensorFlow Lite can be used to train models and how to use them across a variety of devices.
Math concepts
To go deeper with your ML knowledge, these resources can help you understand the underlying math concepts necessary for higher level advancement.
The Machine Learning Crash Course with TensorFlow APIs is a self-study guide for aspiring machine learning practitioners. It features a series of lessons with video lectures, real-world case studies, and hands-on practice exercises.
This online specialization from Coursera aims to bridge the gap of mathematics and machine learning, getting you up to speed in the underlying mathematics to build an intuitive understanding, and relating it to Machine Learning and Data Science.
3blue1brown centers around presenting math with a visuals-first approach. In this video series, you will learn the basics of a neural network and how it works through math concepts.
A series of short, visual videos from 3blue1brown that explain the geometric understanding of matrices, determinants, eigen-stuffs and more.
A series of short, visual videos from 3blue1brown that explain the fundamentals of calculus in a way that give you a strong understanding of the fundamental theorems, and not just how the equations work.
This introductory course from MIT covers matrix theory and linear algebra. Emphasis is given to topics that will be useful in other disciplines, including systems of equations, vector spaces, determinants, eigenvalues, similarity, and positive definite matrices.
This introductory calculus course from MIT covers differentiation and integration of functions of one variable, with applications.
This book provides an accessible overview of the field of statistical learning, an essential toolset for making sense of the vast and complex world of datasets needed to train models in machine learning.
Human-centered AI
When designing an ML model, or building AI-driven applications, it’s important to consider the people interacting with the product, and the best way to build fairness, interpretability, privacy, and security into these AI systems.
This guidebook from Google will help you build human-centered AI products. It’ll enable you to avoid common mistakes, design excellent experiences, and focus on people as you build AI-driven applications.
Learn about Google AI's recommended practices for building fairness, interpretability, privacy, and security into AI systems.
This one-hour module within Google's MLCC introduces learners to different types of human biases that can manifest in training data, as well as strategies for identifying, and evaluating their effects.