Neural Networks and Deep Learning
- License
- Creative Commons Attribution-NonCommercial 3.0 Unported
- Source
- neuralnetworksanddeeplearning.com (official)
Description
A hands-on introduction to neural networks, built around teaching a network to recognize handwritten digits. Derives backpropagation from first principles, then covers why deep networks are hard to train and the ideas that make deep learning work.
Book information
- Language
- English
- Category
- Deep Learning
- Level
- Intermediate
- Published
- 2015
- Format
- HTML
- License
- Creative Commons Attribution-NonCommercial 3.0 Unported
- Source
- neuralnetworksanddeeplearning.com (official)
Topics
License
Creative Commons — Creative Commons Attribution-NonCommercial 3.0 Unported (license text ↗)
This resource is listed because its license permits redistribution.
Stated on the book's official site.
Related books
View all →
Deep Learning
Ian Goodfellow, Yoshua Bengio, Aaron Courville
The widely cited reference on deep learning: the mathematical background, deep feedforward networks, regularization and optimization, convolutional and recurrent networks, and research topics including generative models.
Deep LearningAdvancedMITHTML
Dive into Deep Learning
Aston Zhang, Zachary C. Lipton, Mu Li, Alexander J. Smola
An interactive deep learning textbook combining explanations, mathematics, and runnable code (PyTorch, NumPy, JAX, and TensorFlow). Covers linear and softmax regression, MLPs, CNNs, RNNs, attention and transformers, and more. Adopted at 500+ universities.
Deep LearningAdvancedCreative CommonsPDF · 43 MBMachine 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