Deep Learning for Programmers

Interactive Programming for Artificial Intelligence series; Deep Learning for Programmers: An Interactive Tutorial with CUDA, OpenCL, MKL-DNN, Java, and Clojure

aren’t these surfers adorable? the book too!

subscribe now

or scroll down to read the pitch, and subscribe later :)

Open Source Libraries

Why

basically…

the only DL book for programmers

interactive & dynamic

step-by-step implementation

incredible speed

yet, No C++ hell (!)

Nvidia GPU (CUDA and cuDNN)

AMD GPU (yes, OpenCL too!)

Intel & AMD CPU (MKL-DNN)

Clojure (magic!)

Java Virtual Machine (without Java boilerplate!)

complete source code

beautiful typesetting (see sample chapters below)

No Middleman

no middleman!

100% of the revenue goes towards my open-source work!

For Programmers

the only AI book that walks the walk

complete, 100% executable, code inside

step-by-step instructions

full path from theory to implementation in actual code

superfast implementation

Other books are either math-only monographs for academics, or written for non-technical end users.

Deep Learning

learn DL by implementing it from scratch

classic neural networks using fast linear algebra

optimized backpropagation algorithm step-by-step

explore it on the CPU

put it on the GPU!

design elegant neural networks API

build tensor support

integrate it with Intel’s MKL-DNN performance libray

integrate it with Nvidia’s cuDNN performance library

learn nuts and bolts

build convolutional layers

build RNN support

understand how to use it

…and much more!

Interactive

immediate dynamic feedback

see the result of executing each line

experiment in a live environment

no C++ build hell

no C++!

Java Virtual Machine, but without Java boilerplate

Clojure, the nicest language on earth :-)

no C++!!!

Fast

optimized

yet, high-level (you don’t touch C++)

GPU

learn CUDA & cuDNN

learn OpenCL

all hardware: Nvidia, AMD, Intel

CPU

learn Intel MKL-DNN

you don’t touch C++!!!

Download

download sample chapters (DRAFTS)

Representing Layers and Connections

Bias and Activation Function

GPU Computing with CUDA and OpenCL

many free articles at dragan.rocks

or subscribe now and get the latest version of the book and the the source code.

buy

subscribe now for early access

read drafts now

get new chapters as soon as they are written

all revenue goes towards funding my work on open-source libraries used in the book

subscription perks

name in the acknowledgments

special copies with a personalized thank you note

personalized handcrafted hardcovers for chapter sponsors

get the book and help make it awesome!

Contents

Table of Contents

Part 1: Getting Started

4-6 chapters, (TO BE DETERMINED)

Part 2: Inference (AVAILABLE)

Representing layers and connections (AVAILABLE)

Bias and activation function (AVAILABLE)

Fully connected inference layers (AVAILABLE)

Increasing performance with batch processing (AVAILABLE)

Sharing memory (AVAILABLE)

GPU computing with CUDA and OpenCL (AVAILABLE)

Part 3: Learning (AVAILABLE)

Gradient descent and backpropagation (AVAILABLE)

The forward pass (AVAILABLE)

The activation and its derivative (AVAILABLE)

The backward pass (AVAILABLE)

Part 4: A simple neural networks API (SOON)

Inference API (SOON)

Training API (SOON)

Initializing weights (SOON)

Learning a regression (SOON)

Part 5: Training optimizations (SOON)

Weight decay (SOON)

Momentum (SOON)

Nesterov momentum (SOON)

Adaptive learning rates (SOON)

Dropout (SOON)

Batch normalization (SOON)

Learning a regression (SOON)

Learning a classification (SOON)

Part 6: Tensors (TO BE DETERMINED)

Tensors, Matrices, and ND-arrays (TBD)

Tensors on the CPU with MKL-DNN (TBD)

Tensors on the GPU with cuDNN (TBD)

Tensor API (TBD)

Part 7: Convolutional layers (TBD)

4-6 Chapters, (TBD)

Part 8: Recurrent networks (TBD)

4-6 Chapters, (TBD)

Part 9: A real world architecture (TBD)

4-6 Chapters, (TBD)

Part 10: Deep learning in practice (TBD)

4-6 Chapters, (TBD)

Subscribe

subscribe now for early access

read drafts now

get new chapters as soon as they are written

all revenue goes towards funding my work on open-source libraries used in the book

subscription perks

name in the acknowledgments

special copies with a personalized thank you note

personalized handcrafted hardcovers for chapter sponsors

get in early and help make this book awesome!

Blog
More Books

Numerical Linear Algebra for Programmers

click here to read why, and download

Interactive Programming for Artificial Intelligence series; Numerical Linear Algebra for Programmers: An Interactive Tutorial with GPU, CUDA, OpenCL, MKL, Java, and Clojure