Book Image

Deep Learning with TensorFlow

By : Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy
Book Image

Deep Learning with TensorFlow

By: Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy

Overview of this book

Deep learning is the step that comes after machine learning, and has more advanced implementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x. Throughout the book, you’ll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, including search, image recognition, and language processing. Additionally, you’ll learn how to analyze and improve the performance of deep learning models. This can be done by comparing algorithms against benchmarks, along with machine intelligence, to learn from the information and determine ideal behaviors within a specific context. After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects.

Related Content you might be interested in

Current Title:

Small book image
Deep Learning with TensorFlow
Giancarlo Zaccone | Md. Rezaul Karim | Ahmed Menshawy
Apr, 2017 | 320 pages
Small book image
Predictive Analytics with TensorFlow
Md Rezaul Karim
Nov, 2017 | 522 pages
Small book image
TensorFlow: Powerful Predictive Analytics with TensorFlow
Md Rezaul Karim
Mar, 2018 | 164 pages
Small book image
TensorFlow 1.x Deep Learning Cookbook
Amita Kapoor | Antonio Gulli
Dec, 2017 | 536 pages
Table of Contents (11 chapters)
Preface
Preface
What this book covers
What you need for this book
Who this book is for
Conventions
Reader feedback
Customer support
Free Chapter
1
Getting Started with Deep Learning
Getting Started with Deep Learning
Introducing machine learning
What is deep learning?
Neural networks
How does an artificial neural network learn?
Neural network architectures
Autoencoders
Recurrent Neural Networks
Deep learning framework comparisons
Summary
2
First Look at TensorFlow
First Look at TensorFlow
General overview
Installing TensorFlow on Linux
Requirements for running TensorFlow with GPU from NVIDIA
How to install TensorFlow
Installing TensorFlow on Windows
Computational graphs
Why a computational graph?
The programming model
Data model
TensorBoard
Implementing a single input neuron
Source code for the single input neuron
Migrating to TensorFlow 1.x
Summary
3
Using TensorFlow on a Feed-Forward Neural Network
Using TensorFlow on a Feed-Forward Neural Network
Introducing feed-forward neural networks
Classification of handwritten digits
Exploring the MNIST dataset
Softmax classifier
How to save and restore a TensorFlow model
Implementing a five-layer neural network
ReLU classifier
Visualization
Dropout optimization
Visualization
Summary
4
TensorFlow on a Convolutional Neural Network
TensorFlow on a Convolutional Neural Network
Introducing CNNs
CNN architecture
Building your first CNN
Emotion recognition with CNNs
Summary
5
Optimizing TensorFlow Autoencoders
Optimizing TensorFlow Autoencoders
Introducing autoencoders
Implementing an autoencoder
Improving autoencoder robustness
Building a denoising autoencoder
Convolutional autoencoders
Summary
6
Recurrent Neural Networks
Recurrent Neural Networks
RNNs basic concepts
RNNs at work
Unfolding an RNN
The vanishing gradient problem
LSTM networks
An image classifier with RNNs
Bidirectional RNNs
Text prediction
Summary
7
GPU Computing
GPU Computing
GPGPU computing
GPGPU history
The CUDA architecture
GPU programming model
TensorFlow GPU set up
TensorFlow GPU management
GPU memory management
Assigning a single GPU on a multi-GPU system
Using multiple GPUs
Summary
8
Advanced TensorFlow Programming
Advanced TensorFlow Programming
Introducing Keras
Building deep learning models
Sentiment classification of movie reviews
Adding a convolutional layer
Pretty Tensor
Digit classifier
TFLearn
Titanic survival predictor
Summary
9
Advanced Multimedia Programming with TensorFlow
Advanced Multimedia Programming with TensorFlow
Introduction to multimedia analysis
Deep learning for Scalable Object Detection
Accelerated Linear Algebra
TensorFlow and Keras
Deep learning on Android
Summary
10
Reinforcement Learning
Reinforcement Learning
Basic concepts of Reinforcement Learning
Q-learning algorithm
Introducing the OpenAI Gym framework
FrozenLake-v0 implementation problem
Q-learning with TensorFlow
Source code for the Q-learning neural network
Summary

Introducing Keras

Keras is a minimalist, high-level neural networks library, capable of running on top of TensorFlow. It was developed with a focus on enabling easy and fast prototyping and experimentation. Keras runs on Python 2.7 or 3.5, and can seamlessly execute on GPUs and CPUs given the underlying frameworks. It is released under the MIT license.

Keras was developed and maintained by François Chollet, a Google engineer, following these design principles:

  • Modularity: A model is understood as a sequence or a graph of the standalone, fully configurable modules that can be plugged together with as few restrictions as possible. Neural layers, cost functions, optimizers, initialization schemes, and activation functions are all standalone modules that can be combined to create new models.
  • Minimalism: Each module must be short (few lines of code) and simple. The source code should be transparent upon the dirt...
Previous Section
End of Section 2
Next Section