Deep learning by example : a hands-on guide to implementing advanced machine learning algorithms and neural networks / Ahmed Menshawy.

Format:

Book

Author/Creator:

Menshawy, Ahmed, author.

Language:

English

Subjects (All):

Machine learning.

Physical Description:

1 online resource (427 pages) : illustrations

Edition:

1st ed.

Place of Publication:

Birmingham, [England] ; Mumbai, [India] : Packt, 2018.

Summary:

Deep Learning is a subset of Machine Learning and has gained a lot of popularity recently. This book introduces you to the fundamentals of deep learning in a hands-on manner. You will use Tensorflow to train different types of neural networks for tasks related to computer vision, language processing, and other real-world problems.

Contents:

Cover

Copyright and Credits

Packt Upsell

Contributors

Table of Contents

Preface

Chapter 1: Data Science - A Birds' Eye View

Understanding data science by an example

Design procedure of data science algorithms

Data pre-processing

Data cleaning

Feature selection

Model selection

Learning process

Evaluating your model

Getting to learn

Challenges of learning

Feature extraction - feature engineering

Noise

Overfitting

Selection of a machine learning algorithm

Prior knowledge

Missing values

Implementing the fish recognition/detection model

Knowledge base/dataset

Data analysis pre-processing

Model building

Model training and testing

Fish recognition - all together

Different learning types

Supervised learning

Unsupervised learning

Semi-supervised learning

Reinforcement learning

Data size and industry needs

Summary

Chapter 2: Data Modeling in Action - The Titanic Example

Linear models for regression

Motivation

Advertising - a financial example

Dependencies

Importing data with pandas

Understanding the advertising data

Data analysis and visualization

Simple regression model

Learning model coefficients

Interpreting model coefficients

Using the model for prediction

Linear models for classification

Classification and logistic regression

Titanic example - model building and training

Data handling and visualization

Data analysis - supervised machine learning

Different types of errors

Apparent (training set) error

Generalization/true error

Chapter 3: Feature Engineering and Model Complexity - The Titanic Example Revisited

Feature engineering

Types of feature engineering

Dimensionality reduction

Feature construction.

Titanic example revisited

Removing any sample with missing values in it

Missing value inputting

Assigning an average value

Using a regression or another simple model to predict the values of missing variables

Feature transformations

Dummy features

Factorizing

Scaling

Binning

Derived features

Name

Cabin

Ticket

Interaction features

The curse of dimensionality

Avoiding the curse of dimensionality

Titanic example revisited - all together

Bias-variance decomposition

Learning visibility

Breaking the rule of thumb

Chapter 4: Get Up and Running with TensorFlow

TensorFlow installation

TensorFlow GPU installation for Ubuntu 16.04

Installing NVIDIA drivers and CUDA 8

Installing TensorFlow

TensorFlow CPU installation for Ubuntu 16.04

TensorFlow CPU installation for macOS X

TensorFlow GPU/CPU installation for Windows

The TensorFlow environment

Computational graphs

TensorFlow data types, variables, and placeholders

Variables

Placeholders

Mathematical operations

Getting output from TensorFlow

TensorBoard - visualizing learning

Chapter 5: TensorFlow in Action - Some Basic Examples

Capacity of a single neuron

Biological motivation and connections

Activation functions

Sigmoid

Tanh

ReLU

Feed-forward neural network

The need for multilayer networks

Training our MLP - the backpropagation algorithm

Step 1 - forward propagation

Step 2 - backpropagation and weight updation

TensorFlow terminologies - recap

Defining multidimensional arrays using TensorFlow

Why tensors?

Operations

Linear regression model - building and training

Linear regression with TensorFlow

Logistic regression model - building and training.

Utilizing logistic regression in TensorFlow

Why use placeholders?

Set model weights and bias

Logistic regression model

Training

Cost function

Chapter 6: Deep Feed-forward Neural Networks - Implementing Digit Classification

Hidden units and architecture design

MNIST dataset analysis

The MNIST data

Digit classification - model building and training

Data analysis

Building the model

Model training

Chapter 7: Introduction to Convolutional Neural Networks

The convolution operation

Applications of CNNs

Different layers of CNNs

Input layer

Convolution step

Introducing non-linearity

The pooling step

Fully connected layer

Logits layer

CNN basic example - MNIST digit classification

Performance measures

Chapter 8: Object Detection - CIFAR-10 Example

Object detection

CIFAR-10 - modeling, building, and training

Used packages

Loading the CIFAR-10 dataset

Data analysis and preprocessing

Building the network

Testing the model

Chapter 9: Object Detection - Transfer Learning with CNNs

Transfer learning

The intuition behind TL

Differences between traditional machine learning and TL

CIFAR-10 object detection - revisited

Solution outline

Loading and exploring CIFAR-10

Inception model transfer values

Analysis of transfer values

Model building and training

Chapter 10: Recurrent-Type Neural Networks - Language Modeling

The intuition behind RNNs

Recurrent neural networks architectures

Examples of RNNs

Character-level language models

Language model using Shakespeare data

The vanishing gradient problem

The problem of long-term dependencies

LSTM networks

Why does LSTM work?.

Implementation of the language model

Mini-batch generation for training

Stacked LSTMs

Model architecture

Inputs

Building an LSTM cell

RNN output

Training loss

Optimizer

Model hyperparameters

Training the model

Saving checkpoints

Generating text

Chapter 11: Representation Learning - Implementing Word Embeddings

Introduction to representation learning

Word2Vec

Building Word2Vec model

A practical example of the skip-gram architecture

Skip-gram Word2Vec implementation

Data analysis and pre-processing

Chapter 12: Neural Sentiment Analysis

General sentiment analysis architecture

RNNs - sentiment analysis context

Exploding and vanishing gradients - recap

Sentiment analysis - model implementation

Keras

Model training and results analysis

Chapter 13: Autoencoders - Feature Extraction and Denoising

Introduction to autoencoders

Examples of autoencoders

Autoencoder architectures

Compressing the MNIST dataset

The MNIST dataset

Convolutional autoencoder

Dataset

Denoising autoencoders

Applications of autoencoders

Image colorization

More applications

Chapter 14: Generative Adversarial Networks

An intuitive introduction

Simple implementation of GANs

Model inputs

Variable scope

Leaky ReLU

Generator

Discriminator

Building the GAN network

Defining the generator and discriminator

Discriminator and generator losses

Optimizers

Generator samples from training.

Sampling from the generator

Chapter 15: Face Generation and Handling Missing Labels

Face generation

Getting the data

Exploring the Data

Model losses

Model optimizer

Semi-supervised learning with Generative Adversarial Networks (GANs)

Intuition

Appendix: Implementing Fish Recognition

Code for fish recognition

Other Books You May Enjoy

Index.

Notes:

Includes index.

Description based on online resource; title from PDF title page (EBC, viewed March 22, 2018).

ISBN:

9781788395762

178839576X