Java deep learning projects : implement 10 real-world deep learning applications using Deeplearning4j and open source APIs / Md. Rezaul Karim.

Format:

Book

Author/Creator:

Karim, Rezaul, author.

Language:

English

Subjects (All):

Java (Computer program language).

Application program interfaces (Computer software).

Machine learning.

Application software--Development.

Application software.

Physical Description:

1 online resource (428 pages) : illustrations

Edition:

1st edition

Place of Publication:

Birmingham ; Mumbai : Packt, 2018.

System Details:

text file

Summary:

Build and deploy powerful neural network models using the latest Java deep learning libraries About This Book Understand DL with Java by implementing real-world projects Master implementations of various ANN models and build your own DL systems Develop applications using NLP, image classification, RL, and GPU processing Who This Book Is For If you are a data scientist, machine learning professional, or deep learning practitioner keen to expand your knowledge by delving into the practical aspects of deep learning with Java, then this book is what you need! Get ready to build advanced deep learning models to carry out complex numerical computations. Some basic understanding of machine learning concepts and a working knowledge of Java are required. What You Will Learn Master deep learning and neural network architectures Build real-life applications covering image classification, object detection, online trading, transfer learning, and multimedia analytics using DL4J and open-source APIs Train ML agents to learn from data using deep reinforcement learning Use factorization machines for advanced movie recommendations Train DL models on distributed GPUs for faster deep learning with Spark and DL4J Ease your learning experience through 69 FAQs In Detail Java is one of the most widely used programming languages. With the rise of deep learning, it has become a popular choice of tool among data scientists and machine learning experts. Java Deep Learning Projects starts with an overview of deep learning concepts and then delves into advanced projects. You will see how to build several projects using different deep neural network architectures such as multilayer perceptrons, Deep Belief Networks, CNN, LSTM, and Factorization Machines. You will get acquainted with popular deep and machine learning libraries for Java such as Deeplearning4j, Spark ML, and RankSys and you'll be able to use their features to build and deploy projects on distributed computing environments. You will then explore advanced domains such as transfer learning and deep reinforcement learning using the Java ecosystem, covering various real-world domains such as healthcare, NLP, image classification, and multimedia analytics with an easy-to-follow approach. Expert reviews and tips will follow every project to give you insights and hacks. By the end of this book, you will have stepped up your expertise when it comes to deep learning in Java, taking it beyond theory and be able to build ...

Contents:

Intro

Title Page

Copyright and Credits

Packt Upsell

Contributors

Table of Contents

Preface

Chapter 1: Getting Started with Deep Learning

A soft introduction to ML

Working principles of ML algorithms

Supervised learning

Unsupervised learning

Reinforcement learning

Putting ML tasks altogether

Delving into deep learning

How did DL take ML into next level?

Artificial Neural Networks

Biological neurons

A brief history of ANNs

How does an ANN learn?

ANNs and the backpropagation algorithm

Forward and backward passes

Weights and biases

Weight optimization

Activation functions

Neural network architectures

Deep neural networks

Multilayer Perceptron

Deep belief networks

Autoencoders

Convolutional neural networks

Recurrent neural networks

Emergent architectures

Residual neural networks

Generative adversarial networks

Capsule networks

DL frameworks and cloud platforms

Deep learning frameworks

Cloud-based platforms for DL

Deep learning from a disaster - Titanic survival prediction

Problem description

Configuring the programming environment

Feature engineering and input dataset preparation

Training MLP classifier

Evaluating the MLP classifier

Frequently asked questions (FAQs)

Summary

Answers to FAQs

Chapter 2: Cancer Types Prediction Using Recurrent Type Networks

Deep learning in cancer genomics

Cancer genomics dataset description

Preparing programming environment

Titanic survival revisited with DL4J

Multilayer perceptron network construction

Hidden layer 1

Hidden layer 2

Output layer

Network training

Evaluating the model

Cancer type prediction using an LSTM network

Dataset preparation for training

Recurrent and LSTM networks

Dataset preparation

LSTM network construction.

Network training

Answers to questions

Chapter 3: Multi-Label Image Classification Using Convolutional Neural Networks

Image classification and drawbacks of DNNs

CNN architecture

Convolutional operations

Pooling and padding operations

Fully connected layer (dense layer)

Multi-label image classification using CNNs

Description of the dataset

Removing invalid images

Workflow of the overall project

Image preprocessing

Extracting image metadata

Image feature extraction

Preparing the ND4J dataset

Training, evaluating, and saving the trained CNN models

Network construction

Scoring the model

Submission file generation

Wrapping everything up by executing the main() method

Chapter 4: Sentiment Analysis Using Word2Vec and LSTM Network

Sentiment analysis is a challenging task

Using Word2Vec for neural word embeddings

Datasets and pre-trained model description

Large Movie Review dataset for training and testing

Folder structure of the dataset

Description of the sentiment labeled dataset

Word2Vec pre-trained model

Sentiment analysis using Word2Vec and LSTM

Preparing the train and test set using the Word2Vec model

Network construction, training, and saving the model

Restoring the trained model and evaluating it on the test set

Making predictions on sample review texts

Chapter 5: Transfer Learning for Image Classification

Image classification with pretrained VGG16

DL4J and transfer learning

Developing an image classifier using transfer learning

Dataset collection and description

Architecture choice and adoption.

Train and test set preparation

Network training and evaluation

Restoring the trained model and inferencing

Making simple inferencing

Chapter 6: Real-Time Object Detection using YOLO, JavaCV, and DL4J

Object detection from images and videos

Object classification, localization, and detection

Convolutional Sliding Window (CSW)

Object detection from videos

You Only Look Once (YOLO)

Developing a real-time object detection project

Step 1 - Loading a pre-trained YOLO model

Step 2 - Generating frames from video clips

Step 3 - Feeding generated frames into Tiny YOLO model

Step 4 - Object detection from image frames

Step 5 - Non-max suppression in case of more than one bounding box

Step 6 - wrapping up everything and running the application

Chapter 7: Stock Price Prediction Using LSTM Network

State-of-the-art automated stock trading

Developing a stock price predictive model

Data collection and exploratory analysis

Preparing the training and test sets

LSTM network construction

Network training, and saving the trained model

Restoring the saved model for inferencing

Chapter 8: Distributed Deep Learning - Video Classification Using Convolutional LSTM Networks

Distributed deep learning across multiple GPUs

Distributed training on GPUs with DL4J

Video classification using convolutional - LSTM

UCF101 - action recognition dataset

Preprocessing and feature engineering

Solving the encoding problem

Data processing workflow

Simple UI for checking video frames

Preparing training and test sets

Network creation and training.

Performance evaluation

Distributed training on AWS deep learning AMI 9.0

Chapter 9: Playing GridWorld Game Using Deep Reinforcement Learning

Notation, policy, and utility for RL

Notations in reinforcement learning

Policy

Utility

Neural Q-learning

Introduction to QLearning

Neural networks as a Q-function

Developing a GridWorld game using a deep Q-network

Generating the grid

Calculating agent and goal positions

Calculating the action mask

Providing guidance action

Calculating the reward

Flattening input for the input layer

Network construction and training

Playing the GridWorld game

Chapter 10: Developing Movie Recommendation Systems Using Factorization Machines

Recommendation systems

Recommendation approaches

Collaborative filtering approaches

Content-based filtering approaches

Hybrid recommender systems

Model-based collaborative filtering

The utility matrix

The cold-start problem in collaborative-filtering approaches

Factorization machines in recommender systems

Developing a movie recommender system using FMs

Dataset description and exploratory analysis

Movie rating prediction

Converting the dataset into LibFM format

Training and test set preparation

Which one makes more sense

- ranking or rating?

Chapter 11: Discussion, Current Trends, and Outlook

Discussion and outlook

Discussion on the completed projects

Titanic survival prediction using MLP and LSTM networks

Cancer type prediction using recurrent type networks

Image classification using convolutional neural networks.

Sentiment analysis using Word2Vec and the LSTM network

Image classification using transfer learning

Real-time object detection using YOLO, JavaCV, and DL4J

Stock price prediction using LSTM network

Distributed deep learning - video classification using a convolutional-LSTM network

Using deep reinforcement learning for GridWorld

Movie recommender system using factorization machines

Current trends and outlook

Current trends

Outlook on emergent DL architectures

GANs

Capsule networks (CapsNet)

Semantic image segmentation

Deep learning for clustering analysis

Other Books You May Enjoy

Index.

Notes:

Description based on print version record.

ISBN:

9781788996525

1788996526

OCLC:

1044949296