True PDF (not conversion).
Build and deploy powerful neural network models using the latest Java deep learning libraries
Key Features
* 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
---
Book Description
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 your own advanced deep learning systems.
---
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
---
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.
True PDF (not conversion).
Author(s): Rezaul Karim
Series: true pdf file.
Edition: True pdf.
Publisher: Packt
Year: 2018
Language: English
Pages: 436
Title Page......Page 2
Copyright and Credits......Page 3
Packt Upsell......Page 4
Contributors......Page 5
Table of Contents......Page 7
Preface......Page 13
Chapter 1: Getting Started with Deep Learning......Page 20
Working principles of ML algorithms......Page 21
Supervised learning......Page 23
Unsupervised learning......Page 25
Reinforcement learning......Page 26
Putting ML tasks altogether......Page 27
How did DL take ML into next level?......Page 28
Biological neurons......Page 31
A brief history of ANNs......Page 32
How does an ANN learn?......Page 33
Forward and backward passes......Page 34
Weights and biases......Page 35
Weight optimization......Page 37
Activation functions......Page 38
Deep neural networks......Page 40
Deep belief networks......Page 41
Autoencoders......Page 43
Convolutional neural networks......Page 44
Recurrent neural networks ......Page 45
Residual neural networks......Page 46
Capsule networks......Page 47
Deep learning frameworks......Page 48
Cloud-based platforms for DL......Page 50
Problem description......Page 51
Configuring the programming environment......Page 53
Feature engineering and input dataset preparation......Page 54
Training MLP classifier ......Page 63
Evaluating the MLP classifier......Page 64
Summary......Page 68
Answers to FAQs......Page 69
Chapter 2: Cancer Types Prediction Using Recurrent Type Networks......Page 75
Deep learning in cancer genomics......Page 76
Cancer genomics dataset description......Page 78
Preparing programming environment......Page 84
Titanic survival revisited with DL4J......Page 87
Multilayer perceptron network construction......Page 90
Output layer......Page 92
Network training......Page 93
Evaluating the model......Page 95
Dataset preparation for training......Page 98
Recurrent and LSTM networks......Page 102
LSTM network construction......Page 107
Network training......Page 110
Evaluating the model......Page 111
Summary......Page 112
Answers to questions......Page 113
Chapter 3: Multi-Label Image Classification Using Convolutional Neural Networks......Page 121
Image classification and drawbacks of DNNs......Page 122
CNN architecture......Page 123
Convolutional operations......Page 125
Pooling and padding operations......Page 126
Problem description......Page 129
Description of the dataset......Page 130
Removing invalid images......Page 131
Workflow of the overall project......Page 132
Image preprocessing......Page 134
Extracting image metadata......Page 141
Image feature extraction......Page 142
Preparing the ND4J dataset......Page 149
Training, evaluating, and saving the trained CNN models......Page 150
Network construction......Page 151
Scoring the model......Page 156
Submission file generation......Page 157
Wrapping everything up by executing the main() method......Page 159
Summary......Page 161
Answers to questions......Page 162
Chapter 4: Sentiment Analysis Using Word2Vec and LSTM Network......Page 167
Sentiment analysis is a challenging task......Page 168
Using Word2Vec for neural word embeddings......Page 170
Folder structure of the dataset......Page 172
Word2Vec pre-trained model......Page 174
Sentiment analysis using Word2Vec and LSTM......Page 175
Preparing the train and test set using the Word2Vec model......Page 176
Network construction, training, and saving the model......Page 184
Restoring the trained model and evaluating it on the test set......Page 186
Making predictions on sample review texts......Page 188
Summary......Page 192
Answers to questions......Page 193
Image classification with pretrained VGG16......Page 200
DL4J and transfer learning......Page 202
Developing an image classifier using transfer learning......Page 203
Dataset collection and description......Page 204
Architecture choice and adoption......Page 205
Train and test set preparation......Page 211
Network training and evaluation......Page 212
Restoring the trained model and inferencing......Page 215
Making simple inferencing......Page 216
Summary......Page 219
Answers to questions......Page 220
Object detection from images and videos......Page 222
Object classification, localization, and detection......Page 223
Convolutional Sliding Window (CSW)......Page 226
Object detection from videos......Page 229
You Only Look Once (YOLO)......Page 231
Step 1 – Loading a pre-trained YOLO model......Page 236
Step 2 – Generating frames from video clips......Page 238
Step 3 – Feeding generated frames into Tiny YOLO model......Page 241
Step 4 – Object detection from image frames......Page 242
Step 5 – Non-max suppression in case of more than one bounding box......Page 243
Step 6 – wrapping up everything and running the application......Page 246
Frequently asked questions (FAQs)......Page 249
Answers to questions......Page 250
Chapter 7: Stock Price Prediction Using LSTM Network......Page 252
State-of-the-art automated stock trading......Page 253
Developing a stock price predictive model......Page 256
Data collection and exploratory analysis......Page 258
Preparing the training and test sets......Page 262
LSTM network construction......Page 270
Network training, and saving the trained model......Page 273
Restoring the saved model for inferencing......Page 275
Evaluating the model......Page 276
Summary......Page 285
Answers to questions......Page 286
Chapter 8: Distributed Deep Learning – Video Classification Using Convolutional LSTM Networks......Page 288
Distributed deep learning across multiple GPUs......Page 289
Distributed training on GPUs with DL4J......Page 290
UCF101 – action recognition dataset......Page 293
Solving the encoding problem......Page 295
Data processing workflow......Page 297
Simple UI for checking video frames......Page 301
Preparing training and test sets......Page 303
Network creation and training......Page 305
Performance evaluation......Page 309
Distributed training on AWS deep learning AMI 9.0......Page 311
Summary......Page 322
Answers to questions......Page 323
Notation, policy, and utility for RL......Page 325
Notations in reinforcement learning......Page 326
Policy......Page 328
Introduction to QLearning......Page 329
Neural networks as a Q-function......Page 330
Developing a GridWorld game using a deep Q-network......Page 333
Generating the grid......Page 334
Calculating agent and goal positions......Page 336
Calculating the action mask......Page 337
Providing guidance action......Page 338
Flattening input for the input layer......Page 339
Network construction and training......Page 340
Playing the GridWorld game......Page 347
Summary......Page 350
Answers to questions......Page 351
Chapter 10: Developing Movie Recommendation Systems Using Factorization Machines......Page 354
Collaborative filtering approaches......Page 355
Model-based collaborative filtering......Page 357
The utility matrix......Page 358
The cold-start problem in collaborative-filtering approaches......Page 359
Factorization machines in recommender systems......Page 360
Developing a movie recommender system using FMs......Page 363
Dataset description and exploratory analysis......Page 364
Converting the dataset into LibFM format......Page 371
Training and test set preparation......Page 375
Movie rating prediction......Page 378
Which one makes more sense ;– ranking or rating?......Page 389
Summary......Page 400
Answers to questions......Page 401
Chapter 11: Discussion, Current Trends, and Outlook......Page 405
Titanic survival prediction using MLP and LSTM networks......Page 406
Image classification using convolutional neural networks......Page 407
Image classification using transfer learning......Page 408
Stock price prediction using LSTM network......Page 409
Using deep reinforcement learning for GridWorld......Page 410
Current trends......Page 411
Residual neural networks......Page 412
GANs......Page 413
Capsule networks (CapsNet)......Page 414
Deep learning for clustering analysis......Page 415
Frequently asked questions (FAQs)......Page 416
Answers to questions......Page 417
Other Books You May Enjoy......Page 419
Index......Page 422
