Deep Learning: Practical Neural Networks with Java

by

Publisher - Packt Publishing

Category - Engineering & IT

Key FeaturesDevelop a sound strategy to solve predictive modelling problems using the most popular machine learning Java libraries.Explore a broad variety of data processing, machine learning, and natural language processing through diagrams, source code, and real-world applicationsThis step-by-step guide will help you solve real-world problems and links neural network theory to their applicationBook DescriptionMachine learning applications are everywhere, from self-driving cars, spam detection, document search, and trading strategies, to speech recognitionStarting with an introduction to basic machine learning algorithms, this course takes you further into this vital world of stunning predictive insights and remarkable machine intelligence. This course helps you solve challenging problems in image processing, speech recognition, language modeling. You will discover how to detect anomalies and fraud, and ways to perform activity recognition, image recognition, and text. You will also work with examples such as weather forecasting, disease diagnosis, customer profiling, generalization, extreme machine learning and more. By the end of this course, you will have all the knowledge you need to perform deep learning on your system with varying complexity levels, to apply them to your daily work.The course provides you with highly practical content explaining deep learning with Java, from the following Packt books:Java Deep Learning EssentialsMachine Learning in JavaNeural Network Programming with Java, Second EditionWhat you will learnGet a practical deep dive into machine learning and deep learning algorithmsExplore neural networks using some of the most popular Deep Learning frameworksDive into Deep Belief Nets and Stacked Denoising Autoencoders algorithmsApply machine learning to fraud, anomaly, and outlier detectionExperiment with deep learning concepts, algorithms, and the toolbox for deep learningSelect and split data sets into training, test, and validation, and explore validation strategiesApply the code generated in practical examples, including weather forecasting and pattern recognitionAbout the AuthorYusuke Sugomori is a creative technologist with a background in information engineering. When he was a graduate school student, he cofounded Gunosy with his colleagues, which uses machine learning and web-based data mining to determine individual users respective interests and provides an optimized selection of daily news items based on those interests. This algorithm-based app has gained a lot ofattention since its release and now has more than 10 million users. The company has been listed on the Tokyo Stock Exchange since April 28, 2015.In 2013, Sugomori joined Dentsu, the largest advertising company in Japan based on nonconsolidated gross profit in 2014, where he carried out a wide variety of digital advertising, smartphone app development, and big data analysis. He was also featured as one of eight new generation creators by the Japanese magazine Web Designing.In April 2016, he joined a medical start-up as cofounder and CTO.Bostjan Kaluza is a researcher in artificial intelligence and machine learning. Bostjan is the chief data scientist at Evolven, a leading IT operations analytics company, focusing on configuration and change management. He works with machine learning, predictive analytics, pattern mining, and anomaly detection to turn data into understandable relevant information and actionable insight.Prior to Evolven, Bostjan served as a senior researcher in the department of intelligent systems at the Jozef Stefan Institute, a leading Slovenian scientific research institution, and led research projects involving pattern and anomaly detection, ubiquitous computing, and multi-agent systems. Bostjan was also a visiting researcher at the University of Southern California, where he studied suspicious and anomalous agent behavior in the context of security applications. Bostjan has extensive experience in Java and Python, and he also lectures on Weka in the classroom.Focusing on machine learning and data science, Bostjan has published numerous articles in professional journals, delivered conference papers, and authored or contributed to a number of patents. In 2013, Bostjan published his first book on data science, Instant Weka How-to, Packt Publishing, exploring how to leverage machine learning using Weka. Learn more about him at http://bostjankaluza.net.Fabio M. Soares is currently a PhD candidate at the Federal University of Para (Universidade Federal do Para - UFPA), in northern Brazil. He is very passionate about technology in almost all fields, and designs neural network solutions since 2004 and has applied this technique in several fields like telecommunications, industrial process control and modeling, hydroelectric power generation, financial applications, retail customer analysis and so on. His research topics cover supervised learning for data-driven modeling. As of 2017, he is currently carrying on research projects with chemical process modeling and control in the aluminum smelting and ferronickel processing industries, and has worked as a lecturer teaching subjects involving computer programming and artificial intelligence paradigms. As an active researcher, he has also a number of articles published in English language in many conferences and journals, including four book chapters.Alan M. F. Souza is computer engineer from Instituto de Estudos Superiores da Amazonia (IESAM). He holds a post-graduate degree in project management software and a masters degree in industrial processes (applied computing) from Universidade Federal do Para (UFPA). He has been working with neural networks since 2009 and has worked with Brazilian IT companies developing in Java, PHP, SQL, and other programming languages since 2006. He is passionate about programming and computational intelligence. Currently, he is a professor at Universidade da Amazonia (UNAMA) and a PhD candidate at UFPA.Table of ContentsDeep Learning OverviewAlgorithms for Machine Learning – Preparing for Deep LearningDeep Belief Nets and Stacked Denoising AutoencodersDropout and Convolutional Neural NetworksExploring Java Deep Learning Libraries – DL4J, ND4J, and MoreApproaches to Practical Applications – Recurrent Neural Networks and MoreOther Important Deep Learning LibrariesWhats Next?Applied Machine Learning Quick StartJava Libraries and Platforms for Machine LearningBasic Algorithms – Classification, Regression, and ClusteringCustomer Relationship Prediction with EnsemblesAffinity AnalysisRecommendation Engine with Apache MahoutFraud and Anomaly DetectionImage Recognition with Deeplearning4jActivity Recognition with Mobile Phone SensorsText Mining with Mallet – Topic Modeling and Spam DetectionWhat is Next?ReferencesGetting Started with Neural NetworksGetting Neural Networks to LearnPerceptrons and Supervised LearningSelf-Organizing MapsForecasting WeatherClassifying Disease DiagnosisClustering Customer ProfilesText RecognitionOptimizing and Adapting Neural NetworksCurrent Trends in Neural NetworksReferencesBibliography

Please login to borrow the book. Preview