Apache Spark Deep Learning Cookbook

Ahmed Sherif is a data scientist who has worked with data in various roles since 2005. He started off with BI solutions and transitioned to data science in 2013. In 2016, he obtained a master's in Predictive Analytics from Northwestern University, where he studied the science and application of machine learning and predictive modeling using both Python and R. Lately, he has been developing machine learning and deep learning solutions on the cloud using Azure. In 2016, he published his first book, Practical Business Intelligence. He currently works as a Technology Solution Profession in Data and AI for Microsoft. Amrith Ravindra is a machine learning enthusiast who holds degrees in electrical and industrial engineering. While pursuing his masters, he dove deeper into the world of machine learning and developed a love for data science. Graduate-level courses in engineering gave him the mathematical background to launch himself into a career in machine learning. He met Ahmed Sherif at a local data science meetup in Tampa. They decided to put their brains together to write a book on their favorite machine learning algorithms. He hopes this book will help him achieve his ultimate goal of becoming a data scientist and actively contributing to machine learning. Michal Malohlava, creator of Sparkling Water, is a geek and the developer; Java, Linux, programming languages enthusiast who has been developing software for over 10 years. He obtained his PhD from Charles University in Prague in 2012, and post doctorate from Purdue University. During his studies, he was interested in the construction of not only distributed but also embedded and real-time, component-based systems, using model-driven methods and domain-specific languages. He participated in the design and development of various systems, including SOFA and Fractal component systems and the jPapabench control system. Now, his main interest is big data computation. He participates in the development of the H2O platform for advanced big data math and computation, and its embedding into Spark engine, published as a project called Sparkling Water. Adnan Masood, PhD is an artificial intelligence and machine learning researcher, visiting scholar at Stanford AI Lab, software engineer, Microsoft MVP (Most Valuable Professional), and Microsoft's regional director for artificial intelligence. As chief architect of AI and machine learning at UST Global, he collaborates with Stanford AI Lab and MIT CSAIL, and leads a team of data scientists and engineers building artificial intelligence solutions to produce business value and insights that affect a range of businesses, products, and initiatives.

• Table of ContentsSetting Up Spark for Deep Learning DevelopmentCreating a Neural Network in SparkPain Points of Convolutional Neural NetworksPain Points of Recurrent Neural NetworksPredicting Fire Department Calls with Spark MLUsing LSTMs in Generative NetworksNatural Language Processing with TF-IDFReal Estate Value Prediction using XGBoostPredicting Apple Stock Market Cost with LSTMFace Recognition using Deep Convolutional NetworksCreating and Visualizing Word Vectors Using Word2VecCreating a Movie Recommendation Engine with KerasImage Classification with TensorFlow on Spark