Efficient Learning Machines ― Theories, Concepts, and Applications for Engineers and System Designers

Efficient Learning Machines explores all the major topics of machine learning, including big data, knowledge discovery, classifications, genetic algorithms, neural networking, kernel methods, and gaming theory.

The authors' synthetic approach weaves together theoretical exposition, design principle, and practical application. Their experiential emphasis, expressed in close analysis of sample algorithms throughout the book, aims to equip the reader to design and create new and more efficient systems.

Rahul Khanna is currently a platform architect at Intel Corporation involved in development of energy-efficient algorithms. Over the past 17 years he has worked on server system software technologies, including platform automation, power/thermal optimization techniques, reliability, optimization, and predictive methodologies. He has authored numerous technical papers and book chapters in the areas related to energy optimization, platform wireless interconnects, sensor networks, interconnect reliability, predictive modeling, motion estimation, and security. He holds 27 patents. He is the co-inventor of the Intel IBIST methodology for High-Speed interconnect testing. His research interests include machine learning-based power/thermal optimization algorithms, narrow-channel high-speed wireless interconnects, and information retrieval in dense sensor networks. Rahul is member of IEEE and the recipient of three Intel Achievement Awards for his contributions in areas related to advancements of platform technologies. He is the author of A Vision for Platform Autonomy: Robust Frameworks for Systems.