Based on current literature and cutting-edge advances in the machine learning field, there are four algorithms whose usage in new application domains must be explored: neural networks, rule induction algorithms, tree-based algorithms, and density-based algorithms. A number of machine learning related algorithms have been derived from these four algorithms. Consequently, they represent excellent underlying methods for extracting hidden knowledge from unstructured data, as essential data mining tasks. Implementation of Machine Learning Algorithms Using Control-Flow and Dataflow Paradigms presents widely used data-mining algorithms and explains their advantages and disadvantages, their mathematical treatment, applications, energy efficient implementations, and more. It presents research of energy efficient accelerators for machine learning algorithms. Covering topics such as control-flow implementation, approximate computing, and decision tree algorithms, this book is an essential resource for computer scientists, engineers, students and educators of higher education, researchers, and academicians.

As computers continue to remain essential tools for the pursuit of physics, medicine, economics, social sciences, and more, supercomputers are proving that they can further extend and greatly enhance as-of-yet undiscovered knowledge and solve the world's most complex problems. As these instruments continue to lead to groundbreaking discoveries and breakthroughs, it is imperative that research remains up to date with the latest findings and uses. The Handbook of Research on Methodologies and Applications of Supercomputing is a comprehensive and critical reference book that provides research on the latest advances of control flow and dataflow supercomputing and highlights selected emerging big data applications needing high acceleration and/or low power. Consequently, this book advocates the need for hybrid computing, where the control flow part represents the host architecture and dataflow part represents the acceleration architecture. These issues cover the initial eight chapters. The remaining eight chapters cover selected modern applications that are best implemented on a hybrid computer, in which the transactional parts (serial code) are implemented on the control flow part and the loops (parallel code) on the dataflow part. These final eight chapters cover two major application domains: scientific computing and computing for digital economy. This book offers applications in marketing, medicine, energy systems, and library science, among others, and is an essential source for scientists, programmers, engineers, practitioners, researchers, academicians, and students interested in the latest findings and advancements in supercomputing.

Based on current literature and cutting-edge advances in the machine learning field, there are four algorithms whose usage in new application domains must be explored: neural networks, rule induction algorithms, tree-based algorithms, and density-based algorithms. A number of machine learning related algorithms have been derived from these four algorithms. Consequently, they represent excellent underlying methods for extracting hidden knowledge from unstructured data, as essential data mining tasks. Implementation of Machine Learning Algorithms Using Control-Flow and Dataflow Paradigms presents widely used data-mining algorithms and explains their advantages and disadvantages, their mathematical treatment, applications, energy efficient implementations, and more. It presents research of energy efficient accelerators for machine learning algorithms. Covering topics such as control-flow implementation, approximate computing, and decision tree algorithms, this book is an essential resource for computer scientists, engineers, students and educators of higher education, researchers, and academicians.