Implementation of Machine Learning Algorithms Using Control-Flow and Dataflow Paradigms

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.

About the Author

Veljko Milutinović (1951) received his PhD from the University of Belgrade in Serbia, spent about a decade on various faculty positions in the USA (mostly at Purdue University and more recently at the University of Indiana in Bloomington), and was a co-designer of the DARPAs pioneering GaAs RISC microprocessor on 200MHz (about a decade before the first commercial effort on that same speed) and was a co-designer also of the related GaAs Systolic Array (with 4096 GaAs microprocessors). Later, for almost three decades, he taught and conducted research at the University of Belgrade in Serbia, for departments of EE, MATH, BA, and PHYS/CHEM. His research is mostly in data mining algorithms and dataflow computing, with the emphasis on mapping of data analytics algorithms onto fast energy efficient architectures. Most of his research was done in cooperation with industry (Intel, Fairchild, Honeywell, Maxeler, HP, IBM, NCR, RCA, etc.). For 20 of his edited books, publication forewords or other contributions were written by 20 different Nobel Laureates with whom he cooperated on his past industry sponsored projects.

Nenad Mitić is a full Professor at the Department of Computer Science, Faculty of Mathematics, University of Belgrade. He received his BSc, MSc and PhD from the University of Belgrade, Faculty of Mathematics. From 1983 to 1991 he was the system analyst on an IBM mainframe in Statistical Office of the Republic of Serbia, Belgrade. From 1991 till now he is with Faculty of Mathematics, Belgrade. His research interests cover areas of bioinformatics, data mining, big data, and functional programming.

Aleksandar Kartelj completed his PhD in Computer Science at Faculty of Mathematics in the year 2014. His research interests cover the areas of optimization, mathematical programming, and data mining. His publications are mostly related to metaheuristic optimization methods, data classification, and dimensionality reduction.

Miloš Kotlar received his B.Sc. (2016) and M.Sc. (2017) degrees in Electrical and Computer Engineering from the University of Belgrade, School of Electrical Engineering, Serbia. He is a Ph.D. candidate at the School of Electrical Engineering, University of Belgrade. His general research interests include implementation of energy efficient tensor implementations using the dataflow paradigm (FPGA and ASIC accelerators) and meta learning approaches for anomaly detection tasks.