Advances In Machine Learning Research

In the digital age, the field of machine learning has lived up to its promise of learning from and leveraging data in diverse fields, creating knowledge and driving decisions. This book intends to detail advances in the state-of-the-art in machine learning, one of the fastest emerging fields in the industry and one of the most popular fields of research in computational sciences. The roots of machine learning methods can be traced back to both statistics and computer science. Its story continues to evolve and the future is set to be greatly influenced through ML's contributions to the human knowledge-base as well as the economic engine. Applied machine learning research enthuses the masses with applications such as video games that interact through a camera, self-driving cars, etc. At the same time, more basic machine learning research holds the potential to impact knowledge elicitation, learning, predictions, decisions, and optimizations in fields ranging from environmental/biomedical/clinical informatics on one hand to online retail and search on the other. Accordingly, the contents of this volume are geared to present a full-color palette consisting of improved optimization algorithms, novel ANN design architectures, along with customized methods for mining an environmental dataset, pattern recognition in images, and for improved document and text search. While many out-of-the-box implementations of machine learning algorithms are currently available, customized methods developed by honed and innovative researchers continue to provide significant improvements in various contexts. Advancements through basic research continue to break the barriers of the extent of ML's contribution to the world.