Dimensionality Reduction With Unsupervised Nearest Neighbors

Dimensionality Reduction with Unsupervised Nearest Neighbors

This book is devoted to a novel approach for dimensionality reduction based on the famous nearest neighbor method that is a powerful classification and regression approach. It starts with an introduction to machine learning concepts and a real-world application from the energy domain. Then, unsupervised nearest neighbors (UNN) is introduced as efficient iterative method for dimensionality reduction. Various UNN models are developed step by step, reaching from a simple iterative strategy for discrete latent spaces to a stochastic kernel-based algorithm for learning submanifolds with independent parameterizations. Extensions that allow the embedding of incomplete and noisy patterns are introduced. Various optimization approaches are compared, from evolutionary to swarm-based heuristics. Experimental comparisons to related methodologies taking into account artificial test data sets and also real-world data demonstrate the behavior of UNN in practical scenarios. The book contains numerous color figures to illustrate the introduced concepts and to highlight the experimental results.

Proceedings of the Third ICMDS'24: Machine Learning, Inverse Problems and Related Fields

This book offers innovative insights into the integration of machine learning and inverse problems, showcasing cutting-edge methodologies that enhance computational efficiency and accuracy. By leveraging artificial intelligence, optimization techniques, and high-performance computing, it addresses complex challenges across various scientific and industrial domains. The contributions featured in this book encompass theoretical advancements and practical applications, highlighting diverse topics such as data-driven approaches, uncertainty quantification, and algorithmic innovations. This interdisciplinary collection is designed for researchers, practitioners, and students interested in the transformative potential of informatics and computational sciences. By presenting meticulously reviewed papers from the Third International Conference on Mathematical and Computational Sciences (ICMDS 2024), this issue serves as a valuable resource for fostering further research and development, inspiring new approaches to solving pressing problems through advanced computational methods.

Brain Functional Analysis and Brain-like Intelligence