Artificial Neural Networks and Statistical Pattern Recognition: Old and New Connections

Sethi, I. K.

ISBN 10: 0444887415 / ISBN 13: 9780444887412

Published by North Holland, 1991

About this Item

8vo (22.5 cm), XIV, 271 pp. Laminated wrappers. The book explores the intriguing interplay between two prominent fields in the realm of machine learning and data analysis. This thought-provoking book delves into the historical development and the modern-day synergies between artificial neural networks (ANNs) and statistical pattern recognition (SPR), shedding light on their shared roots and divergent paths. By examining the historical context, readers gain a comprehensive understanding of how ANNs and SPR have evolved independently over time. The book traces their origins, from the early perceptron models and foundational statistical techniques to the emergence of deep learning and advanced probabilistic models. Through this historical lens, it becomes evident that ANNs and SPR have followed distinct trajectories, with ANNs prioritizing flexible, connectionist approaches, and SPR emphasizing probabilistic modeling and statistical inference. However, the book goes beyond mere historical analysis and illuminates the contemporary convergence of ANNs and SPR. It explores how recent developments in both fields have led to a remarkable convergence, creating new avenues for collaboration and synergy. The advent of deep learning, which combines ANN architectures with large-scale data and computational power, has revolutionized both ANNs and SPR, unlocking new possibilities for pattern recognition, data analysis, and decision-making. Seller Inventory # 008331

Bibliographic Details

Title: Artificial Neural Networks and Statistical ...

Publisher: North Holland

Publication Date: 1991

Binding: Soft cover

Condition: As New

About this title

Synopsis:

With the growing complexity of pattern recognition related problems being solved using Artificial Neural Networks, many ANN researchers are grappling with design issues such as the size of the network, the number of training patterns, and performance assessment and bounds. These researchers are continually rediscovering that many learning procedures lack the scaling property; the procedures simply fail, or yield unsatisfactory results when applied to problems of bigger size. Phenomena like these are very familiar to researchers in statistical pattern recognition (SPR), where the curse of dimensionality is a well-known dilemma. Issues related to the training and test sample sizes, feature space dimensionality, and the discriminatory power of different classifier types have all been extensively studied in the SPR literature. It appears however that many ANN researchers looking at pattern recognition problems are not aware of the ties between their field and SPR, and are therefore unable to successfully exploit work that has already been done in SPR. Similarly, many pattern recognition and computer vision researchers do not realize the potential of the ANN approach to solve problems such as feature extraction, segmentation, and object recognition. The present volume is designed as a contribution to the greater interaction between the ANN and SPR research communities.

Review:

...a useful book... to be recommended to both those working in statistical pattern recognition as well as those in neural networks interested in the growing relationships between these fields. -- IEEE Transactions on Neural Networks