ANN and SPR Relationship. Evaluation of a Class of Pattern-Recognition Networks (L. Kanal). Links between ANN and SPR (P.J. Werbos). Small Sample Size Problems in Designing Artificial Neural Networks (Š. Raudys, A.K. Jain). On Tree Structured Classifiers (S.B. Gelfand, E.J. Delp). Decision Tree Performance Enhancement Using an ANN Implementation (I.K. Sethi). Applications. Bayesian and Neural Network Pattern Recognition: A Theoretical Connection and Empirical Results with Handwritten Characters (D.-S. Lee, S.N. Srihari, R. Gaborski). Shape and Texture Recognition by a Neural Network (A. Khotanzad, J.-H. Lu). Neural Networks for Textured Image Processing (J. Ghosh, A.C. Bovik). Markov Random Fields and Neural Networks with Applications to Early Vision Problems (A. Rangarajan, R. Chellappa, B.S. Manjunath). Connectionist Models and their Application to Automatic Sppeech Recognition (Y. Bengio, R. De Mori). Implementation Aspects. Dynamic Associative Memories (M.H. Hassoun). Optical Associative Memories (B.V.K. Vijaya Kumar, P.K. Wong). Artificial Neural Nets in MOS Silicon (F.M.A. Salam, M.-R. Choi, Y. Wang). Author Index.
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.
- No. of pages:
- © North Holland 1991
- 30th September 1991
- North Holland
- eBook ISBN:
@qu:...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. @source:IEEE Transactions on Neural Networks
Wayne State University, Detroit, MI, USA
Professor in the Departments of Computer Science & Engineering, and Electrical & Computer Engineering at Michigan State University, East Lansing, MI, USA