Project CellNet: Evolving An Autonomous Pattern Recognizer

We describe the desire for a black box approach to pattern classification: a generic Autonomous Pattern Recognizer, which is capable of self-adapting to specific alphabets without human intervention. The CellNet software system is introduced, an evolutionary system that optimizes a set of pattern-recognizing agents relative to a provided set of features and a given pattern database. CellNet utilizes a new genetic operator designed to facilitate a canalization of development: Merger. CellNet utilizes our own set of arbitrarily chosen features, and is applied to the CEDAR Database of handwritten Latin characters, as well as to a database of handwritten Indian digits provided by CENPARMI. CellNet's cooperative co-evolutionary approach shows significant improvement over a more standard Genetic Algorithm, both in terms of efficiency and in nearly eliminating over-fitting (to the training set). Additionally, the binary classifiers autonomously evolved by CellNet return validation accuracies approaching 98% for both Latin and Indian digits, with no global changes to the system between the two trials.

[1]  Rabab Kreidieh Ward,et al.  A novel invariant mapping applied to hand-written arabic character recognition , 2001, Pattern Recognit..

[2]  Korris Fu-Lai Chung,et al.  Neocognitron based handwriting recognition system performance tuning using genetic algorithm , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[3]  M. Vose The Simple Genetic Algorithm , 1999 .

[4]  Mineichi Kudo,et al.  A comparative evaluation of medium- and large-scale feature selectors for pattern classifiers , 1998, Kybernetika.

[5]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[6]  Donald E. Brown,et al.  Fast generic selection of features for neural network classifiers , 1992, IEEE Trans. Neural Networks.

[7]  Michael Fairhurst,et al.  Feature selection in automatic signature verification , 1994 .

[8]  M.J. Martin-Bautista,et al.  A survey of genetic feature selection in mining issues , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[9]  Jack Sklansky,et al.  On Automatic Feature Selection , 1988, Int. J. Pattern Recognit. Artif. Intell..

[10]  Ching Y. Suen,et al.  Databases for recognition of handwritten Arabic cheques , 2003, Pattern Recognit..

[11]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[12]  Kenneth DeJong,et al.  Robust feature selection algorithms , 1993, Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93).

[13]  Dit-Yan Yeung,et al.  Recognition of Handwritten Digits Using Deformable , 1998 .

[14]  Melanie Mitchell,et al.  Investigation of image feature extraction by a genetic algorithm , 1999, Optics + Photonics.

[15]  Fred Stentiford,et al.  Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search Procedure , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  R. E. Uhrig,et al.  Using genetic algorithms to select inputs for neural networks , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[17]  Haitao Liu,et al.  Feature selection for handwritten Chinese character recognition based on genetic algorithms , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).