Evolving Neural Networks for the Classification of Galaxies

The FIRST survey (Faint Images of the Radio Sky at Twenty-cm) is scheduled to cover 10,000 square degrees of the northern and southern galactic caps. Until recently, astronomers classified radio-emitting galaxies through a visual inspection of FIRST images. Besides being subjective, prone to error and tedious, this manual approach is becoming infeasible: upon completion, FIRST will include almost a million galaxies. This paper describes the application of six methods of evolving neural networks (NNs) with genetic algorithms (GAs) to identify bent-double galaxies. The objective is to demonstrate that GAs can successfully address some common problems in the application of NNs to classification problems, such as training the networks, choosing appropriate network topologies, and selecting relevant features. The results indicate that most of the methods we tried performed equally well on our data, but using a GA to select features produced the best results.

[1]  Thomas P. Caudell,et al.  Parametric Connectivity: Training of Constrained Networks using Genetic Algorithms , 1989, ICGA.

[2]  Nicholas J. Radcliffe,et al.  Genetic neural networks on MIMD computers , 1992 .

[3]  C. Kamath,et al.  Finding Bent-double Radio Galaxies: A Case Study in Data Mining , 2000 .

[4]  S. Odewahn,et al.  Automated star/galaxy discrimination with neural networks , 1992 .

[5]  Simon M. Lucas,et al.  A comparison of matrix rewriting versus direct encoding for evolving neural networks , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[6]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.

[7]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[8]  A. Skinner,et al.  Neural networks in computational materials science: training algorithms , 1995 .

[9]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[10]  Frédéric Gruau,et al.  Genetic synthesis of Boolean neural networks with a cell rewriting developmental process , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[11]  Patrick K. Simpson,et al.  Dynamic Feature Set Training of Neural Nets for Classification , 1995, Evolutionary Programming.

[12]  Richard L. White,et al.  A Catalog of 1.4 GHz Radio Sources from the FIRST Survey , 1997 .

[13]  Worthy N. Martin,et al.  Genetic Algorithms for Feature Selection for Counterpropagation Networks , 1990 .

[14]  L. Darrell Whitley,et al.  Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..

[15]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[16]  L. Darrell Whitley,et al.  Optimizing Neural Networks Using FasterMore Accurate Genetic Search , 1989, ICGA.

[17]  Richard L. White,et al.  The FIRST Survey: Faint Images of the Radio Sky at twenty centimeters , 1995 .

[18]  Robert F. Harrison,et al.  Optimization and training of feedforward neural networks by genetic algorithms , 1991 .

[19]  Johan A. K. Suykens,et al.  Genetic Weight Optimization of a Feedforward Neural Network Controller , 1993 .

[20]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..

[21]  O. Lahav,et al.  Morphological Classification of galaxies by Artificial Neural Networks , 1992 .

[22]  J. Urgen Branke.  Evolutionary Algorithms for Neural Network Design and Training , 1995 .

[23]  A. Adams,et al.  Hubble classification of galaxies using neural networks , 1994 .

[24]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[25]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[26]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.