Credit Assignment Among Neurons in Co-evolving Populations

Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem).

[1]  M. Husken,et al.  Optimization for problem classes-neural networks that learn to learn , 2000, 2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks. Proceedings of the First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (Cat. No.00.

[2]  Bruce A. Whitehead,et al.  Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction , 1996, IEEE Trans. Neural Networks.

[3]  Michael Conrad,et al.  Combining evolution with credit apportionment: A new learning algorithm for neural nets , 1994, Neural Networks.

[4]  Bruce A. Whitehead,et al.  Genetic evolution of radial basis function coverage using orthogonal niches , 1996, IEEE Trans. Neural Networks.

[5]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[6]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[7]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[8]  Risto Miikkulainen,et al.  COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS , 2001 .

[9]  Risto Miikkulainen,et al.  Forming Neural Networks Through Efficient and Adaptive Coevolution , 1997, Evolutionary Computation.

[10]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[11]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[12]  Christian Igel,et al.  Empirical evaluation of the improved Rprop learning algorithms , 2003, Neurocomputing.

[13]  Xin Yao,et al.  Making use of population information in evolutionary artificial neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[14]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[15]  Farmer,et al.  Predicting chaotic time series. , 1987, Physical review letters.