Learn More
The paper presents an integrated approach to incremental learning in autonomous systems, that includes both pattern recognition and feature selection. The approach utilizes evolving connectionist systems (ECoS) and is applied on on-line image and speech pattern learning and recognition tasks. The experiments show that ECoS are a suitable paradigm for(More)
Convolutional neural networks are known to be effective in learning complex image classification tasks. However, how to design the architecture or complexity of the network structure requires a more quantitative analysis of the architecture design. In this paper, we study the effect of model complexity on generalization capability of the convolutional(More)
  • 1