论文信息 - Data Mining Using Surface and Deep Agents Based on Neural Networks

Data Mining Using Surface and Deep Agents Based on Neural Networks

This paper presents an approach to data mining based on an architecture that uses two kinds of neural network-based agents: (i) an instantaneously-trained surface learning agent that quickly adapts to new modes of operation; and, (ii) a deep learning agent that is very accurate within a specific regime of operation. The two agents perform complementary functions that improve the overall performance. The performance of the hybrid architecture has been compared with that of a backpropagation network for a variety of classification problems and found to be superior based on the RMS error criterion.

Subhash C. Kak | Lei Wang | Yuhua Chen

[1] Subhash Kak,et al. The Three Languages of the Brain: Quantum, Reorganizational, and Associative , 1996 .

[2] Philip S. Yu,et al. A framework for on-demand classification of evolving data streams , 2006, IEEE Transactions on Knowledge and Data Engineering.

[3] Subhash Kak,et al. New algorithms for training feedforward neural networks , 1994, Pattern Recognit. Lett..

[4] Má. PATTERN RECOGNITION USING NEURAL NETWORKS , 2008 .

[5] Subhash Kak. Better Web Searches and Prediction with Instantaneously Trained Neural Networks , 1999 .

[6] Subhash Kak,et al. Fast Classification Networks For Signal Processing , 2002 .

[7] E. Mine Cinar,et al. Neural Networks: A New Tool for Predicting Thrift Failures , 1992 .

[8] Yurong Liu,et al. State estimation for jumping recurrent neural networks with discrete and distributed delays , 2009, Neural Networks.

[9] Subhash C. Kak,et al. A class of instantaneously trained neural networks , 2002, Inf. Sci..

[10] Kun-Won Tang,et al. A new corner classification approach to neural network training , 1998 .