+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Reorganizing knowledge in neural networks: an explanatory mechanism for neural networks in data classification problems



Reorganizing knowledge in neural networks: an explanatory mechanism for neural networks in data classification problems



IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics 26(1): 107-117



We propose an explanatory mechanism for multilayered neural networks (NN). In spite of the effective learning capability as a uniform function approximator, the multilayered NN suffers from unreadability, i.e., it is difficult for the user to interpret or understand the "knowledge" that the NN has by looking at the connection weights and thresholds obtained by backpropagation (BP). This unreadability comes from the distributed nature of the knowledge representation in the NN. In this paper, we propose a method that reorganizes the distributed knowledge in the NN to extract approximate classification rules. Our rule extraction method is based on the analysis of the function that the NN has learned, rather than on the direct interpretation of connection weights as correlation information. More specifically, our method divides the input space into "monotonic regions" where a monotonic region is a set of input patterns that belongs to the same class with the same sensitivity pattern. Approximate classification rules are generated by projecting these monotonic regions.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 055492312

Download citation: RISBibTeXText

PMID: 18263010

DOI: 10.1109/3477.484442


Related references

For classification and predictive purposes, simulated neural networks (SNNs; more often called artificial neural networks, ANNs) offer a powerful alternative to traditional statistical analyses. Epilepsia 40(9): 1323-1324, 1999

Neural Networks Applied to Pharmaceutical Problems. VI. Reconstruction of Weight Matrices in Neural Networks. A Method of Correlating Outputs with Inputs. Chemical & Pharmaceutical Bulletin 39(5): 1222-1228, 1991

Testing the identity of hashish samples with ICP-AES and NAA and data handling with neural networks. 2. Data verification with the use of artificial neural networks. Die Pharmazie 53(1): 39-42, 1998

On-line retrainable neural networks: improving the performance of neural networks in image analysis problems. IEEE Transactions on Neural Networks 11(1): 137-155, 2008

Identity determination of hashish samples quantified by means of ICP-AES and NAA and data handling with neural networks. Part 2. Separation of sample signatures with neural networks. Pharmazie 53(1): 39-42, 1998

A reliable data delivery mechanism for grid power quality using neural networks in wireless sensor networks. Sensors 10(10): 9349-9358, 2012

An investigation into the application of neural networks, fuzzy logic, genetic algorithms, and rough sets to automated knowledge acquisition for classification problems. Neurocomputing 24(1-3): 37-54, 1999

Neural networks applied to pharmaceutical problems. IV. Basic operating characteristics of neural networks when applied to structure-activity studies. Chemical & Pharmaceutical Bulletin 39(2): 358-366, 1991

Neural networks applied to pharmaceutical problems. Iii. Neural networks applied to quantitative structure-activity relationship (Qsar) analysis. Journal of Medicinal Chemistry 33(9): 2583-2590, 1990

Comparative Study of Artificial Neural Networks and Wavelet Artificial Neural Networks for Groundwater Depth Data Forecasting with Various Curve Fractal Dimensions. Water Resources Management 28(15): 5297-5317, 2014

Efficient classification for multiclass problems using modular neural networks. IEEE Transactions on Neural Networks 6(1): 117-124, 1995

Protein secondary structure prediction improved by recurrent neural networks integrated with two-dimensional convolutional neural networks. Journal of Bioinformatics and Computational Biology 16(5): 1850021, 2018

The Use of Artificial Neural Networks to Study Perception in Animals || Neural Networks for Perceptual Processing: From Simulation Tools to Theories. Philosophical Transactions Biological Sciences 362(1479): 339-353, 2007

The Use of Artificial Neural Networks to Study Perception in Animals || Sensory Ecology and Perceptual Allocation: New Prospects for Neural Networks. Philosophical Transactions Biological Sciences 362(1479): 355-367, 2007

Drought Forecasting Using Neural Networks, Wavelet Neural Networks, and Stochastic Models: Case of the Algerois Basin in North Algeria. Water Resources Management 30(7): 2445-2464, 2016