skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Rule generation from neural networks

Abstract

The neural network approach has proven useful for the development of artificial intelligence systems. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. In this paper, we show how to interpret neural network knowledge in symbolic form. We lay down required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. The main result is a formalized relationship between a neural network and a rule-based system. In addition, it has been demonstrated that the neural network generates rules of better performance than the decision tree approach in noisy conditions. 7 refs.

Authors:
 [1]
  1. Univ. of Florida, Gainesville, FL (United States)
Publication Date:
OSTI Identifier:
135309
Resource Type:
Journal Article
Resource Relation:
Journal Name: IEEE Transactions on Systems, Man, and Cybernetics; Journal Volume: 24; Journal Issue: 8; Other Information: PBD: Aug 1994
Country of Publication:
United States
Language:
English
Subject:
99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; ARTIFICIAL INTELLIGENCE; ALGORITHMS; NEURAL NETWORKS; DESIGN; KNOWLEDGE BASE

Citation Formats

Fu, L. Rule generation from neural networks. United States: N. p., 1994. Web.
Fu, L. Rule generation from neural networks. United States.
Fu, L. 1994. "Rule generation from neural networks". United States. doi:.
@article{osti_135309,
title = {Rule generation from neural networks},
author = {Fu, L.},
abstractNote = {The neural network approach has proven useful for the development of artificial intelligence systems. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. In this paper, we show how to interpret neural network knowledge in symbolic form. We lay down required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. The main result is a formalized relationship between a neural network and a rule-based system. In addition, it has been demonstrated that the neural network generates rules of better performance than the decision tree approach in noisy conditions. 7 refs.},
doi = {},
journal = {IEEE Transactions on Systems, Man, and Cybernetics},
number = 8,
volume = 24,
place = {United States},
year = 1994,
month = 8
}
  • The authors consider the Hopfield model with the most simple form of the Hebbian learning rule, when only simultaneous activity of pre- and post-synaptic neurons leads to modification of synapse. An extra inhibition proportional to full network activity is needed. Both symmetric nondiluted and asymmetric diluted networks are considered. The model performs well at extremely low level of activity rho < {Kappa}/sup -1/2/, where {Kappa} is the mean number of synapses per neuron.
  • In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less
  • One of the inconveniences associated with the existing finite-element packages is the need for an educated user to develop a correct mesh at the preprocessing level. Procedures which start with a coarse mesh and attempt serious refinements, as is the case in most adaptive finite-element packages, are time consuming and costly. Hence, it is very important to develop a tool that can provide a mesh that either leads immediately to an acceptable solution, or would require fewer correcting steps to achieve better results. In this paper, the authors present a technique for automatic mesh generation based on artificial neural networksmore » (ANN). The essence of this technique is to predict the mesh density distribution of a given model, and then supply this information to a Kohonen neural network which provides the final mesh. Prediction of mesh density is accomplished by a simple feedforward neural network which has the ability to learn the relationship between mesh density and model geometric features. It will be shown that ANN are able to recognize delicate areas where a sharp variation of the magnetic field is expected. Examples of 2-D models are provided to illustrate the usefulness of the proposed technique.« less
  • The study of animal and human brains suggests overall architectural principles for sixth generation computers. Each such machine will comprise a network of more specialized devices, with many of these devices structured as highly parallel arrays of interacting neuron-like, possibly adaptive, components. The authors stress the interaction between computational neurobiology and neural engineering and note the two grains of analysis of schemas and neural networks, arguing that schemas will be the programming language of the sixth generation. After a brief introduction to the variety of neuron models now current, schemas are exemplified in a discussion of high-level vision. The papermore » emphasizes the domain-specific structure neural networks, as well as emphasizing that technologists have much to learn from the study of neurobiological systems. The authors close with a brief account of adaptation and the programming of sixth generation computers.« less
  • Prediction of the amount of hospital waste production will be helpful in the storage, transportation and disposal of hospital waste management. Based on this fact, two predictor models including artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. In this study, a 5-fold cross-validation procedure on a database containing total of 50 hospitals of Fars province (Iran) were used to verify the performance of the models. Three performance measures including MAR, RMSE and R{sup 2} were used to evaluate performancemore » of models. The MLR as a conventional model obtained poor prediction performance measure values. However, MLR distinguished hospital capacity and bed occupancy as more significant parameters. On the other hand, ANNs as a more powerful model, which has not been introduced in predicting rate of medical waste generation, showed high performance measure values, especially 0.99 value of R{sup 2} confirming the good fit of the data. Such satisfactory results could be attributed to the non-linear nature of ANNs in problem solving which provides the opportunity for relating independent variables to dependent ones non-linearly. In conclusion, the obtained results showed that our ANN-based model approach is very promising and may play a useful role in developing a better cost-effective strategy for waste management in future.« less