Results 1  10
of
37
Symbolic knowledge extraction from trained neural networks: A sound approach
, 2001
"... Although neural networks have shown very good performance in many application domains, one of their main drawbacks lies in the incapacity to provide an explanation for the underlying reasoning mechanisms. The "explanation capability" of neural networks can be achieved by the extraction of ..."
Abstract

Cited by 55 (9 self)
 Add to MetaCart
Although neural networks have shown very good performance in many application domains, one of their main drawbacks lies in the incapacity to provide an explanation for the underlying reasoning mechanisms. The "explanation capability" of neural networks can be achieved by the extraction of symbolic knowledge. In this paper, we present a new method of extraction that captures nonmonotonic rules encoded in the network, and prove that such a method is sound. We start by discussing some of the main problems of knowledge extraction methods. We then discuss how these problems may be ameliorated. To this end, a partial ordering on the set of input vectors of a network is defined, as well as a number of pruning and simplification rules. The pruning rules are then used to reduce the search space of the extraction algorithm during a pedagogical extraction, whereas the simplification rules are used to reduce the size of the extracted set of rules. We show that, in the case of regular networks, the extraction algorithm is sound and complete. We proceed to extend the extraction algorithm to the class of nonregular networks, the general case. We show that nonregular networks always contain regularities in their subnetworks. As a result, the underlying extraction method for regular networks can be applied, but now in a decompositional fashion. In order to combine the sets of rules extracted from each subnetwork into the final set of rules, we use a method whereby we are able to keep the soundness of the extraction algorithm. Finally, we present the results of an empirical analysis of the extraction system, using traditional examples and realworld application problems. The results have shown that a very high fidelity between the extracted set of rules and the network can be achieved....
Hybrid Neural Systems
, 2000
"... This chapter provides an introduction to the field of hybrid neural systems. Hybrid neural systems are computational systems which are based mainly on artificial neural networks but also allow a symbolic interpretation, or interaction with symbolic components. In this overview, we will describe rece ..."
Abstract

Cited by 53 (11 self)
 Add to MetaCart
(Show Context)
This chapter provides an introduction to the field of hybrid neural systems. Hybrid neural systems are computational systems which are based mainly on artificial neural networks but also allow a symbolic interpretation, or interaction with symbolic components. In this overview, we will describe recent results of hybrid neural systems. We will give a brief overview of the main methods used, outline the work that is presented here, and provide additional references. We will also highlight some important general issues and trends.
Hybrid neural systems: from simple coupling to fully integrated neural networks
 Neural Computing Surveys
, 1999
"... This paper describes techniques for integrating neural networks and symbolic components into powerful hybrid systems. Neural networks have unique processing characteristics that enable tasks to be performed that would be di cult or intractable for a symbolic rulebased system. However, a standalone ..."
Abstract

Cited by 33 (7 self)
 Add to MetaCart
This paper describes techniques for integrating neural networks and symbolic components into powerful hybrid systems. Neural networks have unique processing characteristics that enable tasks to be performed that would be di cult or intractable for a symbolic rulebased system. However, a standalone neural network requires an interpretation either by ahuman or a rulebased system. This motivates the integration of neural/symbolic techniques within a hybrid system. Anumber of integration possibilities exist: some systems consist of neural network components performing symbolic tasks while other systems are composed of several neural networks and symbolic components, each component acting as a selfcontained module communicating with the others. Other hybrid systems are able to transform subsymbolic representations into symbolic ones and viceversa. This paper providesanoverview and evaluation of the state of the artofseveral hybrid neural systems for rulebased processing. 1
The Connectionist Inductive Learning and Logic Programming System
, 1999
"... This paper presents the Connectionist Inductive Learning and Logic Programming System (CIL²P). CIL²P is a new massively parallel computational model based on a feedforward Artificial Neural Network that integrates inductive learning from examples and background knowledge, with deductive learning ..."
Abstract

Cited by 23 (6 self)
 Add to MetaCart
This paper presents the Connectionist Inductive Learning and Logic Programming System (CIL²P). CIL²P is a new massively parallel computational model based on a feedforward Artificial Neural Network that integrates inductive learning from examples and background knowledge, with deductive learning from Logic Programming. Starting with the background knowledge represented by a propositional logic program, a translation algorithm is applied generating a neural network that can be trained with examples. The results obtained with this refined network can be explained by extracting a revised logic program from it. Moreover, the neural network computes the stable model of the logic program inserted in it as background knowledge, or learned with the examples, thus functioning as a parallel system for Logic Programming. We have successfully applied CIL2Ptotwo realworld problems of computational biology, specifically DNA sequence analyses. Comparisons with the results obtained by some of the main neural, symbolic, and hybrid inductive learning systems, using the same domain knowledge, show the effectiveness of CIL²P.
Dimensions of neuralsymbolic integration – a structural survey
 We Will Show Them: Essays in Honour of Dov Gabbay
"... Research on integrated neuralsymbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to ..."
Abstract

Cited by 22 (6 self)
 Add to MetaCart
Research on integrated neuralsymbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to
Neurules: Improving the Performance of Symbolic Rules
 In Proceedings of the Eleventh IEEE International Conference on Tools with Artificial Intelligence (TAI’99
, 1999
"... ..."
Connectionist Inference Models
 NEURAL NETWORKS
, 2001
"... The performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rulebased reasoning and whethe ..."
Abstract

Cited by 19 (0 self)
 Add to MetaCart
The performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rulebased reasoning and whether they involve distributed or localist representations. The benefits and disadvantages of different representations and systems are outlined, and conclusions drawn regarding the capabilities of connectionist inference systems when compared with symbolic inference systems or when used for cognitive modelling.
Constructing Modular Hybrid Rule Bases for Expert Systems
 Proceedings of the 13th International FLAIRS Conference
, 2001
"... Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed ..."
Abstract

Cited by 6 (5 self)
 Add to MetaCart
Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present a method for generating neurules from empirical data. To overcome the difficulty of the adaline unit to classify nonseparable training examples, the notion of 'closeness' between training examples is introduced. In case of a training failure, two subsets of 'close' examples are produced from the initial training set and a copy of the neurule for each subset is trained. Failure of training any copy, leads to production of further subsets as far as success is achieved.
A Hybrid Approach for Arabic Literal Amounts Recognition
 THE ARABIAN J. SCIENCE AND ENG
, 2004
"... The challenge of hybrid learning systems is to use the information provided by one source of information to compensate information missing from the other source. The neuro–symbolic combination represents a promising research way. The synergy between the symbolic (theoretical) and neural (empirical) ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
The challenge of hybrid learning systems is to use the information provided by one source of information to compensate information missing from the other source. The neuro–symbolic combination represents a promising research way. The synergy between the symbolic (theoretical) and neural (empirical) approaches makes their combination more effective than each of them used alone. In this article, we describe an Arabic literal amount recognition system that uses a neurosymbolic classifier. For this purpose, we first extract structural features from the words contained in the amounts vocabulary. Then, we build a symbolic knowledge base that reflects a classification of words according to their features. In a third step, we use a translation algorithm (from rules to neural network) to determine the neural network architecture and to initialize its connections with specific values rather than random values, as is the case in classical neural networks. This
Hybrid approaches to neural networkbased language processing
, 1997
"... In this paper we outline hybrid approaches to arti cial neural networkbased natural language processing. We start by motivating hybrid symbolic/connectionist processing. Then we suggest various types of symbolic/connectionist integration for language processing: connectionist structure architecture ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
In this paper we outline hybrid approaches to arti cial neural networkbased natural language processing. We start by motivating hybrid symbolic/connectionist processing. Then we suggest various types of symbolic/connectionist integration for language processing: connectionist structure architectures, hybrid transfer architectures, hybrid processing architectures. Furthermore, we focus particularly on loosely coupled, tightly coupled, and fully integrated hybrid processing architectures. We give particular examples of these hybrid processing architectures and argue that the hybrid approach to arti cial neural networkbased language processing has a lot of potential to overcome the gap between a neural level and a symbolic conceptual level. ii 1 Motivation for hybrid symbolic/connectionist processing In recent years, the eld of hybrid symbolic/connectionist processing has seen a remarkable