A connectionist fuzzy case-based reasoning model

Knowledge-Based Systems, 1996

A model to implement the case-based reasoning developed from using a neural net as a base to calculate a measure of similarity between the new problem and each case is presented. It is shown how the neural net provides a mechanism to retrieve cases considering information that in other models needs a parallel architecture. Moreover, in this paper it is analyzed how the model can be employed to create expert networks and case-based planners. ~ 1997 Elsevier Science B.V. All rights reserved.

A hybrid learning system is presented which combines the methodologies of Case Based Reasoning (CBR) and Artificial Neural Networks (ANN) in an agent-oriented architecture and which may learn from past experience and from feedback from the current state of its environment, in order to (i) forecast the state of the environment at some point in the future, and (ii) adapt its behaviour so as to deal with new unexpected situations. The work focuses on Adaptive Agents operating in complex environments in which constraints change in an unpredictable manner, an underlying domain model is not available, but where data on previous states of the environment are accessible. The CBR and ANN methods are used at different stages and with different goals during the learning and forecasting process. The approach is being tested in a practical situation with the aim of developing a methodology for predicting the physical structure, in three dimensions, around a sea going vessel from data acquired in situ and also from historical records.

Indian Journal of Computer Science and Engineering, 8(3), 2017

Case-based Reasoning (CBR) is an Artificial Intelligence (AI) paradigm that attempts to solve new problems based on its past experiences of solving similar problems. Due to the intrinsic similarity of CBR with human reasoning process, it is used for automated problem-solving. The effectiveness of CBR can be enhanced by combining it with other AI techniques. One such approach is the inclusion of fuzzy logic in CBR. This paper surveys the application of fuzzy logic in each of the four phases of CBR. We also present a brief overview on some of the fuzzy-CBR systems developed for a wide range of real world applications.

International Journal of …, 1998

Soft Computing, 2016

Case-based reasoning (CBR) is an artificial intelligent approach to learning and problem-solving, which solves a target problem by relating past similar solved problems. But it faces the challenge of weights assignment to features to measure similarity between cases. There are many methods to overcome this feature weighting problem of CBR. However, neural network's pruning is one of the powerful and useful methods to overcome this feature weighting problem, which extracts feature weights from trained neural network without losing the generality of training set by four popular mechanisms: sensitivity, activity, saliency and relevance. It is habitually assumed that the training sets used for learning are balanced. However, this hypothesis is not always true in real-world applications, and hence, the tendency is to yield classification models that are biased toward the overrepresented class. Therefore, a hybrid CBR system is proposed in this paper to overcome this problem, which adopts a cost-sensitive back-propagation neural network (BPNN) in network pruning to find feature weights. These weights are used in CBR. A single cost parameter is used by the costsensitive BPNN to distinguish the importance of class errors. A balanced decision boundary is generated by the cost parameter using prior information. Thus, the class imbalance problem of network pruning is overcome to improve the accuracy of the hybrid CBR. From the empirical results, it is observed that the performance of the proposed hybrid CBR Communicated by V. Loia.

2000

2000

Various case based systems designed in soft computing paradigms are, first of all, described in brief. This is followed by a detailed description of a fuzzy neural network for selection of cases. The notion of fuzzy similarity is used for selecting the same from both overlapping and non-overlapping regions. The architecture of the network is adaptively determined through growing and pruning of hidden nodes under supervised training. The effectiveness of the cases, thus selected by the network, is demonstrated for pattern classification problem using the INN rule with the cases as the prototypes. Results are presented using real-life data.

Knowledge Engineering …, 2005

The aim of this commentary is to discuss the contribution of soft computing-a consortium of fuzzy logic, neural network theory, evolutionary computing, and probabilistic reasoning-to the development of case-based reasoning (CBR) systems. We will describe how soft computing has been used in case representation, retrieval, adaptation, reuse, and case-base maintenance, and then present a brief summary of six CBR applications that use soft computing techniques.

Journal of Electrical Engineering

Case-based reasoning is a relatively new and promising area of artificial intelligence. In general speaking, case-based reasoning (CBR) is a reasoning method that facilitates knowledge management in which knowledge is a case base acquired by a learning process. Case-based reasoning can be used, for solving problems, in many practical domains such as: mechanical engineering, medicine, business administration etc. Furthermore, for each domain, various task types can be implemented. Some of them are: classification, diagnosis, configuration, planning, decision support etc. The purpose of this paper is to present basic concepts of this promising area. At the beginning, some technical terms of artificial intelligence are introduced. Following this, the foundations of case-based reasoning are presented. At the end, Case Retrieval Netan efficient memory structure for implementation case-based reasoning systems, is described.

1995

This paper presents a new approach for learning general knowledge in a diagnostic case-based system through the use of a neural network. We take advantage of the self-adapting nature of the neural network to discover the most relevant features and combination of features for each diagnosis considered. The knowledge acquired by the network is interpreted and mapped into symbolic diagnosis descriptors, which are kept and used by the case-based system to guide its reasoning process, to retrieve cases from a case library and to build explanations. The neural network used in the learning process was the Combinatorial Neural Model, a network that has been combined with other symbolic approaches previously. The paper presents the method used to interpret the knowledge learned in the neural network, as well as the guidelines followed by the reasoning process of the CBR system. An initial experiment in clinical psychology is also reported, where the case-based model introduced here was used to learn and represent the psychological pro le of patients in evaluation for heart transplant.