A comparison of Kernel methods for instantiating case based reasoning systems

Abstract Instance based reasoning systems and in general case based reasoning systems are normally used in problems for which it is difficult to define rules. Instance based reasoning is the term which tends to be applied to systems where there are a great amount of data (often of a numerical nature). The volume of data in such systems leads to difficulties with respect to case retrieval and matching. This paper presents a comparative study of a group of methods based on Kernels, which attempt to identify only the most significant cases with which to instantiate a case base. Kernels were originally derived in the context of Support Vector Machines which identify the smallest number of data points necessary to solve a particular problem (e.g. regression or classification). We use unsupervised Kernel methods to identify the optimal cases to instantiate a case base. The efficiencies of the Kernel models measured as Mean Absolute Percentage Error are compared on an oceanographic problem.

[1]  A CarpenterGail,et al.  The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network , 1988 .

[2]  John Hunt,et al.  Hybrid case-based reasoning , 1994, The Knowledge Engineering Review.

[3]  Juan M. Corchado,et al.  A hybrid case-based model for forecasting , 2001, Appl. Artif. Intell..

[4]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[5]  Sean Breen,et al.  Developing Industrial Case-Based Reasoning Applications: The INRECA Methodology , 1999 .

[6]  Gunnar Rätsch,et al.  Input space versus feature space in kernel-based methods , 1999, IEEE Trans. Neural Networks.

[7]  Martin I. Sereno,et al.  Proceedings, Thirteenth Annual Conference of the Cognitive Science Society , 1991 .

[8]  Teuvo Kohonen,et al.  In: Self-organising Maps , 1995 .

[9]  Hiroaki Kitano,et al.  Challenges of massive parallelism , 1993, IJCAI 1993.

[10]  Larry R. Medsker,et al.  Hybrid Intelligent Systems , 1995, Springer US.

[11]  Bernhard Schölkopf,et al.  Sparse Kernel Feature Analysis , 2002 .

[12]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[13]  Costas Tsatsoulis,et al.  PANDA: A case-based system to aid novice designers , 1993, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[14]  Frédéric Alexandre,et al.  Connectionist-Symbolic Integration: From Unified to Hybrid Approaches , 1996 .

[15]  David W. Aha,et al.  Learning Representative Exemplars of Concepts: An Initial Case Study , 1987 .

[16]  Ramón López de Mántaras,et al.  Case-Based Reasoning: An Overview , 1997, AI Commun..

[17]  Enric Plaza,et al.  CasedBased Reasoningc an overview , 1997 .

[18]  Corchado RodriÌguez,et al.  Neuro-symbolic model for real-time forecasting problems. , 2000 .

[19]  Juan M. Corchado,et al.  Unsupervised neural method for temperature forecasting , 1999, Artif. Intell. Eng..

[20]  M VelosoManuela,et al.  Derivational Analogy in PRODIGY , 1993 .

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Juan M. Corchado,et al.  Automating the construction of CBR systems using kernel methods , 2001, Int. J. Intell. Syst..

[23]  Ron Sun,et al.  Commonsense reasoning with rules, cases, and connectionist models: A paradigmatic comparison , 1996, Fuzzy Sets Syst..

[24]  Ian D. Watson,et al.  Applying case-based reasoning - techniques for the enterprise systems , 1997 .

[25]  E. R. Bareiss,et al.  PROTOS: An Experiment in Knowledge Acquisition for Heuristic ClassificationTasks , 1986 .

[26]  Jaime G. Carbonell,et al.  Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization , 1993, Machine Learning.

[27]  Juan M. Corchado,et al.  Adaptation of Cases for Case Based Forecasting with Neural Network Support , 2000, Soft Computing in Case Based Reasoning.