Adaptation-Guided Case Base Maintenance
Authors: Vahid Jalali, David Leake
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In comparisons of AGCBM to five alternative methods in four domains, for varying case base densities, AGCBM outperformed the alternatives in all domains, with greatest benefit at high compression. |
| Researcher Affiliation | Academia | Vahid Jalali and David Leake School of Informatics and Computing, Indiana University Informatics West, 901 E. 10th Street Bloomington, Indiana 47408, USA |
| Pseudocode | Yes | Alg. 1 summarizes the AGCBM algorithm, where Next, AGCBMRanking ,and Find Centroids respectively denote functions for accessing the next element of an ordered list, for ordering cases based on their competence calculated by Eq. 3, and for finding cases closest to the centroids of the case base. Value(c) is the solution value associated with case c, and Find Sol(c) is the CBR procedure used to generate the solution. Algorithm 2 Algorithm for value estimation (CAAR) Input: Q: input query n: number of source cases to adapt to solve query r: number of rules to be applied per source case CB: case base Output: Estimated solution value for Q |
| Open Source Code | No | The paper does not provide any explicit links or statements about the release of source code for the described methodology. |
| Open Datasets | Yes | We evaluated AGCBM1 s performance on four sample domains from the UCI repository (Frank and Asuncion 2010): Automobile (Auto), Auto MPG (MPG), Housing, and Computer Hardware (Hardware). For all data sets, records with unknown values were removed. |
| Dataset Splits | Yes | Ten fold cross validation is used for all experiments, and all methods parameters are tuned by using hill climbing on the training data. |
| Hardware Specification | No | The paper does not specify the hardware used for running experiments, such as CPU or GPU models, memory, or specific computing environments. |
| Software Dependencies | No | The paper does not provide specific software dependencies or their version numbers used in the experiments. |
| Experiment Setup | Yes | The parameters to tune for AGCBM1 are the number of source cases to use and the number of adaptations to apply per source case for estimating the case values, and α from Eq. 3. The size limit used in the CNN process was set based on the desired reduction in the training set size. |