Name
Abstract | ||
|---|---|---|
How to determine a priori whether a learning algorithm is suited to a learning problem instance is a major scientific and technological challenge. A first step toward this goal, inspired by the Phase Transition (PT) paradigm developed in the Constraint Satisfaction domain, is presented in this paper.Based on the PT paradigm, extensive and principled experiments allow for constructing the Competence Map associated to a learning algorithm, describing the regions where this algorithm on average fails or succeeds. The approach is illustrated on the long and widely used C4.5 algorithm. A non trivial failure region in the landscape of k-term DNF languages is observed and some interpretations are offered for the experimental results. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1145/1015330.1015398 | ICML |
Keywords | Field | DocType |
constraint satisfaction domain,pt paradigm,technological challenge,competence map,problem instance,principled experiment,k-term dnf language,non trivial failure region,phase transition-inspired approach,phase transition,constraint satisfaction | Constraint satisfaction,Stability (learning theory),Phase transition,Computer science,A priori and a posteriori,Wake-sleep algorithm,Artificial intelligence,Generalization error,Difference-map algorithm,Machine learning | Conference |
ISBN | Citations | PageRank |
1-58113-838-5 | 5 | 0.40 |
References | Authors | |
16 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nicolas Baskiotis | 1 | 119 | 11.73 |
| Michèle Sebag | 2 | 1547 | 138.94 |