Abstract | ||
---|---|---|
First-order learning systems (e.g., FOIL, FOCL, FORTE) generally rely on hill-climbing heuristics in order to avoid the combinatorial explosion inherent in learning first-order concepts. However, hill-climbing leaves these systems vulnerable to local maxima and local plateaus. We present a method, called relational pathfinding, which has proven highly effective in escaping local maxima and crossing local plateaus. We present our algorithm and provide learning results in two domains: family relationships and qualitative model building. |
Year | Venue | Keywords |
---|---|---|
1992 | AAAI | qualitative model building,family relationship,first-order concept,combinatorial explosion,local maximum,relational pathfinding,hill-climbing heuristics,local plateau,first order,hill climbing |
Field | DocType | ISBN |
Pathfinding,Computer science,Model building,Maxima and minima,Heuristics,Artificial intelligence,Combinatorial explosion,Machine learning | Conference | 0-262-51063-4 |
Citations | PageRank | References |
50 | 16.58 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bradley L. Richards | 1 | 209 | 37.47 |
Raymond J. Mooney | 2 | 10408 | 961.10 |