Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567001657> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W1567001657 endingPage "286" @default.
- W1567001657 startingPage "278" @default.
- W1567001657 abstract "Teaching problem-solving through exercises is a widely used pedagogic technique. A human teacher selects certain problems and orders them according to their level of difficulty to form a sequence of exercises. A student starts by solving simple problems first; then, attempts harder problems applying the knowledge gained from solving the earlier problems; and then still harder problems, and so on. Machine learning of problem solving using exercises, apart from following this pedagogic tradition, offers a compromise between supervised speedup learning and unsupervised speedup learning. Supervised speedup learning, although more efficient than the latter, places the burden of providing the solutions to the training problems on the teacher-mostly a human. Unsupervised speedup learning, in contrast, expects the learner to solve the training problems, while unburdening the teacher. However, this is computationally hard for the learner for it lacks control knowledge and, hence, its only recourse is brute-force search. In exercises approach, teacher has the task of providing an exercise set-a sequence of problems ordered by difficulty. The learner has to solve the exercise problems using the bootstrapping method akin to the above-described method followed by a human student. Previously, Natarajan (1989) used exercises approach in speedup learning for learning control rules represented in the form of tree patterns. In this work, we use exercises approach for learning first-order recursive goal-decomposition rules (d-rules). A d-rule is a 3-tuple (g, c, sg) that decomposes a goal g into a sequence of subgoals sg, provided the condition c holds. The input to the system is a sequence of exercises ordered according to their difficulty levels. The difficulty levels correspond to goal-subgoal hierarchies except in the case of recursion-where the number of recursive calls is also used to set the difficulty level of a goal. This approach follows two main steps: For each exercise, (1) exercise-solver solves the exercise by searching in the space of operators and previously learned drules, and outputs the solution (the plan) and the subgoals used; and (2) first-order inductive learner forms a hypothesis d-rule using the initial state as the d-rule" @default.
- W1567001657 created "2016-06-24" @default.
- W1567001657 creator A5014260664 @default.
- W1567001657 creator A5063973068 @default.
- W1567001657 date "1997-07-08" @default.
- W1567001657 modified "2023-09-29" @default.
- W1567001657 title "Learning Goal-Decomposition Rules using Exercises" @default.
- W1567001657 cites W168407115 @default.
- W1567001657 cites W2115005659 @default.
- W1567001657 cites W2150470619 @default.
- W1567001657 cites W2180885055 @default.
- W1567001657 cites W3013459749 @default.
- W1567001657 hasPublicationYear "1997" @default.
- W1567001657 type Work @default.
- W1567001657 sameAs 1567001657 @default.
- W1567001657 citedByCount "22" @default.
- W1567001657 countsByYear W15670016572012 @default.
- W1567001657 countsByYear W15670016572019 @default.
- W1567001657 crossrefType "proceedings-article" @default.
- W1567001657 hasAuthorship W1567001657A5014260664 @default.
- W1567001657 hasAuthorship W1567001657A5063973068 @default.
- W1567001657 hasConcept C111919701 @default.
- W1567001657 hasConcept C118615104 @default.
- W1567001657 hasConcept C118930307 @default.
- W1567001657 hasConcept C119857082 @default.
- W1567001657 hasConcept C154945302 @default.
- W1567001657 hasConcept C162324750 @default.
- W1567001657 hasConcept C177264268 @default.
- W1567001657 hasConcept C187736073 @default.
- W1567001657 hasConcept C199360897 @default.
- W1567001657 hasConcept C2778112365 @default.
- W1567001657 hasConcept C2780451532 @default.
- W1567001657 hasConcept C33923547 @default.
- W1567001657 hasConcept C41008148 @default.
- W1567001657 hasConcept C54355233 @default.
- W1567001657 hasConcept C68339613 @default.
- W1567001657 hasConcept C8038995 @default.
- W1567001657 hasConcept C86803240 @default.
- W1567001657 hasConceptScore W1567001657C111919701 @default.
- W1567001657 hasConceptScore W1567001657C118615104 @default.
- W1567001657 hasConceptScore W1567001657C118930307 @default.
- W1567001657 hasConceptScore W1567001657C119857082 @default.
- W1567001657 hasConceptScore W1567001657C154945302 @default.
- W1567001657 hasConceptScore W1567001657C162324750 @default.
- W1567001657 hasConceptScore W1567001657C177264268 @default.
- W1567001657 hasConceptScore W1567001657C187736073 @default.
- W1567001657 hasConceptScore W1567001657C199360897 @default.
- W1567001657 hasConceptScore W1567001657C2778112365 @default.
- W1567001657 hasConceptScore W1567001657C2780451532 @default.
- W1567001657 hasConceptScore W1567001657C33923547 @default.
- W1567001657 hasConceptScore W1567001657C41008148 @default.
- W1567001657 hasConceptScore W1567001657C54355233 @default.
- W1567001657 hasConceptScore W1567001657C68339613 @default.
- W1567001657 hasConceptScore W1567001657C8038995 @default.
- W1567001657 hasConceptScore W1567001657C86803240 @default.
- W1567001657 hasLocation W15670016571 @default.
- W1567001657 hasOpenAccess W1567001657 @default.
- W1567001657 hasPrimaryLocation W15670016571 @default.
- W1567001657 hasRelatedWork W11088338 @default.
- W1567001657 hasRelatedWork W1489183362 @default.
- W1567001657 hasRelatedWork W1509999309 @default.
- W1567001657 hasRelatedWork W1545688112 @default.
- W1567001657 hasRelatedWork W1567972407 @default.
- W1567001657 hasRelatedWork W167923453 @default.
- W1567001657 hasRelatedWork W1868639127 @default.
- W1567001657 hasRelatedWork W1966028617 @default.
- W1567001657 hasRelatedWork W1967346767 @default.
- W1567001657 hasRelatedWork W1981446214 @default.
- W1567001657 hasRelatedWork W2020149918 @default.
- W1567001657 hasRelatedWork W2035078485 @default.
- W1567001657 hasRelatedWork W2100988719 @default.
- W1567001657 hasRelatedWork W2115005659 @default.
- W1567001657 hasRelatedWork W2122048287 @default.
- W1567001657 hasRelatedWork W2128361632 @default.
- W1567001657 hasRelatedWork W2147357263 @default.
- W1567001657 hasRelatedWork W2160841629 @default.
- W1567001657 hasRelatedWork W2162227979 @default.
- W1567001657 hasRelatedWork W2399950914 @default.
- W1567001657 isParatext "false" @default.
- W1567001657 isRetracted "false" @default.
- W1567001657 magId "1567001657" @default.
- W1567001657 workType "article" @default.