S
Shaul Markovitch
Researcher at Technion – Israel Institute of Technology
Publications - 110
Citations - 7668
Shaul Markovitch is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Heuristics & Tree (data structure). The author has an hindex of 32, co-authored 108 publications receiving 7381 citations. Previous affiliations of Shaul Markovitch include University of Michigan & Google.
Papers
More filters
Book ChapterDOI
The role of forgetting in learning
Shaul Markovitch,Paul D. Scott +1 more
TL;DR: An analysis of the economics of learning is carried out and it is argued that knowledge can sometimes have a negative value and research into knowledge acquisition should take seriously the possibility that knowledge may sometimes be harmful.
Proceedings ArticleDOI
Contextual word similarity and estimation from sparse data
TL;DR: A method is presented that makes local analogies between each specific unobserved cooccurrence and other cooccurrences that contain similar words, as determined by an appropriate word similarity metric, and may provide an alternative to class based models.
Proceedings Article
Learning models of intelligent agents
David Carmel,Shaul Markovitch +1 more
TL;DR: A model-based approach is presented as a possible method for learning an effective interactive strategy and an unsupervised algorithm is presented that infers a model of the opponent's automaton from its input/output behavior.
Journal ArticleDOI
Contextual word similarity and estimation from sparse data
TL;DR: The evaluation suggests that this method performs better than existing, frequency-based, smoothing methods, and may provide an alternative to class-based models.
Book ChapterDOI
Learning implicit transfer for person re-identification
TL;DR: The implicit approach models camera transfer by a binary relation R={(x,y)|x and y describe the same person seen from cameras A and B respectively, which implies that the camera transfer function is a multi-valued mapping and not a single-valued transformation.