Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
- Keyword
-
- COVID-19 (7)
- Computational geometry (6)
- Periodic framework (6)
- Protein rigidity (6)
- Unfolding (6)
-
- Flexibility (5)
- Folding (5)
- Review (5)
- Dilution (4)
- Historical manuscripts (4)
- Image Schemas (4)
- Rigid clusters (4)
- Sexuality (4)
- Simulated unfolding (4)
- Theory (4)
- Vulpes vulpes (4)
- Algorithms (3)
- Auxetic deformation (3)
- Circuit polynomial (3)
- Combinatorial resultant (3)
- Conceptual Dependency (3)
- Conceptual dependency (3)
- Education (3)
- Evaluation (3)
- Gender (3)
- Genus-zero (3)
- Gröbner basis elimination (3)
- High performance computing (3)
- Inductive construction (3)
- Knots (3)
- Publication Year
Articles 361 - 364 of 364
Full-Text Articles in Computer Sciences
Improving Minority Class Prediction Using Case-Specific Feature Weights, Claire Cardie, Nicholas Howe
Improving Minority Class Prediction Using Case-Specific Feature Weights, Claire Cardie, Nicholas Howe
Computer Science: Faculty Publications
This paper addresses the problem of handling skewed class distributions within the case-based learning (CBL) framework. We first present as a baseline an information gain-weighted CBL algorithm and apply it to three data sets from natural language processing (NLP) with skewed class distributions. Although overall performance of the baseline CBL algorithm is good, we show that the algorithm exhibits poor performance on minority class instances. We then present two CBL algorithms designed to improve the performance of minority class predictions. Each variation creates test-case-specific feature weights by first observing the path taken by the test case in a decision tree …
Examining Locally Varying Weights For Nearest Neighbor Algorithms, Nicholas Howe, Claire Cardie
Examining Locally Varying Weights For Nearest Neighbor Algorithms, Nicholas Howe, Claire Cardie
Computer Science: Faculty Publications
Previous work on feature weighting for case-based learning algorithms has tended to use either global weights or weights that vary over extremely local regions of the case space. This paper examines the use of coarsely local weighting schemes, where feature weights are allowed to vary but are identical for groups or clusters of cases. We present a new technique, called class distribution weighting (CDW), that allows weights to vary at the class level. We further extend CDW into a family of related techniques that exhibit varying degrees of locality, from global to local. The class distribution techniques are then applied …
Clusters Of Stars, Ileana Streinu
Clusters Of Stars, Ileana Streinu
Computer Science: Faculty Publications
We solve two open problems posed by Goodman and Pollack[GP84] about sets of signed circular permutations (clusters of stars) arising from generalized configurations of points: recognition and efficient reconstruction (drawing). As a biproduct we get an O(n2) space data structure constructible in O(n2) time, representing the order type of a (generalized) configuration of points and from which the orientation of each triple can be found in constant time, a problem posed in [EHN].
A Pseudo-Algorithmic Separation Of Lines From Pseudo-Lines, William Steiger, Ileana Streinu
A Pseudo-Algorithmic Separation Of Lines From Pseudo-Lines, William Steiger, Ileana Streinu
Computer Science: Faculty Publications
No abstract provided.