MaxiMin Active Learning in Overparameterized Model Classes
نویسندگان
چکیده
منابع مشابه
Is active learning like broccoli? Student perceptions of active learning in large lecture classes
Although research suggests that active learning is associated with positive outcomes (e.g., memory, test performance), use of such techniques can be difficult to implement in large lecture-based classes. In the current study, 1,091 students completed out-of-class group exercises to complement course material in an Introductory Psychology class. Students were assigned either active learning or c...
متن کاملLearning Verb Classes in an Incremental Model
The ability of children to generalize over the linguistic input they receive is key to acquiring productive knowledge of verbs. Such generalizations help children extend their learned knowledge of constructions to a novel verb, and use it appropriately in syntactic patterns previously unobserved for that verb—a key factor in language productivity. Computational models can help shed light on the...
متن کاملAsymptotic Theory of Overparameterized
A theory of overparameterized structural models is presented. In such a model some "redundant" parameters are involved; the parameter vector is not identified, and the information matrix is not nonsingular. The minimum discrepancy function (MDF) test statistic is shown to have an asymptotic chi-squared distribution almost everywhere for a wide class of discrepancy functions. Asymptotic distribu...
متن کاملMaximin affinity learning of image segmentation
Images can be segmented by first using a classifier to predict an affinity graph that reflects the degree to which image pixels must be grouped together and then partitioning the graph to yield a segmentation. Machine learning has been applied to the affinity classifier to produce affinity graphs that are good in the sense of minimizing edge misclassification rates. However, this error measure ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal on Selected Areas in Information Theory
سال: 2020
ISSN: 2641-8770
DOI: 10.1109/jsait.2020.2991518