Surrogate losses in passive and active learning
نویسندگان
چکیده
منابع مشابه
Surrogate Losses in Passive and Active Learning
Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a classifier of relatively low risk, as measured under the 0-1 loss, ideally using fewer label requests than the number of random labeled data points sufficie...
متن کاملSurrogate Losses in Passive and Active Learning by Steve Hanneke
Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a classifier of relatively low risk, as measured under the 0-1 loss, ideally using fewer label requests than the number of random labeled data points sufficie...
متن کاملActive and passive contributions to spatial learning.
It seems intuitively obvious that active exploration of a new environment will lead to better spatial learning than will passive exposure. However, the literature on this issue is decidedly mixed-in part, because the concept itself is not well defined. We identify five potential components of active spatial learning and review the evidence regarding their role in the acquisition of landmark, ro...
متن کاملQuagent control via Passive and Active Learning
Artificial intelligence algorithms using passive and active learning versions of direct utility estimation, adaptive dynamic programming and temporal difference approaches to simulate an agent. The explored worlds consisted of discrete states (positions) bounded by internally generated “walls” that included one or more terminal states and a pre determined configuration of rewards for each state...
متن کاملLower Bounds for Passive and Active Learning
We develop unified information-theoretic machinery for deriving lower bounds for passive and active learning schemes. Our bounds involve the so-called Alexander’s capacity function. The supremum of this function has been recently rediscovered by Hanneke in the context of active learning under the name of “disagreement coefficient.” For passive learning, our lower bounds match the upper bounds o...
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: Electronic Journal of Statistics
سال: 2019
ISSN: 1935-7524
DOI: 10.1214/19-ejs1635