Learning with infinitely many features
نویسندگان
چکیده
منابع مشابه
Learning with Many Irrelevant Features
In many domains, an appropriate inductive bias is the MIN-FEATURES bias, which prefers consistent hypotheses deenable over as few features as possible. This paper deenes and studies this bias. First, it is shown that any learning algorithm implementing the MIN-FEATURES bias requires (1 ln 1 + 1 2 p + p lnn]) training examples to guarantee PAC-learning a concept having p relevant features out of...
متن کاملLearning with Infinitely Many Kernels via Semi-infinite Programming
In recent years, learning methods are desirable because of their reliability and efficiency in real-world problems. We propose a novel method to find infinitely many kernel combinations for learning problems with the help of infinite and semi-infinite optimization regarding all elements in kernel space. This will provide to study variations of combinations of kernels when considering heterogene...
متن کاملQueues with infinitely many servers
— In the time interval (0, oo) calls arrive in a téléphone exchange in accordance with a récurrent process. There are an unlimited number ofavailable Unes. The holding times are mutually independent and identically distributed positive rondom variables and are independent of the arrivai times. In this paper we détermine the limit distribution of the number of the busy Unes at the arrivai of the...
متن کاملComputing with Infinitely Many Processes
We explore four classic problems in concurrent computing (election, mutual exclusion, consensus, and naming) when the number of processes which may participate is infinite. Partial information about the number of actually participating processes and the concurrency level is shown to affect the possibility and complexity of solving these problems. We survey and generalize work carried out in mod...
متن کاملInfinitely many solutions for a bi-nonlocal equation with sign-changing weight functions
In this paper, we investigate the existence of infinitely many solutions for a bi-nonlocal equation with sign-changing weight functions. We use some natural constraints and the Ljusternik-Schnirelman critical point theory on C1-manifolds, to prove our main results.
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: Machine Learning
سال: 2012
ISSN: 0885-6125,1573-0565
DOI: 10.1007/s10994-012-5324-5