✦ LIBER ✦

Approximating Hyper-Rectangles: Learning and Pseudorandom Sets

✍ Scribed by Peter Auer; Philip M Long; Aravind Srinivasan

Book ID: 102585863
Publisher: Elsevier Science
Year: 1998
Tongue: English
Weight: 458 KB
Volume: 57
Category: Article
ISSN: 0022-0000
DOI: 10.1006/jcss.1998.1593

No coin nor oath required. For personal study only.

✦ Synopsis

The PAC learning of rectangles has been studied because they have been found experimentally to yield excellent hypotheses for several applied learning problems. Also, pseudorandom sets for rectangles have been actively studied recently because (i) they are a subproblem common to the derandomization of depth-2 (DNF) circuits and derandomizing randomized logspace, and (ii) they approximate the distribution of n independent multivalued random variables. We present improved upper bounds for a class of such problems of ``approximating'' high-dimensional rectangles that arise in PAC learning and pseudorandomness.

📜 SIMILAR VOLUMES

The exemplar-aided constructor of hyper-

The exemplar-aided constructor of hyper-rectangles learning algorithm for stream flow estimation

✍ Fi-John Chang; Hui-Fen Lin 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 171 KB

The exemplar-aided constructor of hyper-rectangles (EACH) model which simulates human intelligence by learning from experience and adjusting in time, proposed by Salzberb (1991), is presented and modi®ed to strengthen its performance in variable stream ¯ow extension. The modi®cation is intended to r