✦ LIBER ✦

On the complexity of approximating mappings using feedforward networks

✍ Scribed by Pascal Koiran

Publisher: Elsevier Science
Year: 1993
Tongue: English
Weight: 359 KB
Volume: 6
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(05)80108-x

No coin nor oath required. For personal study only.

✦ Synopsis

I4~, study the approximation o.f continuous mappings and dichotomies by one-hidden-layer networks from a computational point of view Our approach is based on a new approximation method specially designed for constructing "small networks. We give upper bounds on the size o.f these networks.

📜 SIMILAR VOLUMES

On learning the derivatives of an unknow

On learning the derivatives of an unknown mapping with multilayer feedforward networks

✍ A. Ronald Gallant; Halbert White 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 673 KB

The complexity of approximating MAPs for

The complexity of approximating MAPs for belief networks with bounded probabilities

✍ Ashraf M. Abdelbar; Stephen T. Hedetniemi; Sandra M. Hedetniemi 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 69 KB

Probabilistic inference and maximum a posteriori (MAP) explanation are two important and related problems on Bayesian belief networks. Both problems are known to be NP-hard for both approximation and exact solution. In 1997, Dagum and Luby showed that efficiently approximating probabilistic inferenc

On the complexity of approximating the V

On the complexity of approximating the VC dimension

✍ Elchanan Mossel; Christopher Umans 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 181 KB

We study the complexity of approximating the VC dimension of a collection of sets, when the sets are encoded succinctly by a small circuit. We show that this problem is: 3 -hard to approximate to within a factor 2 À e for all e > 0; \* approximable in AM to within a factor 2; and \* AM-hard to appr

The errors of approximation for feedforw

The errors of approximation for feedforward neural networks in the metric

✍ Feilong Cao; Rui Zhang 📂 Article 📅 2009 🏛 Elsevier Science 🌐 English ⚖ 564 KB

On the Complexity of Approximating Extre

On the Complexity of Approximating Extremal Determinants in Matrices

✍ L. Khachiyan 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 525 KB

On the approximate realization of contin

On the approximate realization of continuous mappings by neural networks

✍ Ken-Ichi Funahashi 📂 Article 📅 1989 🏛 Elsevier Science 🌐 English ⚖ 733 KB

In this paper, we prove that any continuous mapping can be approximately realized by Rumelhart-Hinton-Williams' multilayer neural networks with at least one hidden layer whose output functions are sigmoid functions. The starting point of the proof for the one hidden layer case is an integral formula