๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Design of function-generating mapping networks by interactive neural-network simulation

โœ Scribed by Granino A. Korn

Publisher
Elsevier Science
Year
1991
Tongue
English
Weight
812 KB
Volume
33
Category
Article
ISSN
0378-4754

No coin nor oath required. For personal study only.

โœฆ Synopsis

We apply a new interactive simulation environment for neural-network development to the development of mapping networks, which produce learned or preset functions of real inputs. Function-mapping networks are useful for adaptive control and as general-purpose, self-learning function generators. DESIRE/NEUNET describes neural networks in a reasonable matrix language. A built-in, extra-fast compiler lets screen-edited programs execute immediately, without annoying translation delays, and simulations run faster than MicrosoQ FQRTRAN, We simulate a simple backpropagation algorithm for function-table learning and proceed to describe an accurate self-optimizing sum qf limiters ("diode") function generator for functions of one argument.

๐Ÿ“œ SIMILAR VOLUMES

General asymmetric neural networks and s
General asymmetric neural networks and structure design by genetic algorithms
โœ Stefan Bornholdt; Dirk Graudenz ๐Ÿ“‚ Article ๐Ÿ“… 1992 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 666 KB

Abstraet--A learning algorithm for neural networks based on genetic algorithms is proposed. The concept leads in a natural way to a model for the explanation of inherited behavior. Explicitly we study a simplified model for a brain with sensory and motor neurons. We use a general asymmetric network

On the approximate realization of contin
On the approximate realization of continuous mappings by neural networks
โœ Ken-Ichi Funahashi ๐Ÿ“‚ Article ๐Ÿ“… 1989 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 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