✦ LIBER ✦

A convergent generator of neural networks

✍ Scribed by Pierre Courrieu

Publisher: Elsevier Science
Year: 1993
Tongue: English
Weight: 822 KB
Volume: 6
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(05)80128-5

No coin nor oath required. For personal study only.

✦ Synopsis

This article presents a new algorithm.[br the automatic generation of neural architectures and supervised learning. Given a set of examples, the algorithm generates an architecture and s),naptic weights that are adapted to the sampled problem. The algorithm supports an), type and amount of numerical input and output. The learning/ generation process is guaranteed to converge in a strictly finite number of steps. 147th the exception of certain a priori nonoptimal architectures, all architectures without internal loops are potentially accessible, and the algorithm tends to generate architectures of minimal complexit); giving it high generalization performance in the learned domain.

📜 SIMILAR VOLUMES

Global exponential convergence for delay

Global exponential convergence for delayed cellular neural networks with a class of general activation functions

✍ Jianying Shao 📂 Article 📅 2009 🏛 Elsevier Science 🌐 English ⚖ 350 KB

Exponential convergence for high-order r

Exponential convergence for high-order recurrent neural networks with a class of general activation functions

✍ Hong Zhang; Wentao Wang; Bing Xiao 📂 Article 📅 2011 🏛 Elsevier Science 🌐 English ⚖ 201 KB

Convergence analysis of general neural n

Convergence analysis of general neural networks under almost periodic stimuli

✍ Zhenkun Huang; S. Mohamad; Xinghua Wang; Chunhua Feng 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 432 KB 👁 1 views

A class of convergent neural network dyn

A class of convergent neural network dynamics

✍ Bernold Fiedler; Tomáš Gedeon 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 340 KB

We consider a class of systems of differential equations in Nn which exhibits convergent dynamics. We find a Lyapunov function and show that every bounded trajectory converges to the set of equilibria. Our result generalizes the results of Cohen and Grossberg (1983) for convergent neural networks. I

Convergence of a self-organizing stochas

Convergence of a self-organizing stochastic neural network

✍ Olivier Francois; Jacques Demongeot; Thierry Herve 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 451 KB

In this paper, we focus on the convergence of a stochastic neural process. In this process, a "physiologically plausible" Hebb's learning rule gives rise to a self-organization phenomenon. Some preliminary results concern the asymptotic behaviour of the nework given that the update of neurons is eit

Development of a generalized neural netw

Development of a generalized neural network

✍ Greger G Andersson; Peter Kaufmann 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 162 KB

The interest for neural networks has grown concomitantly with the increased awareness of the ubiquity of non-linear systems. The main focus on improvements in this field has been on the development of different algorithms that either speed up the convergence rate andror avoid entrapment in local min