𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Hierarchically structured neural networks: A way to shape a ‘magma’ of neurons

✍ Scribed by Sergio Bittanti; Sergio M. Savaresi

Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
982 KB
Volume
335
Category
Article
ISSN
0016-0032

No coin nor oath required. For personal study only.

✦ Synopsis

In this paper we present a new way of structuring standard classes ~?f NN, so obtaining a new class of parametric ./unctions, which will be named 'HierarchicalO '-Structured-Neural-Networks' ( HSNNs). HSNNs are a special class of networks, constituted h)' two sub-networks: the 'slave' unit and the 'master' unit; the master network is fi'd by a subset of inputs and its outputs are used to 'drire' the parameters (~/'the slave network, whose inputs are di~/oint.fi'om those (?/'the other sub-network. After the general definition of HSNN has been given, two simple classes ~/ HSNNs are presented, and dedicated Back-Propagation algorithms are derived. The HSNNs are a use/ul tool when some prior knowledge (~f the nonlinear .function to he approximated or designed is available; this is illustrated by means of five examples, where a rarietv ~[ simple problems are

📜 SIMILAR VOLUMES

A protein interaction network for the an
A protein interaction network for the analysis of the neuronal differentiation of neural stem cells in response to titanium dioxide nanoparticles
✍ Xiaoyan Liu; Xiufang Ren; Xiaoyong Deng; Yinan Huo; Jiang Xie; Hai Huang; Zheng 📂 Article 📅 2010 🏛 Elsevier Science 🌐 English ⚖ 886 KB

The effects of titanium dioxide (TiO(2)) nanoparticles (NPs) on the differentiation of neural stem cells are reported. Our findings indicate that TiO(2) NPs lead to a differentiational tendency towards neurons from neural stem cells, suggesting TiO(2) NPs might be a beneficial inducer for neuronal d

Reduction of the size of the learning da
Reduction of the size of the learning data in a probabilistic neural network by hierarchical clustering. Application to the discrimination of seeds by artificial vision
✍ Younes Chtioui; Dominique Bertrand; Dominique Barba 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 798 KB

The control of seed batches is necessary before their commercialization. In the present work, we attempted to apply computer vision to this goal. A pattern recognition system formed by a color image analysis device combined with a neural network classifier was tested on a practical problem which con