Abstract
We propose a new machine-learning algorithm. The approach combines artificial neural network style learning and Petri net style modeling in a single technique. We call this technique tokenized artificial neural networks. We apply the technique on a basic perceptron-type network and present results from experimental investigations as well as a proof for the proposed technique.
Original language | English |
---|---|
Title of host publication | Intelligent Computing Everywhere |
Publisher | Springer London |
Pages | 61-77 |
Number of pages | 17 |
ISBN (Print) | 9781846289422 |
DOIs | |
Publication status | Published - 2007 Dec 1 |
Externally published | Yes |
ASJC Scopus subject areas
- Computer Science(all)