Sine Net

Sine Net (International Patent)

Sine Net (SN) is characterized by the presence of a specific double non-linear relationship on the connections between nodes. This characteristic has some evident consequences on the properties of this network both on the computed function and on the behaviour of this network during the learning phase.

The basic idea in the SN processing is to provide each node with receivers interposed between each input and the summation.

Fig. 1 – Conceptual processing in classical Sine Net networks

The receivers appropriately transforms in a non linear way the input from each input node, before summing the input contributes into a value to be filtered through a non linear function. The meaning of the receivers is the introduction of a quanti-qualitative process on the input value, in substitution of a merely quantitative process on it, in analogy to what is done in biological organisms by chemical ports with respect to potential ports. The qualitative aspects of transformation are obtained by using sinusoidal functions. For each i-th coordinate of the input space, this allows the introduction of a dependency of each i-th transformed value by the spatial position of the coordinate value with respect a spatial wave of given wavelength. Input coordinate values, multiplied by the wavelength, are then transformed into the same value. The wavelength on each input receiver is tuned during the learning phase.

References

[1]  P.M. Buscema, S. Terzi, M. Breda
A feed forward sine based neural network for functional approximation of a waste incinerator emissions
Proceedings of the 8th WSEAS Int. Conference on Automatic Control,  Modeling and Simulation , Praga, March 12 th -14 th, 2006.

[2] PM. Buscema, S. Terzi, M. Breda
Using Sinusoidal Modulated Weights Improve Feed-Forward Neural Network Performances
in Classification and Functional Approximation Problems, , in WSEAS Transactions on Information Science & Applications, Issue 5, vol. 3, May 2006 pp. 885-893.

Patent
Sine Net : AN ARTIFICIAL NEURAL NETWORK. Applicant Semeion Research Centre. Inventor P.M. Buscema.
European Patent(Application n. 03425582.8 deposited 09-09-2003). USA Patent No US 7,788,196 B2 – Aug.31,2010.
International Patent: Application PCT/EP2004/05189 deposited 08-28-2004.