On Very Large Scale Hamiltonian Neural Nets
This paper presents how to design very large scale lossless neural nets (LONN), which can be used as Walsh-spectrum analyzer. This analysis relies on the orthogonality of weight matrix W where W is Hurwitz-Radon matrix. The unique feature of the LONN is the possibility to treat them either as algorithms or as Hamiltonian physical objects (Walsh Transformation Processors).
KeywordsHamiltonian System Weight Matrix Hamiltonian Function Walsh Spectrum Compatible Connection
Unable to display preview. Download preview PDF.
- Sienko W., Zurada J. (1990) Neural Signal-Flow Networks. Proc. of Neuronet’90. Conf., Prague, Czechoslovakia.Google Scholar
- Sienko W., Zurada J. (1991) Pseudopassive Neural Networks. Proc. IEEE ISCAS 1991, Singapore, p. 2495.Google Scholar
- Sienko W., Luksza A, Citko W. (1993) On Properties of Passive Neural Networks. Scientific Journal of Gdynia Maritime Academy, No. 25, p. 5, Gdynia.Google Scholar
- Sienko W. (2001) On Modeling the Quantum and Anticipatory Systems by Passive Neural Nets, International Journal of Computing Anticipatory Systems Edited by D. M. Dubois, Vol. 10, p. 218, CHAOS, Liege, Belgium.Google Scholar
- Roychowdhury V., Kai-Yeung Siu, Orlitsky A. (1994) Neural Models and Spectral Methods, in Theoretical Advances in Neural Computing and Learning. p. 3, Kluwer Academic Publishers Boston, London, Dordrecht.Google Scholar
- Mansour Y. (1994) Learning Boolean Functions via the Fourier Transform. in Theoretical Advances in Neural Computing and Learning. p. 391, Kluwer Academic Publishers Boston, London, Dordrecht.Google Scholar
- Ventura D., Martinez T. A Quantum Computational Learning Algorithm. quantph/9807052 18 July 1998.Google Scholar