A probabilistic neural network hardware system using a learning-parameter parallel architecture

A novel PNN (Probabilistic Neural Networks) hardware architecture called 'Sigma Parallel Architecture' (SPA) is proposed. Different values of the network parameter are calculated in parallel in the SPA and it speeds up the PNN learning as well as recognition overcoming the difficulty in the VLSI implementation. The hardware prototype is developed using FPGA chips and it shows a high speed leaning of about 10 seconds that satisfies the requirements in the real world image recognition tasks.

[1]  Mahmood R. Azimi-Sadjadi,et al.  Comparison of two different PNN training approaches for satellite cloud data classification , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[2]  Mahmood R. Azimi-Sadjadi,et al.  Temporal updating scheme for probabilistic neural network with application to satellite cloud classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  Donald F. Specht,et al.  Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification , 1990, IEEE Trans. Neural Networks.

[4]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[5]  A. Zaknich,et al.  A design for FPGA implementation of the probabilistic neural network , 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

[6]  Wee Ser,et al.  Probabilistic neural-network structure determination for pattern classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[7]  Mahmood R. Azimi-Sadjadi,et al.  Comparison of two different PNN training approaches for satellite cloud data classification , 2001, IEEE Trans. Neural Networks.