Complex Preferences for the Integration of Neural Codes

This paper presents a complex preferences framework of integrating pulsed neural networks into neural/symbolic hybrid approaches. In particular, we introduce an interpretation of neural codes as multidimensional complex neural preferences and preference classes which allow the integration of knowledge from dierent neural and symbolic models. We dene some basic operations on complex preferences and preference classes that allow them to be directly integrated into symbolic models. Furthermore, we show the interpretation of mean ring rate, time-to-rst-spike, synchrony and phase codes as complex neural preferences and the interpretation of the operations on preference classes of these codes. To the best of our knowledge this is the rst work that addresses the integration of pulsed neural networks into hybrid approaches, in particular the symbolic interpretation and simultaneous processing of mean ring rate and pulse coding schemes in a preferences framework.

@InProceedings{PW00a, 
 	 author =  {Panchev, Christo and Wermter, Stefan},  
 	 title = {Complex Preferences for the Integration of Neural Codes}, 
 	 booktitle = {Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium},
 	 editors = {},
 	 number = {},
 	 volume = {2},
 	 pages = {253--258},
 	 year = {2000},
 	 month = {Oct},
 	 publisher = {IEEE},
 	 doi = {10.1109/IJCNN.2000.857905}, 
 }