摘要: … for networks with Clifford valued weight and activation values. This work ceases to be biologically motivated, but it is hoped that by bringing together multidimensional signals into single …
kent.ac.uk
sci-hub.se 参考文章(3)
Ian R. Porteous, Topological Geometry: Frontmatter ,(1981) , 10.1017/CBO9780511623943
Gordon R. Little, Steven C. Gustafson, Robert A. Senn, Generalization of the backpropagation neural network learning algorithm to permit complex weights Applied Optics. ,vol. 29, pp. 1591- 1592 ,(1990) , 10.1364/AO.29.001591
G.M. Georgiou, C. Koutsougeras, Complex domain backpropagation IEEE Transactions on Circuits and Systems Ii: Analog and Digital Signal Processing. ,vol. 39, pp. 330- 334 ,(1992) , 10.1109/82.142037