Neurons, N-tuples and faces
Enthusiasm for neural computing seems, at present, to know no bounds. Neural networks are powerful pattern classifiers that are normally thought to require custom VLSI devices in order to obtain the advantages of their inherent parallelism. By exploiting N-tuple techniques, the real-time application of such networks is possible, using conventional computers, for such tasks as recognising and locating facial features.
- T. Kohonen . (1989) , Self-organisation and associative memory.
- Bledsoe, W.W., Browning, I.: Proc. Eastern Joint Computer Conference, 1959, p. 225–232.
- P. Kanerva . (1988) , Sparse distributed memory.
- I. Aleksander . (1985) , Advanced digital information systems.
- M.J. Johnson , N.M. Allinson , K.J. Moon , D.S. Touretzky . (1989) , Advances in neural information processing systems.
- N.M. Allinson , M.J. Johnson , J.G. Taylor , C.L.T. Mannion . (1989) , New developments in neural computing.
- A.J. Luckman , N.M. Allinson . (1990) Proc. SPIE.