A HIGHER ORDER BAYESIAN NEURAL NETWORK WITH SPIKING UNITS
1996 ◽
Vol 07
(02)
◽
pp. 115-128
◽
Keyword(s):
We treat a Bayesian confidence propagation neural network, primarily in a classifier context. The onelayer version of the network implements a naive Bayesian classifier, which requires the input attributes to be independent. This limitation is overcome by a higher order network. The higher order Bayesian neural network is evaluated on a real world task of diagnosing a telephone exchange computer. By introducing stochastic spiking units, and soft interval coding, it is also possible to handle uncertain as well as continuous valued inputs.
2019 ◽
Vol 1321
◽
pp. 032110
2016 ◽
Vol 29
(1)
◽
pp. 123-132
◽
2008 ◽
Vol 31
(7)
◽
pp. 1101-1111
◽