id: 01929172
dt: a
an: 01929172
au: Tung, W.L.; Quek, C.
ti: BackPOLE: Back propagation based on objective learning errors.
so: Ishizuka, Mitsuru (ed.) et al., PRICAI 2002: Trends in artificial
    intelligence. 7th Pacific Rim international conference on artificial
    intelligence, Tokyo, Japan, August 18-22, 2002. Proceedings. Berlin:
    Springer. Lect. Notes Comput. Sci. 2417, 265-274 (2002).
py: 2002
pu: Berlin: Springer
la: EN
cc: I.2.6
ut: 
ci: 
li: http://link.springer.de/link/service/series/0558/bibs/2417/24170265.htm
ab: Summary: A new variant of the back propagation (BP) algorithm is proposed
    in this paper. The BP algorithm is widely used to tune the parameters
    of multi-layered neural networks and hybrid neural fuzzy systems. Most
    applications of the BP algorithm are based on the negative gradient
    descent approach (NGD-BP). However, NGD-BP may not be suitable for use
    in neural fuzzy systems due to the poor interpretations of its error
    signals and over-reliance on prior knowledge of the node functions
    (i.e. the aggregation and activation functions of individual nodes). In
    neural fuzzy systems such as the POPFNN, the node functions are defined
    by the inference scheme adopted. This results in the NGD-BP algorithm
    being overly dependent on the gradient definition defined by the
    inference engine. That is, a set of customized learning equations is
    required for a given inference scheme. Hence, a change of the inference
    scheme requires a re-computation of the back propagation learning
    equations. This makes the neural fuzzy structure and learning highly
    dependent on the type of fuzzy inference engine employed. In contrast,
    the proposed BackPOLE algorithm generates intuitive error signals using
    a set of pre-defined objectives and is resilient to the change of
    inference schemes. This is highly desirable since the
    parameter-learning phase of neural fuzzy systems can then be
    generalized and be independent of the fuzzy inference scheme. The
    BackPOLE algorithm has been implemented in a new neural fuzzy
    architecture named GenSoFNN to demonstrate its effectiveness.
rv: