Image Classification with the Fisher Vector: Theory and Practice
International Journal of Computer Vision
| Hi-index | 0.00 |
The derivation of a supervised training algorithm for a neural network implies the selection of a norm criterion which gives a suitable global measure of the particular distribution of errors. The author addresses this problem and proposes a correspondence between error distribution at the output of a layered feedforward neural network and Lp norms. The generalized delta rule is investigated in order to verify how its structure can be modified in order to perform a minimization in the generic Lp norm. The particular case of the Chebyshev norm is developed and tested