Training methodology of the Back Propagation Network (BPN) is well documented. One aspect of BPN that requires investigation is whether or not the BPN would get trained for a given training data set and architecture. In this paper the behavior of the BPN is analyzed during its training phase considering convergent and divergent training data sets. Evolution of the weights during the training phase was monitored for the purpose of analysis. The evolution of weights was plotted as return map and was characterized by means of fractal dimension. This fractal dimensional analysis of the weight evolution trajectories is used to provide a new insight to understand the behavior of BPN and dynamics in the evolution of weights.
The electronic absorption spectra of eight substituted acetic acids have been measured at room temperature in several solvents. The ground state dipole moments are evaluated experimentally for these molecules. These ground state values are used in conjunction with the spectral results to evaluate their first electronically excited state dipole moments. For all the molecules investigated here the dipole moments in the excited state are higher than their ground state values.