Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A comparative analysis of neural network performances in astronomical imaging
Applied Numerical Mathematics
Hi-index | 0.01 |
The removal of chromaticity in high precision astrometric measurements is a very important challenge because chromaticity can represent a relevant source of systematic error; we perform this task using a feed forward neural network and focus on the usefulness of a proper preprocessing applied to the network parameters. We use a few statistical moments properly selected with a careful preprocessing and filtering to face the necessity of a good choice of the input parameters that encode images; they are then used as inputs to a feed forward neural network trained by backpropagation to remove chromaticity. We show that a preprocessing devoted to analyze the input-output dependences allows to obtain the same diagnosis performance using as inputs to the neural network less parameters with respect to the diagnosis performed without preprocessing.