- Abstract: Automatic neural network discovery methods face an enormous challenge caused for the size of the search space. A common practice is to split this space at different levels and to explore only a part of it. Neural architecture search methods look for how to combine a subset of layers, which are the most promising, to create an architecture while keeping a predefined number of filters in each layer. On the other hand, pruning techniques take a well known architecture and look for the appropriate number of filters per layer. In both cases the exploration is made iteratively, training models several times during the search. Inspired by the advantages of the two previous approaches, we proposed a fast option to find models with improved characteristics. We apply a small set of templates, which are considered promising, for make a redistribution of the number of filters in an already existing neural network. When compared to the initial base models, we found that the resulting architectures, trained from scratch, surpass the original accuracy even after been reduced to fit the same amount of resources.
- Keywords: Model reduction, Pruning, filter distribution
- Original Pdf: pdf