Can Neural Networks Recognize Parts?
Abstract
Description
We have demonstrated neural networks can recognize parts by visual images. Input signals are gray scale photographs of objects consisting of some parts and output signals are their shapes. By training neural networks by a few set of images, without any supervision they become to be able to recognize the boundary between parts.
Submitted to J. Phys. Soc. Jpn
Submitted to J. Phys. Soc. Jpn