Attentional Neural Network: Feature Selection Using Cognitive Feedback

Abstract

Attentional Neural Network is a new framework that integrates top-down cog-nitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or dif-ficult segmentation problems. Our system is modular and extensible. It is also easy to train and cheap to run, and yet can accommodate complex behaviors. We obtain classification accuracy better than or competitive with state of art results on the MNIST variation dataset, and successfully disentangle overlaid digits with high success rates. We view such a general purpose framework as an essential foundation for a larger system emulating the cognitive abilities of the whole brain. 1