Skip to yearly menu bar Skip to main content


Poster

Attentional Neural Network: Feature Selection Using Cognitive Feedback

Qian Wang · Jiaxing Zhang · Sen Song · Zheng Zhang

Level 2, room 210D

Abstract:

Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult 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.

Live content is unavailable. Log in and register to view live content