TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Image Classification	CIFAR-10	Deep Networks with Internal Selective Attention through Feedback Connections	Percentage correct	90.8	# 181

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/deep-networks-with-internal-selective/image-classification-on-cifar-10)](https://paperswithcode.com/sota/image-classification-on-cifar-10?p=deep-networks-with-internal-selective)`

Deep Networks with Internal Selective Attention through Feedback Connections

NeurIPS 2014 · Marijn Stollenga, Jonathan Masci, Faustino Gomez, Juergen Schmidhuber ·

Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNets feedback structure can dynamically alter its convolutional filter sensitivities during classification. It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters. Feedback is trained through direct policy search in a huge million-dimensional parameter space, through scalable natural evolution strategies (SNES). On the CIFAR-10 and CIFAR-100 datasets, dasNet outperforms the previous state-of-the-art model.