Cognition-Based Deep Learning: Progresses and Perspectives

Abstract

The human brain is composed of multiple modular subsystems, with a unique way interacting among. These subsystems have their own unique characteristics and interact to support cognitive functions such as memory, attention and cognitive control. Nowadays, deep learning methods based on the above-mentioned functions accompanied with knowledge are widely used to design more dynamic, robust and powerful systems. We first review and summarize the progresses of cognition-based deep neural networks, and how cognitive mechanisms can be applied to more brain-like neural networks. Then we propose a general framework for the design of cognition-based deep learning system. Although great efforts have been made in this field, cognition-based deep learning is still in its early age. We put forward the potential directions towards this field, such as associative memory in deep learning, interpretable network with cognitive mechanisms, and deep reinforcement learning based on cognitive science.

Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network

“…Considering the speed of the model, we do not do upsampling, deconvolution and other related operations, but proceed from cognition, hoping to get a more accurate and efficient feature extraction framework. Since memory and attention mechanism is the important parts of cognitive science [14], we use the basic ideas of attention and memory for reference in the construction of the model, and propose a new Recurrent Attentive Neural Network, called RANN.…”