Dynamic saliency-driven associative memories based on network potential field

作者：

Highlights：

• A new design framework of AMs is proposed by constructing Network Potential Fields.

• Visual saliency is introduced to AMs by shaping the EBF kernels.

• The AMs with sparse and dynamic synapses are guaranteed to be asymptotically stable.

摘要

Highlights•A new design framework of AMs is proposed by constructing Network Potential Fields.•Visual saliency is introduced to AMs by shaping the EBF kernels.•The AMs with sparse and dynamic synapses are guaranteed to be asymptotically stable.

论文关键词：Associative memory,Recurrent neural network,Visual saliency,Network potential field,Color image retrieval

论文评审过程：Received 26 February 2015, Revised 21 June 2016, Accepted 22 June 2016, Available online 23 June 2016, Version of Record 13 July 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.06.019