我院先进视觉系统(AVS)研究中心吴思教授课题组荣获ICONIP2018最佳论文奖

来源:AIIT发布日期:2018-12-21

5c1c41c3efe95.png

第25届神经信息处理国际会议(ICONIP 2018)于2018年12月13日至16日在柬埔寨暹粒举行。ICONIP 2018旨在为科学家、工程师和教育工作者提供一个高水平的国际论坛,展示相关领域研究和应用的最新技术,是神经信息处理领域倍受关注的国际会议之一。

5c1c41d8cf0ee.png

此次ICONIP2018会议共收到来自51个国家和地区的575篇投稿文章,我院先进视觉系统(AVS)研究中心吴思教授课题组的论文 "Learning, Storing, and Disentangling Correlated Patterns in Neural Networks" 经评委会公平评选,获得唯一最佳论文奖,论文作者为我院先进视觉系统(AVS)研究中心博士后邹晓龙、吉子龙等。热烈祝贺!

论文题目

Learning, Storing, and Disentangling Correlated Patterns in Neural Networks

论文作者

Xiaolong Zou, Zilong Ji, Xiao Liu, Tiejun Huang, Yuanyuan Mi, Dahui Wang and Si Wu

论文摘要

The brain encodes object relationship using correlated neural representations. Previous studies have revealed that it is a difficult task for neural networks to process correlated memory patterns; thus, strategies based on modified unsupervised Hebb rules have been proposed. Here, we explore a supervised strategy to learn correlated patterns in a recurrent neural network. We consider that a neural network not only learns to reconstruct a memory pattern, but also holds the pattern as an attractor long after the input cue is removed. Adopting backpropagation through time to train the network, we show that the network is able to store correlated patterns, and furthermore, when continuously morphed patterns are presented, the network acquires the structure of a continuous attractor neural network. By inducing spike frequency adaptation in the neural dynamics after training, we further demonstrate that the network has the capacities of anticipative tracking and disentangling superposed patterns. We hope that this study gives us insight into understanding how neural systems process correlated representations for objects.

Link:

https://link.springer.com/chapter/10.1007/978-3-030-04182-3_44

大会网站

https://conference.cs.cityu.edu.hk/iconip/

5c1c41f4bcc1c.png

吴思教授课题组研究方向为计算神经科学和类脑计算,通过和实验神经科学家紧密合作,以数学理论和计算机仿真来构建神经系统的计算模型,解析神经系统处理信息的基本原理,并在此基础上发展类脑智能算法。

先进视觉系统(AVS)研究中心

北京大学信息技术高等研究院先进视觉系统(AVS)研究中心作为北大高文院士团队学术研究成果产业化落地平台,致力于超高清视频采集、处理和编解码以及人工智能相关智能视觉计算等方面的研究;突破4K/8K超高清视频编解码算法、高效视觉特征提取与表示、智能感知视觉计算及高性能芯片等关键技术;研究数字视网膜端到端系统级视频大数据解决方案,提供先进的智能视觉软硬件系统解决方案,为国家标准的产业化落地和大规模产业化应用做出贡献。

打印
返回
关闭