计算机科学 ›› 2015, Vol. 42 ›› Issue (3): 19-25.doi: 10.11896/j.issn.1002-137X.2015.03.004

• 目次 • 上一篇    下一篇

面向视听跨媒体检索的神经认知计算模型研究

刘 扬,涂春龙,郑逢斌   

  1. 河南大学空间信息处理实验室 开封475004;河南大学环境与规划学院 开封475004;河南大学计算机与信息工程学院 开封475004,浙江大学生物医学工程系 杭州310027,河南大学空间信息处理实验室 开封475004;河南大学计算机与信息工程学院 开封475004
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61305042,8),国防科技工业民用专项科研技术研究项目(2012A03A0939),河南省教育厅科学技术研究重点项目(13A520071)资助

Research of Neural Cognitive Computing Model for Visual and Auditory Cross-media Retrieval

LIU Yang, TU Chun-long and ZHENG Feng-bin   

  • Online:2018-11-14 Published:2018-11-14

摘要: 跨媒体语义映射和跨媒体语义检索是跨媒体搜索引擎的核心技术问题。对视听神经认知的功能、层次和结构进行了分析,借鉴深度信念网络和时空层次记忆模型的设计思想,建立了一种仿脑的面向视听跨媒体应用的神经认知计算模型。依据神经系统的信息处理机制和认知理论的功能架构来设计可计算模型,系统地讨论了皮层柱的视听信息整合机制和协同认知的处理流程。本模型可为解决跨媒体语义映射和跨媒体语义检索的相关应用提供借鉴和参考,对实现非冯·诺依曼结构的仿脑认知计算进行了一次有意义的探索。

关键词: 媒体神经认知计算,跨媒体语义检索,跨媒体语义映射,认知计算,仿脑计算

Abstract: Cross-media semantic mapping and cross-media semantic retrieval are key problems of the search engine.In this paper,we analyzed the functionality,the hierarchy and the structure of the brain’s neurocognitive,and established a in-like neural cognitive computing model for visual and auditory cross-media application after taking into account the idea of deep belief network and hierarchical temporal memory.According to the mechanism of information processing in central nervous system and framework of functional approach in cognitive theories,we designed computational model,and discussed systematically information integration mechanism in cortical column and cooperative cognitive processing of visual and auditory.This model provides a reference to resolve application of cross-media semantic mapping and retrieval,and is significant exploration for brain-like cognitive computation of non-von Neumann structure.

Key words: Multimedia neural cognitive computing,Cross-media semantic retrieval,Cross-media semantic mapping,Cognitive computing,Brain-like computing

[1] Wang Ying-xu.On cognitive informatics[J].Brain and Mind,2003,4(2):151-167
[2] Dharmendra S.Modha,Rajagopal Ananthanarayanan,et al.Cognitive Computing[J].Communications of the ACM,2011,54(8):62-71
[3] Fukushima K.Neocognitron trained with winner-kill-loser rule[J].Neural Networks,2010,23(7):926-938
[4] Hinton G E,Osindero S,Teh Y W.A fast learning algorithm fordeep belief nets[J].Neural Computation,2006,8(7):1527-1554
[5] Arel I,Rose D C,et al.Deep Machine Learning-A New Frontier in Artificial Intelligence Research[J].Computational Intelligence Magazine,IEEE,2010,5(4):13-18
[6] Dahl G,Yu D,Deng L,et al.Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(1):30-42
[7] Le Q,Ranzato M,Monga R,et al.Building high-level featuresusing large scale unsupervised learning[C]∥The 29th International Conference on Machine Learning (ICML),2012.Edinburgh,2012:81-88
[8] Modha D S,Singh R.Network architecture of the long-distance pathways in the macaque brain[J].Proceedings of the National Academy of Sciences,2010,107(30):13485-13490
[9] Hagmann P,Cammoun L,et al.Mapping the Structural Core of Human Cerebral Cortex[J].PLOS Biology,2008,6(7):1479-1493
[10] Preissl R,Wong T M,et al.Compass:A scalable simulator for an architecture for Cognitive Computing[C]∥High Perfor-mance Computing,Networking,Storage and Analysis (SC) 2012.Almaden,San Jose,CA,USA,2012:1-11
[11] Eliasmith C,Stewart T C,et al.A large-scale model of the functioning brain[J].Science,2012,338(6111):1202-1205
[12] George D,Hawkins J.Towards a Mathematical Theory of Cortical Micro-circuits[J].PLoS computational biology,2009,5(10):1-26
[13] Jaros R G,George D.Hierarchical temporal memory systemwith enhanced inference capability[J].Google Patents,2012(7)
[14] 姚宏亮,王秀芳,王浩.一种基于结构分解和因子分析的贝叶斯网络隐变量发现算法[J].计算机科学,2012,9(2):244-249
[15] Liu Lu,Zhu Fei-da,Zhang Lei,et al.A probabilistic graphicalmodel for topic and preference discovery on social media[J].Neurocomputing,2012,95:78-88
[16] Frey B J,Jojic,Nebojsa.A comparison of algorithms for infe-rence and learning in probabilistic graphical models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,7(9):1392-1416
[17] Ngiam Ji-quan,Khosla A,et al.Multimodal deep learning[C]∥Proceedings of the 28th International Conference on Machine Learning (ICML-11),2011.Bellevue:ACM,2011:689-696
[18] Srivastava N,Salakhutdinov R.Multimodal learning with deepBoltzmann machines[C]∥Advances in Neural Information Processing Systems 25:26th Annual Conference on Neural Information Processing Systems(NIPS),2012.Lake Tahoe:Curran Associates,2012:2231-2239
[19] Blei D M.Probabilistic topic models[J].Communications of the ACM,2012,55(4):77-84
[20] 李志欣,施智平,李志清,等.融合语义主题的图像自动标注[J].软件学报,2011,2(4):801-812
[21] Modha D S,Singh R.Network architecture of the long-distance pathways in the macaque brain[J].Proceedings of the National Academy of Sciences of the United States of America,2010,USA,2010,107(30):13485-13490
[22] Joseph R.Neuropsychiatry,Neuropsychology,Clinical Neuro-science[M/OL].http://brainmind.com/BrainOverview.html,2000

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!