当前位置: X-MOL 学术IEEE Trans. Syst. Man Cybern. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Real-Time Recurrent Tactile Recognition: Momentum Batch-Sequential Echo State Networks
IEEE Transactions on Systems, Man, and Cybernetics: Systems ( IF 8.6 ) Pub Date : 2020-04-01 , DOI: 10.1109/tsmc.2017.2746565
Lele Cao , Fuchun Sun , Ramamohanarao Kotagiri , Wenbing Huang , Weihao Cheng , Xiaolong Liu

Tactile recognition aims at identifying target objects according to tactile sensory readings. Tactile data have two salient properties: 1) sequentially real-time and 2) temporally correlated, which essentially calls for a real-time (i.e., online fixed-budget) and recurrent recognition procedure. Based on an efficient and robust spatio-temporal feature representation for tactile sequences, we handle the problem of real-time recurrent tactile recognition by proposing a bounded online-sequential learning framework, and incorporates the strength of batch-regularization bootstrapping, bounded recursive reservoir, and momentum-based estimation. Experimental evaluations show that it outperforms the state-of-the-art methods by a large margin on test accuracy; and its training performance is superior to most compared models from aspects of average online training error, computational complexity, and storage efficiency.

中文翻译:

实时循环触觉识别:Momentum Batch-Sequential Echo State Networks

触觉识别旨在根据触觉感官读数识别目标物体。触觉数据具有两个显着特性:1) 顺序实时和 2) 时间相关,这本质上需要实时(即在线固定预算)和循环识别过程。基于触觉序列的有效且稳健的时空特征表示,我们通过提出有界在线序列学习框架来处理实时循环触觉识别问题,并结合批量正则化自举、有界递归库的优势,和基于动量的估计。实验评估表明,它在测试精度上大大优于最先进的方法;
更新日期:2020-04-01
down
wechat
bug