2 Hits in 2.8 sec

DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution [article]

Hongfeng You, Long Yu, Shengwei Tian, Xiang Ma, Yan Xing, Xiaojie Ma
2020 arXiv   pre-print
In the feature mining and feature fusion stage, we construct a multi-directional integrated convolution (MDIC).  ...  To solve the above problems, in this paper, we propose a novel end-to-end semantic segmentation algorithm, DT-Net, and use two new convolution strategies to better achieve end-to-end semantic segmentation  ...  ACKNOWLEDGMENT The authors wish to thank A, B, C. This work was supported in part by a grant from XYZ.  ... 
arXiv:2009.12569v1 fatcat:lc57eytvvne3zhjoh6wca7jqt4

Deep Predictive Learning: A Comprehensive Model of Three Visual Streams [article]

Randall C. O'Reilly, Dean R. Wyatte, John Rohrlich
2017 arXiv   pre-print
Learning is based on making predictions about what the senses will report at 100 msec (alpha frequency) intervals, and adapting synaptic weights to improve prediction accuracy.  ...  We present a comprehensive framework spanning biological, computational, and cognitive levels, with a clear theoretical continuity between levels, providing a coherent answer directly supported by extensive  ...  , that only sends changes (deltas) in activation values -typically only a few percent of neurons send on any given cycle. net += dt.integ * dt * (net raw -net) * time integration of net input, using  ... 
arXiv:1709.04654v1 fatcat:yfwcuiyjj5ggpcro7iblvt3zpi