Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
- 9 January 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in International Journal of Computer Vision
- Vol. 129 (4), 1139-1152
- https://doi.org/10.1007/s11263-020-01422-y
Abstract
No abstract availableThis publication has 19 references indexed in Scilit:
- Do less and achieve more: Training CNNs for action recognition utilizing action images from the WebPattern Recognition, 2017
- Characterization and strengthening effects of γ′ precipitates in a high-strength casting Mg-15Gd-1Zn-0.4Zr (wt.%) alloyMaterials Characterization, 2017
- Top-Down Neural Attention by Excitation BackpropPublished by Springer Science and Business Media LLC ,2016
- Learning Deep Features for Discriminative LocalizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- TFCPublished by Association for Computing Machinery (ACM) ,2016
- Towards dropout training for convolutional neural networksNeural Networks, 2015
- Annealed dropout training of deep networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- A Study of Solar Panel Chimney for House VentilationApplied Mechanics and Materials, 2013
- Competitive Hebbian learning through spike-timing-dependent synaptic plasticityNature Neuroscience, 2000
- The Organization of Behavior; A Neuropsychological TheoryThe American Journal of Psychology, 1950