Structure injected weight normalization for training deep networks
Sign Up to like & getrecommendations! Published in 2021 at "Multimedia Systems"
DOI: 10.1007/s00530-021-00793-7
Abstract: Weight normalization (WN) can help to stabilize the distribution of activations over layers, which boost the performance of DNNs in generalization. In this paper, we further propose deep structural weight normalization (DSWN) methods to inject… read more here.
Keywords: weight normalization; dswn; network; deep networks ... See more keywords
Spatiotemporal deep networks for detecting abnormality in videos
Sign Up to like & getrecommendations! Published in 2020 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-020-08786-w
Abstract: Detecting and localizing anomalous behavior in the surveillance video is explored and spatiotemporal model, which jointly learns the appearance and motion-based feature is proposed. The general solution is to learn from the normal-data as reference… read more here.
Keywords: networks detecting; detecting abnormality; deep networks; spatiotemporal deep ... See more keywords
Knowledge Distillation Based on Narrow-Deep Networks
Sign Up to like & getrecommendations! Published in 2024 at "Neural Processing Letters"
DOI: 10.1007/s11063-024-11646-5
Abstract: Deep neural networks perform better than shallow neural networks, but the former tends to be deeper or wider, introducing large numbers of parameters and computations. We know that networks that are too wide have a… read more here.
Keywords: narrow deep; deep networks; knowledge distillation; distillation based ... See more keywords
An evolutionary generation method of deep neural network sets combined with Gaussian random field
Sign Up to like & getrecommendations! Published in 2021 at "Wireless Networks"
DOI: 10.1007/s11276-021-02677-0
Abstract: As a research hotspot in the field of machine learning, ensemble learning improved the prediction accuracy of the final model by constructing and combining multiple basic models. In recent years, many experts and scholars are… read more here.
Keywords: neural network; field; ensemble learning; deep networks ... See more keywords
Urea Injection Control Based on Deep-Q Networks for SCR Aftertreatment Systems
Sign Up to like & getrecommendations! Published in 2020 at "IFAC-PapersOnLine"
DOI: 10.1016/j.ifacol.2020.12.2309
Abstract: Abstract The regulations on NOx emissions from diesel vehicles have been stringent in recent years. Various techniques such as lean NOx trap (LNT) and selective catalytic reduction (SCR) have been developed to lessen the NOx… read more here.
Keywords: control; urea injection; amount; injection control ... See more keywords
Accurate cloud detection in high-resolution remote sensing imagery by weakly supervised deep learning
Sign Up to like & getrecommendations! Published in 2020 at "Remote Sensing of Environment"
DOI: 10.1016/j.rse.2020.112045
Abstract: Abstract Cloud cover is a common and inevitable phenomenon that often hinders the usability of optical remote sensing (RS) image data and further interferes with continuous cartography based on RS image interpretation. In the literature,… read more here.
Keywords: remote sensing; image; cloud detection; deep networks ... See more keywords
Parallel Distributed Processing Theory in the Age of Deep Networks
Sign Up to like & getrecommendations! Published in 2017 at "Trends in Cognitive Sciences"
DOI: 10.1016/j.tics.2017.09.013
Abstract: Parallel distributed processing (PDP) models in psychology are the precursors of deep networks used in computer science. However, only PDP models are associated with two core psychological claims, namely that all knowledge is coded in… read more here.
Keywords: processing theory; distributed processing; age deep; parallel distributed ... See more keywords
A practical generalization metric for deep networks benchmarking
Sign Up to like & getrecommendations! Published in 2024 at "Scientific Reports"
DOI: 10.1038/s41598-025-93005-5
Abstract: There is an ongoing and dedicated effort to estimate bounds on the generalization error of deep learning models, coupled with an increasing interest with practical metrics that can be used to experimentally evaluate a model’s… read more here.
Keywords: metric deep; deep networks; generalization metric; theoretical estimations ... See more keywords
Deep networks on toroids: removing symmetries reveals the structure of flat regions in the landscape geometry
Sign Up to like & getrecommendations! Published in 2022 at "Journal of Statistical Mechanics: Theory and Experiment"
DOI: 10.1088/1742-5468/ac9832
Abstract: We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of parameters. Grouping classifiers into equivalence classes,… read more here.
Keywords: deep networks; removing symmetries; space; geometry ... See more keywords
Teaching deep networks to see shape: Lessons from a simplified visual world
Sign Up to like & getrecommendations! Published in 2024 at "PLOS Computational Biology"
DOI: 10.1101/2024.03.25.586544
Abstract: Deep neural networks have been remarkably successful as models of the primate visual system. One crucial problem is that they fail to account for the strong shape-dependence of primate vision. Whereas humans base their judgements… read more here.
Keywords: color texture; deep networks; many images; shape ... See more keywords
Matching Matched Filtering with Deep Networks for Gravitational-Wave Astronomy.
Sign Up to like & getrecommendations! Published in 2018 at "Physical review letters"
DOI: 10.1103/physrevlett.120.141103
Abstract: We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals. The standard method for the detection of well-modeled transient… read more here.
Keywords: matching matched; gravitational wave; astronomy; matched filtering ... See more keywords