Version 1
: Received: 6 June 2023 / Approved: 7 June 2023 / Online: 7 June 2023 (05:42:05 CEST)
How to cite:
Gadepally, K.C.; Dhal, S.B.; Kalafatis, S.; Nowka, K. Systematic Model Complexity Reduction by Elimination of Irrelevant Layers in Convolutional Neural Networks. Preprints2023, 2023060492. https://doi.org/10.20944/preprints202306.0492.v1
Gadepally, K.C.; Dhal, S.B.; Kalafatis, S.; Nowka, K. Systematic Model Complexity Reduction by Elimination of Irrelevant Layers in Convolutional Neural Networks. Preprints 2023, 2023060492. https://doi.org/10.20944/preprints202306.0492.v1
Gadepally, K.C.; Dhal, S.B.; Kalafatis, S.; Nowka, K. Systematic Model Complexity Reduction by Elimination of Irrelevant Layers in Convolutional Neural Networks. Preprints2023, 2023060492. https://doi.org/10.20944/preprints202306.0492.v1
APA Style
Gadepally, K.C., Dhal, S.B., Kalafatis, S., & Nowka, K. (2023). Systematic Model Complexity Reduction by Elimination of Irrelevant Layers in Convolutional Neural Networks. Preprints. https://doi.org/10.20944/preprints202306.0492.v1
Chicago/Turabian Style
Gadepally, K.C., Stavros Kalafatis and Kevin Nowka. 2023 "Systematic Model Complexity Reduction by Elimination of Irrelevant Layers in Convolutional Neural Networks" Preprints. https://doi.org/10.20944/preprints202306.0492.v1
Abstract
Neural networks were treated as black boxes for a long time. Previous works have unearthed what aspects of an image were important for convolutional layers at different positions in the network. This was done using deconvolutional networks. In this paper, we examine how well a convolutional neural network performs when those convolutional layers which are relatively unimportant for a particular image (i.e., the image does not produce one of the strongest activations) are skipped in the training, validating, and testing process.
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
