Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size.

Volume: 10, Issue: 1, Pages: 834 - 834
Published: Jan 21, 2020
Abstract
Deep neural networks have gained immense popularity in the Big null problem; however, the availability of training samples can be relatively limited in specific application domains, particularly medical imaging, and consequently leading to overfitting problems. This null Data challenge may need a mindset that is entirely different from the existing Big null paradigm. Here, under the small data scenarios, we examined whether the network structure...
Paper Details
Title
Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size.
Published Date
Jan 21, 2020
Volume
10
Issue
1
Pages
834 - 834
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.