Loading...

Lowering mutual coherence between receptive fields in convolutional neural networks

Amini, S ; Sharif University of Technology | 2019

329 Viewed
  1. Type of Document: Article
  2. DOI: 10.1049/el.2018.7671
  3. Publisher: Institution of Engineering and Technology , 2019
  4. Abstract:
  5. It has been shown that more accurate signal recovery can be achieved with low-coherence dictionaries in sparse signal processing. In this Letter, the authors extend the low-coherence attribute to receptive fields in convolutional neural networks. A new constrained formulation to train low-coherence convolutional neural network is presented and an efficient algorithm is proposed to train the network. The resulting formulation produces a direct link between the receptive fields of a layer through training procedure that can be used to extract more informative representations from the subsequent layers. Simulation results over three benchmark datasets confirm superiority of the proposed low-coherence convolutional neural network over the unconstrained version
  6. Keywords:
  7. Neural networks ; Signal reconstruction ; Benchmark datasets ; Convolutional neural network ; Low-coherence ; Mutual coherence ; Receptive fields ; Signal recovery ; Sparse signal processing ; Training procedures ; Convolution
  8. Source: Electronics Letters ; Volume 55, Issue 6 , 2019 , Pages 325-327 ; 00135194 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8666192