Loading...
Lowering mutual coherence between receptive fields in convolutional neural networks
Amini, S ; Sharif University of Technology | 2019
329
Viewed
- Type of Document: Article
- DOI: 10.1049/el.2018.7671
- Publisher: Institution of Engineering and Technology , 2019
- Abstract:
- 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
- Keywords:
- Neural networks ; Signal reconstruction ; Benchmark datasets ; Convolutional neural network ; Low-coherence ; Mutual coherence ; Receptive fields ; Signal recovery ; Sparse signal processing ; Training procedures ; Convolution
- Source: Electronics Letters ; Volume 55, Issue 6 , 2019 , Pages 325-327 ; 00135194 (ISSN)
- URL: https://ieeexplore.ieee.org/document/8666192