Geometric Operator Convolutional Neural NetworkDownload PDF

27 Sep 2018 (modified: 05 Dec 2018)ICLR 2019 Conference Withdrawn SubmissionReaders: Everyone
  • Abstract: The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems. We present a framework called Geometric Operator Convolutional Neural Network (GO-CNN) that uses domain knowledge, wherein the kernel of the first convolutional layer is replaced with a kernel generated by a geometric operator function. This framework integrates many conventional geometric operators, which allows it to adapt to a diverse range of problems. Under certain conditions, we theoretically analyze the convergence and the bound of the generalization errors between GO-CNNs and common CNNs. Although the geometric operator convolution kernels have fewer trainable parameters than common convolution kernels, the experimental results indicate that GO-CNN performs more accurately than common CNN on CIFAR-10/100. Furthermore, GO-CNN reduces dependence on the amount of training examples and enhances adversarial stability.
  • Keywords: Convolutional Neural Network, Geometric Operator, Image Classification, Theoretical Analysis
  • TL;DR: Traditional image processing algorithms are combined with Convolutional Neural Networks,a new neural network.
6 Replies