SAFE-DNN: A Deep Neural Network With Spike Assisted Feature Extraction For Noise Robust Inference

Xueyuan She, Priyabrata Saha, Daehyun Kim, Yun Long, Saibal Mukhopadhyay

Abstract

We present a Deep Neural Network with Spike Assisted Feature Extraction (SAFE-DNN) to improve robustness of classification under stochastic perturbation of inputs. The proposed network augments a DNN with unsupervised learning of low-level features using spiking neural network (SNN) with spike-timing-dependent plasticity (STDP). The complete network learns to ignore local perturbation while performing global feature detection and classification. The experimental results on CIFAR-10 and ImageNet subset demonstrate improved noise robustness for multiple DNN architectures without sacrificing accuracy on clean images.
BibTeX
@inproceedings{she2020safe,
  author = {Xueyuan She and Priyabrata Saha and Daehyun Kim and Yun Long and Saibal Mukhopadhyay},
  title = {{SAFE-DNN: A Deep Neural Network With Spike Assisted Feature Extraction For Noise Robust Inference}},
  booktitle = {IJCNN},
  year = {2020},
  doi = {10.1109/ijcnn48605.2020.9207274},
}

Loading related content...

Figure