Improving machine vision via incorporating expectation-maximization into Deep Spatio-Temporal learning

Min Jiang, Yulong Ding, Ben Goertzel, Zhongqiang Huang, Changle Zhou, Fei Chao

Abstract

The Deep Spatio-Temporal Inference Network (DeSTIN) is a deep learning architecture which combines un-supervised learning and Bayesian inference. The original version of DeSTIN incorporates k-means clustering inside each processing node. Here we propose to replace k-means with a more sophisticated algorithm, online EM (Expectation Maximization), and show that this improves DeSTIN's performance on image classification and restoration tasks.
BibTeX
@inproceedings{jiang2014improving,
  author = {Min Jiang and Yulong Ding and Ben Goertzel and Zhongqiang Huang and Changle Zhou and Fei Chao},
  title = {{Improving machine vision via incorporating expectation-maximization into Deep Spatio-Temporal learning}},
  booktitle = {IJCNN},
  year = {2014},
  doi = {10.1109/ijcnn.2014.6889723},
}

Loading related content...

Figure