English

Pillar Networks++: Distributed non-parametric deep and wide networks

Computer Vision and Pattern Recognition 2017-11-21 v1 Neural and Evolutionary Computing Computation Machine Learning

Abstract

In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). This was 0.4\% lower than frameworks that used hand-crafted features in addition to the deep convolutional feature extractors. In the present work, we show that combining distributed Gaussian Processes with multi-stream deep convolutional neural networks (CNN) alleviate the need to augment a neural network with hand-crafted features. In contrast to prior work, we treat each deep neural convolutional network as an expert wherein the individual predictions (and their respective uncertainties) are combined into a Product of Experts (PoE) framework.

Keywords

Cite

@article{arxiv.1708.06250,
  title  = {Pillar Networks++: Distributed non-parametric deep and wide networks},
  author = {Biswa Sengupta and Yu Qian},
  journal= {arXiv preprint arXiv:1708.06250},
  year   = {2017}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1707.06923

R2 v1 2026-06-22T21:19:37.593Z