Matrix Neural Networks

Junbin Gao, Yi Guo and Zhiyong Wang

No 2016-06, Working Papers from University of Sydney Business School, Discipline of Business Analytics

Abstract: Traditional neural networks assume vectorial inputs as the network is arranged as layers of single line of computing units called neurons. This special structure requires the non-vectorial inputs such as matrices to be converted into vectors. This process can be problematic. Firstly, the spatial information among elements of the data may be lost during vectorisation. Secondly, the solution space becomes very large which demands very special treatments to the network parameters and high computational cost. To address these issues, we propose matrix neural networks (MatNet), which takes matrices directly as inputs. Each neuron senses summarised information through bilinear mapping from lower layer units in exactly the same way as the classic feed forward neural networks. Under this structure, back prorogation and gradient descent combination can be utilised to obtain network parameters e ciently. Furthermore, it can be conveniently extended for multimodal inputs. We apply MatNet to MNIST handwritten digits classi cation and image super resolution tasks to show its e ectiveness. Without too much tweaking MatNet achieves comparable performance as the state-of-the-art methods in both tasks with considerably reduced complexity.

Keywords: Image Super Resolution; Pattern Recognition; Machine Learning; Back Propagation; Neural Networks (search for similar items in EconPapers)
Date: 2016-11-02
New Economics Papers: this item is included in nep-cmp and nep-ecm
References: Add references at CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
http://hdl.handle.net/2123/15839

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:syb:wpbsba:2123/15839

Access Statistics for this paper

More papers in Working Papers from University of Sydney Business School, Discipline of Business Analytics Contact information at EDIRC.
Bibliographic data for series maintained by Artem Prokhorov ().