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 for loss of spatial information and huge solution space. To address these issues, we propose matrix neural networks (MatNet), which takes matrices directly as inputs. Each layer summarises and passes information through bilinear mapping. Under this structure, back prorogation and gradient descent combination can be utilised to obtain network parameters efficiently. Furthermore, it can be conveniently extended for multimodal inputs. We apply MatNet to MNIST handwritten digits classification and image super resolution tasks to show its effectiveness. Without too much tweaking MatNet achieves comparable performance as the state-of-the-art methods in both tasks with considerably reduced complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Al-Rfou et al.: Theano: a Python framework for fast computation of mathematical expressions. arXiv e-prints abs/1605.02688, May 2016
Bishop, C.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)
Fukushima, K.: Artificial vision by multi-layered neural networks: Neocognitron and its advances. Neural Netw. 37, 103–119 (2013)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Hosmer Jr., D.W., Lemeshow, S., Sturdivant, R.X.: Applied Logistic Regression, vol. 398. Wiley, Hoboken (2013)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 807–814 (2010)
Shu, M., Fyshe, A.: Sparse autoencoders for word decoding from magnetoencephalography. In: Proceedings of the Third NIPS Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI) (2013)
Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gao, J., Guo, Y., Wang, Z. (2017). Matrix Neural Networks. In: Cong, F., Leung, A., Wei, Q. (eds) Advances in Neural Networks - ISNN 2017. ISNN 2017. Lecture Notes in Computer Science(), vol 10261. Springer, Cham. https://doi.org/10.1007/978-3-319-59072-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-59072-1_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59071-4
Online ISBN: 978-3-319-59072-1
eBook Packages: Computer ScienceComputer Science (R0)