Abstract
Through the introduction of local receptive fields, we improve the fidelity of restricted Boltzmann machine (RBM) based representations to encodings extracted by visual processing neurons. Our biologically inspired Gaussian receptive field constraints encourage learning of localized features and can seamlessly integrate into RBMs. Moreover, we propose a method for concurrently finding advantageous receptive field centers, while training the RBM. The strength of our method to reconstruct characteristic details of facial features is demonstrated on a challenging face dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Computation 14(8), 1771–1800 (2002)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Huang, G.B., Mattar, M.A., Lee, H., Learned-Miller, E.: Learning to align from scratch. In: Neural Information Processing Systems, pp. 773–781 (2012)
Kavukcuoglu, K., Sermanet, P., Boureau, Y.L., Gregor, K., Mathieu, M., LeCun, Y.: Learning convolutional feature hierarchies for visual recognition. In: Neural Information Processing Systems, pp. 1090–1098 (2010)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1106–1114 (2012)
Le, Q.V., Monga, R., Devin, M., Corrado, G., Chen, K., Ranzato, M.A., Dean, J., Ng, A.Y.: Building high-level features using large scale unsupervised learning. In: International Conference on Machine Learning, pp. 81–88 (2012)
Lee, H., Ekanadham, C., Ng, A.: Sparse deep belief net model for visual area V2. In: Neural Information Processing Systems, pp. 873–880 (2008)
Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: International Conference on Machine Learning, pp. 609–616 (2009)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning, pp. 807–814 (2010)
Turcsany, D., Bargiela, A., Maul, T.: Modelling retinal feature detection with deep belief networks in a simulated environment. In: European Conference on Modelling and Simulation, pp. 364–370 (2014)
Zhu, Z., Luo, P., Wang, X., Tang, X.: Deep learning identity-preserving face space. In: IEEE International Conference on Computer Vision, pp. 113–120 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Turcsany, D., Bargiela, A. (2014). Learning Local Receptive Fields in Deep Belief Networks for Visual Feature Detection. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds) Neural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8834. Springer, Cham. https://doi.org/10.1007/978-3-319-12637-1_58
Download citation
DOI: https://doi.org/10.1007/978-3-319-12637-1_58
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12636-4
Online ISBN: 978-3-319-12637-1
eBook Packages: Computer ScienceComputer Science (R0)