Density Networks and their Application to Protein Modelling
I define a latent variable model in the form of a neural network for which only target outputs are specified; the inputs are unspecified. Although the inputs are missing, it is still possible to train this model by placing a simple probability distribution on the unknown inputs and maximizing the probability of the data given the parameters. The model can then discover for itself a description of the data in terms of an underlying latent variable space of lower dimensionality. I present preliminary results of the application of these models to protein data.
KeywordsLatent Variable Density Network Density Model Latent Variable Model Beta Sheet
Unable to display preview. Download preview PDF.
- Eddy, S. R., and Durbin, R., (1994) RNA sequence analysis using covariance models. NAR, in press.Google Scholar
- Hinton, G. E., and Zemel, R. S. (1994) Autoencoders, minimum description length and Helmholtz free energy. In Advances in Neural Information Processing Systems 6, ed. by J. D. Cowan, G. Tesauro, and J. Alspector, San Mateo, California. Morgan Kaufmann.Google Scholar
- Luttrell, S. P., (1994) The partitioned mixture distribution: an adaptive Bayesian network for low-level image processing. to appear.Google Scholar
- Mackay, D. J. C. (1995) Bayesian neural networks and density networks. Nuclear Instruments and Methods in Physics Research, Section A.Google Scholar
- MacKay, D. J. C., and Neal, R. M. (1994) Automatic relevance determination for neural networks. Technical Report in preparation, Cambridge University.Google Scholar
- Neal, R. M. (1993) Bayesian learning via stochastic dynamics. In Advances in Neural Information Processing Systems 5, ed. by C. L. Giles, S. J. Hanson, and J. D. Cowan, pp. 475 – 482, San Mateo, California. Morgan Kaufmann.Google Scholar