Loading...
Please wait, while we are loading the content...
Similar Documents
2.16 Markov Chain Monte Carlo Bayesian Learning for Neural Networks Markov Chain Monte Carlo Bayesian Learning for Neural Networks
| Content Provider | Semantic Scholar |
|---|---|
| Author | Goodrich, Michael S. |
| Copyright Year | 2011 |
| Abstract | Conventional training methods lor neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g .• normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available dala and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in networ\( weights and therefore networ\( predictions by using a modified Jeffery's prior combined with a Metropolis Mar\(ov Chain Monte Carlo method . |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/20110012135.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
