Timezone: »

 
Poster
Parsimonious Bayesian deep networks
Mingyuan Zhou

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 210 #3
in Wed Poster Session A »

Combining Bayesian nonparametrics and a forward model selection strategy, we construct parsimonious Bayesian deep networks (PBDNs) that infer capacity-regularized network architectures from the data and require neither cross-validation nor fine-tuning when training the model. One of the two essential components of a PBDN is the development of a special infinite-wide single-hidden-layer neural network, whose number of active hidden units can be inferred from the data. The other one is the construction of a greedy layer-wise learning algorithm that uses a forward model selection criterion to determine when to stop adding another hidden layer. We develop both Gibbs sampling and stochastic gradient descent based maximum a posteriori inference for PBDNs, providing state-of-the-art classification accuracy and interpretable data subtypes near the decision boundaries, while maintaining low computational complexity for out-of-sample prediction.

Keywords: Model Selection and Structure Learning · Deep Learning · Bayesian Nonparametrics
[ Paper]  [ Poster] 

Author Information

Mingyuan Zhou (University of Texas at Austin)

More from the Same Authors