Learning Structured Output Representation using Deep ...

← Back to document page

Learning Structured Output Representationusing Deep Conditional Generative ModelsKihyuk Sohn Xinchen Yan Honglak Lee NEC Laboratories America, Inc. University of Michigan, Ann deep Learning has been successfully applied to many recognition prob-lems. Although it can approximate a complex many-to-one function well when alarge amount of training data is provided, it is still challenging to model com-plex Structured Output representations that effectively perform probabilistic infer-ence and make diverse predictions. In this work, we develop a deep conditionalgenerative model for Structured Output prediction using Gaussian latent model is trained efficiently in the framework of stochastic gradient varia-tional Bayes, and allows for fast prediction using stochastic feed-forward infer-ence.

posterior inference. However, the parameters of the VAE can be estimated efficiently in the stochas-tic gradient variational Bayes (SGVB) [16] framework, where the variational lower bound of the log-likelihood is used as a surrogate objective function. The variational lower bound is written as: logp (x) = KL(q ˚(zjx)kp (zjx))+E q ˚(zjx) logq ...

  Output, Stochas tic, Stochas