Dear all,
Prof. Tapani Raiko will introduce his recent work on extending NADE into NADE-k tomorrow at the tea talk (http://arxiv.org/abs/1406.1485, the paper attached).
=======
- Speaker: Prof. Tapani Raiko (Aalto University, Finland) - Date and Time: 11 June 2014 @ 13.00 - Place: AA3195 - Abstract: Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in k steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-predictive training: (1) Its test likelihood can be computed analytically, (2) it is easy to generate independent samples from it, and (3) it uses an inference engine that is a superset of variational inference for Boltzmann machines. The proposed NADE-k has state-of-the-art performance in density estimation on the two datasets tested.
Afficher les réponses par date