Publications [#338679] of Lawrence Carin

Papers Published

1. Song, J; Gan, Z; Carin, L, Factored temporal sigmoid belief networks for sequence learning, 33rd International Conference on Machine Learning, ICML 2016, vol. 3 (January, 2016), pp. 1937-1946, ISBN 9781510829008
   (last updated on 2024/12/31)

   Abstract:
   Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Belief Network (TSBN), a sequential stack of Sigmoid Belief Networks (SBNs). The transition matrices are further factored to reduce the number of parameters and improve generalization. When side information is not available, a general framework for semi-supervised learning based on the proposed model is constituted, allowing robust sequence classification. Experimental results show that the proposed approach achieves state-of-theart predictive and classification performance on sequential data, and has the capacity to synthesize sequences, with controlled style transitioning and blending.