Publications [#338701] of Lawrence Carin

Papers Published

1. Gan, Z; Li, C; Henao, R; Carlson, DE; Carin, L, Deep temporal sigmoid belief networks for sequence modeling, Advances in Neural Information Processing Systems, vol. 2015-January (2015), pp. 2467-2475
   (last updated on 2024/12/31)

   Abstract:
   Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential stack of sigmoid belief networks (SBNs). Each SBN has a contextual hidden state, inherited from the previous SBNs in the sequence, and is used to regulate its hidden bias. Scalable learning and inference algorithms are derived by introducing a recognition model that yields fast sampling from the variational posterior. This recognition model is trained jointly with the generative model, by maximizing its variational lower bound on the log-likelihood. Experimental results on bouncing balls, polyphonic music, motion capture, and text streams show that the proposed approach achieves state-of-the-art predictive performance, and has the capacity to synthesize various sequences.