用于序列建模的深时态Sigmoid信度网络
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
摘要:
开发了深度动态生成模型来学习时间序列数据中的顺序依赖关系。多层模型的设计是通过构建一个层次的时间S形信念网络(TSBN),定义为一个顺序堆栈的S形信念网络(SBN)。每个SBN都有一个上下文隐藏状态,继承自序列中的前一个SBN,并用于调节其隐藏偏差。可扩展的学习和推理算法,通过引入识别模型,产生快速采样的变分后验。该识别模型与生成模型一起训练,通过最大化其对数似然的变分下限。在弹跳球、复调音乐、运动捕捉和文本流上的实验结果表明,该方法具有最佳的预测性能,并具有合成各种序列的能力。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。