We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture. Compared to other deep models, DRMMs allow more flexible conditional sampling: The model can be trained once with all variables, and then used for sampling with arbitrary combinations of conditioning variables, Gaussian priors, and (in)equality constraints. This provides new opportunities for interactive and exploratory machine learning, where the user does not have to wait for retraining a model. We demonstrate these benefits in constrained multi-limb inverse kinematics, movement planning, and image completion.

翻译：我们提出深残余混合模型(DRMMs),这是一个全新的深层基因模型结构。与其他深层模型相比,DRMMs允许更灵活的有条件抽样:该模型可以经过一次与所有变量的培训,然后用于任意结合调节变量、高山前科和(在)平等制约进行抽样。这为互动和探索机器学习提供了新的机会,用户不必等待再培训模型。我们展示了这些好处,包括有限的多层反动运动、运动规划和图像完成等。