We present a novel Dynamic Differentiable Reasoning (DDR) framework for jointly learning branching programs and the functions composing them; this resolves a significant nondifferentiability inhibiting recent dynamic architectures. We apply our framework to two settings in two highly compact and data efficient architectures: DDRprog for CLEVR Visual Question Answering and DDRstack for reverse Polish notation expression evaluation. DDRprog uses a recurrent controller to jointly predict and execute modular neural programs that directly correspond to the underlying question logic; it explicitly forks subprocesses to handle logical branching. By effectively leveraging additional structural supervision, we achieve a large improvement over previous approaches in subtask consistency and a small improvement in overall accuracy. We further demonstrate the benefits of structural supervision in the RPN setting: the inclusion of a stack assumption in DDRstack allows our approach to generalize to long expressions where an LSTM fails the task.

介绍了一种新颖的动态可微推理（DDR）框架，它可用于学习分支程序和其组成部分的函数，解决了最近动态架构中的重要非可微问题，并将其应用于CLEVR可视化问题回答和逆波兰表达式评估的两个设置中，通过有效利用额外的结构监督，在子任务一致性方面实现了大的改进和总体准确性的小提高。

DDRprog: 一个能够执行可微分动态推理编程的CLEVR程序员