论文标题
从感知到程序：正规化，过度参数化和摊销
From Perception to Programs: Regularize, Overparameterize, and Amortize
论文作者
论文摘要
为了将归纳推理与感知能力相结合，我们开发了神经符号程序综合的技术，其中首先将神经网络的感知输入解析为低维的可解释表示，然后由合成程序处理。我们探索了放松问题的几种技术，并共同学习所有模块端到端，梯度下降：多任务学习；摊销推断；过度参数化；以及惩罚冗长计划的可区分策略。收集的该工具箱可提高梯度指导程序搜索的稳定性，并提出学习如何将输入视为离散抽象的方法，以及如何象征性地处理这些抽象作为程序。
Toward combining inductive reasoning with perception abilities, we develop techniques for neurosymbolic program synthesis where perceptual input is first parsed by neural nets into a low-dimensional interpretable representation, which is then processed by a synthesized program. We explore several techniques for relaxing the problem and jointly learning all modules end-to-end with gradient descent: multitask learning; amortized inference; overparameterization; and a differentiable strategy for penalizing lengthy programs. Collectedly this toolbox improves the stability of gradient-guided program search, and suggests ways of learning both how to perceive input as discrete abstractions, and how to symbolically process those abstractions as programs.
