Inference Over Programs That Make Predictions
This work addresses the problem of building generalizable AI systems for researchers in machine learning, but it is incremental as it builds directly on existing methods without introducing new results.
The paper proposes extending prior work on program induction via probabilistic programming to enable automatic program synthesis that generalizes across diverse data types like text, images, and videos, aiming to tackle the challenge of creating adaptable predictive programs.
This abstract extends on the previous work (arXiv:1407.2646, arXiv:1606.00075) on program induction using probabilistic programming. It describes possible further steps to extend that work, such that, ultimately, automatic probabilistic program synthesis can generalise over any reasonable set of inputs and outputs, in particular in regard to text, image and video data.