Hugging Face Trending Papers

Explaining Attention with Program Synthesis

Read the original on Hugging Face Trending Papers →

A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper, we propose an approach for approximating the behavior of components of deep networks with executable programs.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.