Search Results for author:
Found 3 papers, 1 papers with code
Opening the AI black box: program synthesis via mechanistic interpretability
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code.
Generating Interpretable Networks using Hypernetworks
The hypernetwork is carefully designed such that it can control network complexity, leading to a diverse family of interpretable algorithms ranked by their complexity.
Learning to Optimize Quasi-Newton Methods
This paper introduces a novel machine learning optimizer called LODO, which tries to online meta-learn the best preconditioner during optimization.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
