Authors argue by analogy that localised hardware ML architectures may be more interpretable and efficient than deep neural networks on GPUs for smaller datasets and evaluate candidate hardware paradigms.
(19) Bechtel, W.; Richardson, R
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
citing papers explorer
-
Enhancing AI Interpretability and Safety through Localised Architectures
Authors argue by analogy that localised hardware ML architectures may be more interpretable and efficient than deep neural networks on GPUs for smaller datasets and evaluate candidate hardware paradigms.
- Mechanistic Interpretability of Antibody Language Models Using SAEs