Seeing is believing: Brain-inspired modular training for mechanistic interpretability

Z Liu, E Gan, M Tegmark - Entropy, 2023 - mdpi.com
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …
Speichern Sie Cite Cited by 27 Related articles View as HTML

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability.

Z Liu, E Gan, M Tegmark - Entropy (Basel, Switzerland), 2023 - europepmc.org
Abstract We introduce Brain-Inspired Modular Training (BIMT), a method for making neural
networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - Entropy, 2024 - search.proquest.com
Abstract We introduce Brain-Inspired Modular Training (BIMT), a method for making neural
networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a …
Cite

Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - arXiv preprint arXiv:2305.08746, 2023 - arxiv.org
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - 2023 - dspace.mit.edu
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …
Cite
[HTML] nih.gov

[HTML][HTML] Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - Entropy, 2024 - ncbi.nlm.nih.gov
Abstract We introduce Brain-Inspired Modular Training (BIMT), a method for making neural
networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - Entropy (Basel, Switzerland), 2023 - pubmed.ncbi.nlm.nih.gov
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability

Z Liu, E Gan, M Tegmark - Entropy, 2023 - ui.adsabs.harvard.edu
Abstract We introduce Brain-Inspired Modular Training (BIMT), a method for making neural
networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability.

Z Liu, E Gan, M Tegmark - Entropy, 2024 - search.ebscohost.com
Abstract We introduce Brain-Inspired Modular Training (BIMT), a method for making neural
networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a …
Cite

Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability.

Z Liu, E Gan, M Tegmark - Entropy (Basel, Switzerland), 2023 - europepmc.org
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks
more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric …
Cite