Hugging Face Trending Papers

Graphical Design of Interpretable Architectures

Read the original on Hugging Face Trending Papers →

The paper introduces a new graphical notation, adapted from Penrose tensor notation, to design and represent interpretable AI architectures. Unlike symbolic equations or probabilistic models, this notation provides a global view of an architecture while directly mapping to PyTorch einsum code. The authors demonstrate its use on several interpretable models and on the Steerling-8B language model, revealing structural insights and enabling concise code generation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 20

Graphical Design of Interpretable Architectures

The paper introduces a graphical notation, adapted from Penrose tensor notation, to design and represent interpretable AI architectures. This notation provides a global view of an architecture and maps directly onto PyTorch einsum code, enabling clear depiction of tensor manipulations. The authors apply the notation to several interpretable models—concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models—and use it to diagram the key components of the Steerling-8B language model, revealing its residual structure and allowing a concise 33‑line PyTorch implementation.

By Pietro Barbiero
arXiv AI
Aug 12

sLTN: Structural Logic Tensor Networks

arXiv:2608. 11136v1 Announce Type: new Abstract: Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical constraints to be integrated with differentiable learning.

By Davide Rinaldi, Luciano Serafini