no code implementations • 4 Feb 2024 • Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei, Daniel Murfet
We show that in-context learning emerges in transformers in discrete developmental stages, when they are trained on either language modeling or linear regression tasks.
no code implementations • 10 Oct 2023 • Zhongtian Chen, Edmund Lau, Jake Mendel, Susan Wei, Daniel Murfet
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT).
1 code implementation • 23 Aug 2023 • Edmund Lau, Daniel Murfet, Susan Wei
Deep neural networks (DNN) are singular statistical models which exhibit complex degeneracies.
no code implementations • 30 Mar 2021 • James Clift, Daniel Murfet, James Wallbridge
We re-evaluate universal computation based on the synthesis of Turing machines.
1 code implementation • 22 Oct 2020 • Daniel Murfet, Susan Wei, Mingming Gong, Hui Li, Jesse Gell-Redman, Thomas Quella
In singular models, the optimal set of parameters forms an analytic set with singularities and classical statistical inference cannot be applied to such models.
1 code implementation • ICLR 2020 • James Clift, Dmitry Doryn, Daniel Murfet, James Wallbridge
We introduce the 2-simplicial Transformer, an extension of the Transformer which includes a form of higher-dimensional attention generalising the dot-product attention, and uses this attention to update entity representations with tensor products of value vectors.
no code implementations • 2 Sep 2019 • James Clift, Dmitry Doryn, Daniel Murfet, James Wallbridge
We introduce the $2$-simplicial Transformer, an extension of the Transformer which includes a form of higher-dimensional attention generalising the dot-product attention, and uses this attention to update entity representations with tensor products of value vectors.
1 code implementation • 18 Mar 2019 • Daniel Murfet
We study constructive $A_\infty$-models of the DG-category of matrix factorisations of a potential over a commutative $\mathbb{Q}$-algebra $k$, consisting of a Hom-finite $A_\infty$-category equipped with an $A_\infty$-idempotent functor.
Algebraic Geometry Mathematical Physics Mathematical Physics
no code implementations • 9 Jul 2014 • Daniel Murfet
We give an introduction to logic tailored for algebraists, explaining how proofs in linear logic can be viewed as algorithms for constructing morphisms in symmetric closed monoidal categories with additional structure.
Logic Logic in Computer Science Category Theory