Interpretability for Turing Machines
We show that susceptibilities, an interpretability technique developed for neural networks, can identify the presence of algorithmic structure in Turing machines by probing the local loss landscape of a learning problem for noisy Turing machines introduced by Murfet and Troiani (arXiv:2504.08075). We prove that symmetries and path separation in the algorithm implemented by a Turing machine induce permutation symmetries and low-rank blocks in its susceptibility matrix. We study this empirically on a set of deterministic finite automata (DFAs) and demonstrate that algorithmic features can be recovered by principal component analysis and clustering methods in susceptibility space.
Code (1)
Similar Papers 제목 키워드 기반
Are there intelligent Turing machines?
This paper introduces a new computing model based on the cooperation among Turing machines called orchestrated machines. Like universal Turing machines, orchestrated machines are also designed to simulate Turing machines…
Emotional IntelligenceCompiling Turing Machines into Storage Modification Machines
It is well known that Sch\"onhage's Storage Modification Machines (SMM) can simulate Turing Machines (TM) since Sch\"onhage's original proof of the Turing completeness of the eponymous machines. We propose a simple trans…
Learning to Optimize Capacity Planning in Semiconductor Manufacturing
In manufacturing, capacity planning is the process of allocating production resources in accordance with variable demand. The current industry practice in semiconductor manufacturing typically applies heuristic rules to …
Reinforcement LearningGraph Neural NetworkReservoir memory machines
In recent years, Neural Turing Machines have gathered attention by joining the flexibility of neural networks with the computational capabilities of Turing machines. However, Neural Turing Machines are notoriously hard t…
regressionEvolutionary Turing in the Context of Evolutionary Machines
One of the roots of evolutionary computation was the idea of Turing about unorganized machines. The goal of this work is the development of foundations for evolutionary computations, connecting Turing's ideas and the con…