2 papers
cs.LG2025
Quantifying The Limits of AI Reasoning: Systematic Neural Network Representations of Algorithms
Anastasis Kratsios, Dennis Zvigelsky, Bradd Hart
A main open question in contemporary AI research is quantifying the forms of reasoning neural networks can perform when perfectly trained. This paper answers this by interpreting r…
math.OA2025
Totally Bounded Elements in W*-probability Spaces
Jananan Arulseelan, Isaac Goldbring, Bradd Hart +1
We introduce the notion of a totally (-) bounded element of a W*-probability space and, borrowing ideas of Kadison, give an intrinsic characterization of the -suba…