10 citations · 17 across the 6 of their papers we have counts for
7 papers
Stream Recursion Model (SRM)
Asael Sorensen, Charles Brock, David Chamberlain +3
Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability techniques struggle to scale wit…
Reinforcement Learning for Data-Driven Workflows in Radio Interferometry. I. Principal Demonstration in Calibration
Brian M. Kirk, Urvashi Rau, Ramyaa Ramyaa
Radio interferometry is an observational technique used to study astrophysical phenomena. Data gathered by an interferometer requires substantial processing before astronomers can…
Learning with distributional inverters
Eric Binnendyk, Marco Carmosino, Antonina Kolokolova +2
We generalize the "indirect learning" technique of Furst et. al., 1991 to reduce from learning a concept class over a samplable distribution to learning the same concept class…
Biologically inspired sleep algorithm for artificial neural networks
Giri P Krishnan, Timothy Tadros, Ramyaa Ramyaa +1
Sleep plays an important role in incremental learning and consolidation of memories in biological systems. Motivated by the processes that are known to be involved in sleep generat…
Denotational cost semantics for functional languages with inductive types
Norman Danner, Daniel R. Licata, Ramyaa Ramyaa
A central method for analyzing the asymptotic complexity of a functional program is to extract and then solve a recurrence that expresses evaluation cost in terms of input size. Th…
Power of Nondetreministic JAGs on Cayley graphs
Martin Hofmann, Ramyaa Ramyaa
The Immerman-Szelepcsenyi Theorem uses an algorithm for co-st- connectivity based on inductive counting to prove that NLOGSPACE is closed un- der complementation. We want to invest…
Implicit complexity for coinductive data: a characterization of corecurrence
Daniel Leivant, Ramyaa Ramyaa
We propose a framework for reasoning about programs that manipulate coinductive data as well as inductive data. Our approach is based on using equational programs, which support a…