Sarah Marzen

15 papers A* 1B 1Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2024 J jnl
From reinforcement learning to agency: Frameworks for understanding basal cognition.
Biosyst.
Gabriella Seifert, Ava Sealander, Sarah Marzen, Michael Levin
2024 A* conf
Transformers Represent Belief State Geometry in their Residual Stream.
NeurIPS
Adam S. Shai, Lucas Teixeira, Alexander Gietelink Oldenziel, Sarah Marzen, Paul M. Riechers
2023 J jnl
How Well Can We Infer Selection Benefits and Mutation Rates from Allele Frequencies?
Entropy
Jonathan Soriano, Sarah Marzen
2020 J jnl
Inferring an Observer's Prediction Strategy in Sequence Learning Experiments.
Entropy
Abhinuv Uppal, Vanessa Ferdinand, Sarah Marzen
2018 J jnl
Intrinsic Computation of a Monod-Wyman-Changeux Molecule.
Entropy
Sarah Marzen
2017 B conf
Revisiting Perceptual Distortion for Natural Images: Mean Discrete Structural Similarity Index.
DCC
Christopher J. Hillar, Sarah Marzen
2017 J jnl
The difference between memory and prediction in linear recurrent networks.
CoRR
Sarah Marzen
2016 J jnl
Memory and Information Processing in Recurrent Neural Networks.
CoRR
Alireza Goudarzi, Sarah Marzen, Peter Banda, Guy Feldman, Christof Teuscher, Darko Stefanovic
2015 — conf
Exploring discrete approaches to lossy compression schemes for natural image patches.
EUSIPCO
Ram Mehta, Sarah Marzen, Christopher J. Hillar
2015 J jnl
Signatures of Infinity: Nonergodicity and Resource Scaling in Prediction, Complexity, and Learning.
CoRR
James P. Crutchfield, Sarah Marzen
2014 J jnl
Circumventing the Curse of Dimensionality in Prediction: Causal Rate-Distortion for Infinite-Order Markov Processes.
CoRR
Sarah Marzen, James P. Crutchfield
2014 J jnl
Information Anatomy of Stochastic Equilibria.
CoRR
Sarah Marzen, James P. Crutchfield
2014 J jnl
Information Anatomy of Stochastic Equilibria.
Entropy
Sarah Marzen, James P. Crutchfield
2014 J jnl
Informational and Causal Architecture of Discrete-Time Renewal Processes.
CoRR
Sarah Marzen, James P. Crutchfield
2014 J jnl
Understanding and Designing Complex Systems: Response to "A framework for optimal high-level descriptions in science and engineering - preliminary report".
CoRR
James P. Crutchfield, Ryan G. James, Sarah Marzen, Dowman P. Varn