activity
20192026
most citedDecomposing neural networks as mappings of correlation functions

12 citations · 13 across the 8 of their papers we have counts for

collaborators

9 papers

stat.ML2026

Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence

Itay Lavie, Kirsten Fischer, Andrey Lekov +3

Attention is the key mechanism underlying in-context learning in transformers, and attention patterns have been observed empirically to emerge abruptly during training. We present…

cs.LG2026

A unified theory of feature learning in RNNs and DNNs

Jan P. Bauer, Kirsten Fischer, Moritz Helias +1

Recurrent and deep neural networks (RNNs/DNNs) are cornerstone architectures in machine learning. Remarkably, RNNs differ from DNNs only by weight sharing, as can be shown through…

q-bio.NC2025

Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows

Peter Bouss, Sandra Nestler, Kirsten Fischer +3

Neuronal activity is found to lie on low-dimensional manifolds embedded within the high-dimensional neuron space. Variants of principal component analysis are frequently employed t…

cond-mat.dis-nn2025

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning

Noa Rubin, Kirsten Fischer, Javed Lindner +5

Feature learning in neural networks is crucial for their expressive power and inductive biases, motivating various theoretical approaches. Some approaches describe network behavior…

cond-mat.dis-nn2024

Critical feature learning in deep neural networks

Kirsten Fischer, Javed Lindner, David Dahmen +3

A key property of neural networks driving their success is their ability to learn features from data. Understanding feature learning from a theoretical viewpoint is an emerging fie…

cond-mat.dis-nn2023

Learning Interacting Theories from Data

Claudia Merger, Alexandre René, Kirsten Fischer +5

One challenge of physics is to explain how collective properties arise from microscopic interactions. Indeed, interactions form the building blocks of almost all physical theories…