David A. Ehrlich

According to our database, David A. Ehrlich authored at least 7 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Shannon invariants: A scalable approach to information decomposition.

Aaron J. Gutknecht, Fernando E. Rosas, David A. Ehrlich, Abdullah Makkeh, Pedro A. M. Mediano, Michael Wibral

CoRR, April, 2025

What should a neuron aim for? Designing local objective functions based on information theory.

Andreas Christian Schneider, Valentin Neuhaus, David Alexander Ehrlich, Abdullah Makkeh, Alexander S. Ecker, Viola Priesemann, Michael Wibral

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions.

Abdullah Makkeh, Marcel Graetz, Andreas C. Schneider, David A. Ehrlich, Viola Priesemann, Michael Wibral

Dataset, July, 2024

2023

A Measure of the Complexity of Neural Representations based on Partial Information Decomposition.

David A. Ehrlich, Andreas C. Schneider, Viola Priesemann, Michael Wibral, Abdullah Makkeh

Trans. Mach. Learn. Res., 2023

Partial Information Decomposition for Continuous Variables based on Shared Exclusions: Analytical Formulation and Estimation.

David A. Ehrlich, Kyle Schick-Poland, Abdullah Makkeh, Felix Lanfermann, Patricia Wollstadt, Michael Wibral

CoRR, 2023

Infomorphic networks: Locally learning neural networks derived from partial information decomposition.

Marcel Graetz, Abdullah Makkeh, Andreas C. Schneider, David A. Ehrlich, Viola Priesemann, Michael Wibral

CoRR, 2023

2022

Partial Information Decomposition Reveals the Structure of Neural Representations.

David A. Ehrlich, Andreas C. Schneider, Michael Wibral, Viola Priesemann, Abdullah Makkeh

CoRR, 2022