85 citations · 212 across the 17 of their papers we have counts for
17 papers
Novel Inconsistency Results for Partial Information Decomposition
Philip Hendrik Matthias, Abdullah Makkeh, Michael Wibral +1
We prove that three cornerstone properties of classical information theory, namely non-negativity of information, the chain rule, and invariance under invertible transformations, b…
Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks
Mark Blümel, Andreas C. Schneider, Valentin Neuhaus +5
Associative memory, traditionally modeled by Hopfield networks, enables the retrieval of previously stored patterns from partial or noisy cues. Yet, the local computational princip…
Shannon invariants: A scalable approach to information decomposition
Aaron J. Gutknecht, Fernando E. Rosas, David A. Ehrlich +3
Distributed systems, such as biological and artificial neural networks, process information via complex interactions engaging multiple subsystems, resulting in high-order patterns…
What should a neuron aim for? Designing local objective functions based on information theory
Andreas C. Schneider, Valentin Neuhaus, David A. Ehrlich +4
In modern deep neural networks, the learning dynamics of the individual neurons is often obscure, as the networks are trained via global optimization. Conversely, biological system…
Partial Information Decomposition for Continuous Variables based on Shared Exclusions: Analytical Formulation and Estimation
David A. Ehrlich, Kyle Schick-Poland, Abdullah Makkeh +3
Describing statistical dependencies is foundational to empirical scientific research. For uncovering intricate and possibly non-linear dependencies between a single target variable…
A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions
Abdullah Makkeh, Marcel Graetz, Andreas C. Schneider +3
Despite the impressive performance of biological and artificial networks, an intuitive understanding of how their local learning dynamics contribute to network-level task solutions…
From Babel to Boole: The Logical Organization of Information Decompositions
Aaron J. Gutknecht, Abdullah Makkeh, Michael Wibral
The conventional approach to the general Partial Information Decomposition (PID) problem has been redundancy-based: specifying a measure of redundant information between collection…
A Measure of the Complexity of Neural Representations based on Partial Information Decomposition
David A. Ehrlich, Andreas C. Schneider, Viola Priesemann +2
In neural networks, task-relevant information is represented jointly by groups of neurons. However, the specific way in which this mutual information about the classification label…
A partial information decomposition for discrete and continuous variables
Kyle Schick-Poland, Abdullah Makkeh, Aaron J. Gutknecht +3
Conceptually, partial information decomposition (PID) is concerned with separating the information contributions several sources hold about a certain target by decomposing the corr…
Partial Information Decomposition of Boolean Functions: a Fourier Analysis perspective
Abdullah Makkeh, Dirk Oliver Theis, Raul Vicente
Partial information decomposition (PID) partitions the information that a set of sources has about a target variable into synergistic, unique, and redundant contributions. This inf…
Bits and Pieces: Understanding Information Decomposition from Part-whole Relationships and Formal Logic
Aaron J. Gutknecht, Michael Wibral, Abdullah Makkeh
Partial information decomposition (PID) seeks to decompose the multivariate mutual information that a set of source variables contains about a target variable into basic pieces, th…
Introducing a differentiable measure of pointwise shared information
Abdullah Makkeh, Aaron J. Gutknecht, Michael Wibral
Partial information decomposition (PID) of the multivariate mutual information describes the distinct ways in which a set of source variables contains information about a target va…
MAXENT3D_PID: An Estimator for the Maximum-entropy Trivariate Partial Information Decomposition
Abdullah Makkeh, Daniel Chicharro, Dirk Oliver Theis +1
Chicharro (2017) introduced a procedure to determine multivariate partial information measures within the maximum entropy framework, separating unique, redundant, and synergistic c…
Optimizing Bivariate Partial Information Decomposition
Abdullah Makkeh, Dirk Oliver Theis
None of the BROJA information decomposition measures $\mbox{SI}, \mbox{CI}, \mbox{UIy}, \mbox{UIz}$ are convex or concave over the probability simplex. In this paper, we provide fo…
BROJA-2PID: A robust estimator for bivariate partial information decomposition
Abdullah Makkeh, Dirk Oliver Theis, Raul Vicente
Makkeh, Theis, and Vicente found in [8] that Cone Programming model is the most robust to compute the Bertschinger et al. partial information decompostion (BROJA PID) measure [1].…
The Graph of the Pedigree Polytope is Asymptotically Almost Complete (Extended Abstract)
Abdullah Makkeh, Mozhgan Pourmoradnasseri, Dirk Oliver Theis
Graphs (1-skeletons) of Traveling-Salesman-related polytopes have attracted a lot of attention. Pedigree polytopes are extensions of the classical Symmetric Traveling Salesman Prob…
On the Graph of the Pedigree Polytope
Abdullah Makkeh, Mozhgan Pourmoradnasseri, Dirk Oliver Theis
Pedigree polytopes are extensions of the classical Symmetric Traveling Salesman Problem polytopes whose graphs (1-skeletons) contain the TSP polytope graphs as spanning subgraphs.…