no code implementations • 8 Nov 2023 • Kieran A. Murphy, Dani S. Bassett
Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy.
1 code implementation • 11 Jul 2023 • Shubhankar P. Patankar, Mathieu Ouellet, Juan Cervino, Alejandro Ribeiro, Kieran A. Murphy, Dani S. Bassett
The theories view curiosity as an intrinsic motivation to optimize for topological features of subgraphs induced by nodes visited in the environment.
1 code implementation • 10 Jul 2023 • Kieran A. Murphy, Dani S. Bassett
Guided by the distributed information bottleneck as a learning objective, the information decomposition identifies the variation in the measurements of the system state most relevant to specified macroscale behavior.
no code implementations • 30 Nov 2022 • Kieran A. Murphy, Dani S. Bassett
Borrowing from information theory, we use the Distributed Information Bottleneck to find optimal compressions of each feature that maximally preserve information about the output.
1 code implementation • 25 Oct 2022 • Kieran A. Murphy, Dani S. Bassett
A hallmark of chaotic dynamics is the loss of information with time.
no code implementations • 15 Apr 2022 • Kieran A. Murphy, Dani S. Bassett
The Distributed Information Bottleneck throttles the downstream complexity of interactions between the components of the input, deconstructing a relationship into meaningful approximations found through deep learning without requiring custom-made datasets or neural network architectures.
1 code implementation • CVPR 2022 • Kieran A. Murphy, Varun Jampani, Srikumar Ramalingam, Ameesh Makadia
We propose a novel algorithm that utilizes a weak form of supervision where the data is partitioned into sets according to certain inactive (common) factors of variation which are invariant across elements of each set.