Search Results for author:
Found 7 papers, 4 papers with code
Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
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.
Intrinsically motivated graph exploration using network theories of human curiosity
The theories view curiosity as an intrinsic motivation to optimize for topological features of subgraphs induced by nodes visited in the environment.
Information decomposition in complex systems via machine learning
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.
Interpretability with full complexity by constraining feature information
Borrowing from information theory, we use the Distributed Information Bottleneck to find optimal compressions of each feature that maximally preserve information about the output.
Characterizing information loss in a chaotic double pendulum with the Information Bottleneck
A hallmark of chaotic dynamics is the loss of information with time.
The Distributed Information Bottleneck reveals the explanatory structure of complex systems
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.
Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision
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.
