no code implementations • 20 Jan 2024 • Isaac J. Sledge, Dominic M. Byrne, Jonathan L. King, Steven H. Ostertag, Denton L. Woods, James L. Prater, Jermaine L. Kennedy, Timothy M. Marston, Jose C. Principe
We propose a weakly-supervised framework for the semantic segmentation of circular-scan synthetic-aperture-sonar (CSAS) imagery.
no code implementations • 20 Dec 2022 • Isaac J. Sledge, Jose C. Principe
We then illustrate that these trends hold for deep, value-of-information-based agents that learn to play ten simple games and over forty more complicated games for the Nintendo GameBoy system.
1 code implementation • 24 Sep 2021 • Isaac J. Sledge, Jose C. Principe
This yields matrix-based estimators of R\'enyi's $\alpha$-cross-entropies.
no code implementations • 22 Jul 2021 • Isaac J. Sledge, Christopher D. Toole, Joseph A. Maestri, Jose C. Principe
We propose a memory-based framework for real-time, data-efficient target analysis in forward-looking-sonar (FLS) imagery.
no code implementations • 5 Jul 2021 • Isaac J. Sledge, Jose C. Principe
A fundamental problem when aggregating Markov chains is the specification of the number of state groups.
no code implementations • 24 Feb 2021 • Isaac J. Sledge, Darshan W. Bryner, Jose C. Principe
We have previously developed a means of constraining, and hence speeding up, the search process through the use of motion primitives; motion primitives are sequences of pre-specified actions taken across a state series.
no code implementations • 18 Jan 2021 • Isaac J. Sledge, Jose C. Principe
It yields unsupervised object recognition that surpass convolutional autoencoders and are on par with convolutional networks trained in a supervised manner.
no code implementations • 10 Jan 2021 • Isaac J. Sledge, Matthew S. Emigh, Jonathan L. King, Denton L. Woods, J. Tory Cobb, Jose C. Principe
We show that our framework outperforms supervised, deep-saliency networks designed for natural imagery.
no code implementations • 22 Jan 2019 • Isaac J. Sledge, Jose C. Principe
An important property of our radial basis function networks is that they are guaranteed to yield the same responses as conventional radial-basis networks trained on a corresponding vector realization of the relationships encoded by the adjacency-matrix.
no code implementations • 5 Feb 2018 • Isaac J. Sledge, Matthew S. Emigh, Jose C. Principe
The value of information yields a stochastic routine for choosing actions during learning that can explore the policy space in a coarse to fine manner.
no code implementations • 28 Oct 2017 • Isaac J. Sledge, Jose C. Principe
In this paper, we provide an approach to clustering relational matrices whose entries correspond to either similarities or dissimilarities between objects.
no code implementations • 8 Oct 2017 • Isaac J. Sledge, Jose C. Principe
High amounts of policy information are associated with exploration-dominant searches of the space and yield high rewards.
no code implementations • 28 Feb 2017 • Isaac J. Sledge, Jose C. Principe
This cost function is the value of information, which provides the optimal trade-off between the expected return of a policy and the policy's complexity; policy complexity is measured by number of bits and controlled by a single hyperparameter on the cost function.