6 papers
Contrastive Entropy Bounds for Density and Conditional Density Decomposition
Bo Hu, Jose C. Principe
This paper studies the interpretability of neural network features from a Bayesian Gaussian view, where optimizing a cost is reaching a probabilistic bound; learning a model approx…
A Closed-Form Solution for Kernel Adaptive Filtering
Benjamin Colburn, Luis G. Sanchez Giraldo, Kan Li +1
Unlike the conventional kernel adaptive filtering (KAF) approach of using a fixed kernel to define the Reproducing Kernel Hilbert Space (RKHS), this paper embeds the statistics of…
A Simple and Effective Method for Uncertainty Quantification and OOD Detection
Yaxin Ma, Benjamin Colburn, Jose C. Principe
Bayesian neural networks and deep ensemble methods have been proposed for uncertainty quantification; however, they are computationally intensive and require large storage. By util…
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
Shihan Ma, Bo Hu, Tianyu Jia +5
The cortico-spinal neural pathway is fundamental for motor control and movement execution, and in humans it is typically studied using concurrent electroencephalography (EEG) and e…
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Hongming Li, Shujian Yu, Bin Liu +1
This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that…
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Shujian Yu, Xi Yu, Sigurd Løkse +2
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum suf…