
Estimating Rényi's αCrossEntropies in a MatrixBased Way
Conventional informationtheoretic quantities assume access to probabili...
read it

ExternalMemory Networks for LowShot Learning of Targets in ForwardLookingSonar Imagery
We propose a memorybased framework for realtime, dataefficient target...
read it

An InformationTheoretic Approach for Automatically Determining the Number of States when Aggregating Markov Chains
A fundamental problem when aggregating Markov chains is the specificatio...
read it

Annotating Motion Primitives for Simplifying Action Search in Reinforcement Learning
Reinforcement learning in largescale environments is challenging due to...
read it

Faster Convergence in DeepPredictiveCoding Networks to Learn Deeper Representations
Deeppredictivecoding networks (DPCNs) are hierarchical, generative mod...
read it

Target Detection and Segmentation in CircularScan SyntheticApertureSonar Images using SemiSupervised Convolutional EncoderDecoders
We propose a saliencybased, multitarget detection and segmentation fra...
read it

Reduction of Markov Chains using a ValueofInformationBased Approach
In this paper, we propose an approach to obtain reducedorder models of ...
read it

An Exact Reformulation of FeatureVectorbased RadialBasisFunction Networks for Graphbased Observations
Radialbasisfunction networks are traditionally defined for sets of vec...
read it

Guided Policy Exploration for Markov Decision Processes using an UncertaintyBased ValueofInformation Criterion
Reinforcement learning in environments with many actionstate pairs is c...
read it

Partitioning Relational Matrices of Similarities or Dissimilarities using the Value of Information
In this paper, we provide an approach to clustering relational matrices ...
read it

Using the Value of Information to Explore Stochastic, Discrete MultiArmed Bandits
In this paper, we propose an informationtheoretic exploration strategy ...
read it

Analysis of Agent Expertise in Ms. PacMan using ValueofInformationbased Policies
Conventional reinforcement learning methods for Markov decision processe...
read it
Isaac J. Sledge
is this you? claim profile