Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations.

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feedback connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse, invariant features.

An Exact Reformulation of Feature-Vector-Based Radial-Basis-Function Networks for Graph-Based Observations.

Radial basis function (RBF) networks are traditionally defined for sets of vector-based observations. In this brief, we reformulate such networks so that they can be applied to adjacency-matrix representations of weighted, directed graphs that represent the relationships between object pairs. We restate the sum-of-squares objective function so that it is purely dependent on entries from the adjacency matrix.

Reduction of Markov Chains Using a Value-of-Information-Based Approach.

In this paper, we propose an approach to obtain reduced-order models of Markov chains. Our approach is composed of two information-theoretic processes. The first is a means of comparing pairs of stationary chains on different state spaces, which is done via the negative, modified Kullback-Leibler divergence defined on a model joint space.

Guided Policy Exploration for Markov Decision Processes Using an Uncertainty-Based Value-of-Information Criterion.

Reinforcement learning in environments with many action-state pairs is challenging. The issue is the number of episodes needed to thoroughly search the policy space. Most conventional heuristics address this search problem in a stochastic manner.

An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits.

In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards.

Design considerations for an underwater soft-robot inspired from marine invertebrates.

This article serves as an overview of the unique challenges and opportunities made possible by a soft, jellyfish inspired, underwater robot. We include a description of internal pressure modeling as it relates to propulsive performance, leading to a desired energy-minimizing volume flux program. Strategies for determining optimal actuator placement derived from biological body motions are presented.

Identifying and modeling motion primitives for the hydromedusae Sarsia tubulosa and Aequorea victoria.

The movements of organisms can be thought of as aggregations of motion primitives: motion segments containing one or more significant actions. Here, we present a means to identify and characterize motion primitives from recorded movement data. We address these problems by assuming that the motion sequences can be characterized as a series of dynamical-system-based pattern generators.

Emergent trend detection in diurnal activity.

When monitoring elders' daily routines, it is desirable to track significant deviations from a baseline pattern, as consecutive, aberrant days may foreshadow a need for medical attention. However, many traditional, unsupervised methods for pattern classification are ill-suited for this task, as they are incapable for adapting to additive datasets. To surmount this shortcoming, we establish a framework for recognizing temporal trends in feature data extracted from passive sensors.