Filtering-Ranking Perceptron Learning for Partial Parsing

This work introduces a general phrase recognition system based on perceptrons, and a global online learning algorithm to train them together. The method applies to complex domains in which some structure has to be recognized. This global problem is broken down into two layers of local subproblems: a filtering layer, which reduces the search space by identifying plausible phrase candidates; and a ranking layer, which builds the optimal phrase structure by discriminating among competing phrases. A recognition-based feedback rule is presented which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. As a result, the learned functions automatically behave as filters and rankers, rather than binary classifiers, which we argue to be better for this type of problems. Extensive experimentation on partial parsing tasks gives state-of-the-art results and evinces the advantages of the global training method over optimizing each function locally and independently.Editors: Dan Roth and Pascale Fung     

Frequency tuning in electromagnetic bandgap nonlinear transmission lines

Frequency tuning in stopband filters based on nonlinear transmission lines is demonstrated for the first time. The structure is an electromagnetic bandgap (EBG) coplanar waveguide reflector periodically loaded with varactor diodes, acting as tuning elements. By varying the capacitance of the diodes the phase velocity can be tailored, the result being a wide tuning range for the central frequency of the rejected band. It was also found that the EBG-based reflector is able to inhibit harmonic generation under large-signal driving conditions.     

Interval methods for fault-tree analysis in robotics

This paper describes a novel technique, based on interval methods, for estimating reliability using fault trees. The approach encodes inherent uncertainty in the input data by modeling these data in terms of intervals. Appropriate interval arithmetic is then used to propagate the data through standard fault trees to generate output distributions which reflect the uncertainty in the input data. Through a canonical example of reliability estimation for a robot manipulator system, we show how the use of this novel interval method appreciably improves the accuracy of reliability estimates over existing approaches to the problem of uncertain input data. This method avoids the key problem of loss of uncertainty inherent in some approaches when applied to noncoherent systems. It is further shown that the method has advantages over approaches based on partial simulation of the input-data space because it can provide guaranteed bounds for the estimates in reasonable times     

Spectral learning of weighted automata

In recent years we have seen the development of efficient provably correct algorithms for learning Weighted Finite Automata (WFA). Most of these algorithms avoid the known hardness results by defining parameters beyond the number of states that can be used to quantify the complexity of learning automata under a particular distribution. One such class of methods are the so-called spectral algorithms that measure learning complexity in terms of the smallest singular value of some Hankel matrix. However, despite their simplicity and wide applicability to real problems, their impact in application domains remains marginal to this date. One of the goals of this paper is to remedy this situation by presenting a derivation of the spectral method for learning WFA that—without sacrificing rigor and mathematical elegance—puts emphasis on providing intuitions on the inner workings of the method and does not assume a strong background in formal algebraic methods. In addition, our algorithm overcomes some of the shortcomings of previous work and is able to learn from statistics of substrings. To illustrate the approach we present experiments on a real application of the method to natural language parsing.     

BIONETS: Bio-Inspired Networking for Pervasive Communication Environments

This paper presents BIONETS, which is a novel bio-inspired approach to the design of localized services in pervasive communication/computing environments. Conventional networking approaches are not suitable for such scenarios, where they face three main issues, namely: 1) heterogeneity, 2) scalability, and 3) complexity. The proposed solution draws inspiration from the living world in terms of 1) evolutionary paradigms able to drive the adaptation process of autonomic services and 2) social paradigms for the provisioning of the necessary cooperation mechanisms. The net result is the introduction of autonomic self-evolving services that are able to adapt to localized needs and conditions while ensuring the maintenance of a purposeful system. Such a system requires scalable support from the communication standpoint. In networking terms, this results in the introduction of a two-tier architecture based on localized opportunistic exchanges of information. The presented approach is able to achieve better scalability properties when compared to more conventional communication approaches     

Optimal combined word-length allocation and architectural synthesis of digital signal processing circuits

In this brief, we address the combined application of word-length allocation and architectural synthesis of linear time-invariant digital signal processing systems. These two design tasks are traditionally performed sequentially, thus lessening the overall design complexity, but ignoring forward and backward dependencies that may lead to cost reductions. Mixed integer linear programming is used to formulate the combined problem and results are compared to the two-step traditional approach.     

Two-step gradient-based reinforcement learning for underwater robotics behavior learning

This article proposes a field application of a Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot in a cable tracking task. The Ictineu Autonomous Underwater Vehicle (AUV) learns to perform a visual based cable tracking task in a two step learning process. First, a policy is computed by means of simulation where a hydrodynamic model of the vehicle simulates the cable following task. The identification procedure follows a specially designed Least Squares (LS) technique. Once the simulated results are accurate enough, in a second step, the learnt-in-simulation policy is transferred to the vehicle where the learning procedure continues in a real environment, improving the initial policy. The Natural Actor–Critic (NAC) algorithm has been selected to solve the problem. This Actor–Critic (AC) algorithm aims to take advantage of Policy Gradient (PG) and Value Function (VF) techniques for fast convergence. The work presented contains extensive real experimentation. The main objective of this work is to demonstrate the feasibility of RL techniques to learn autonomous underwater tasks, the selection of a cable tracking task is motivated by an increasing industrial demand in a technology to survey and maintain underwater structures.