Tracking the states of a nonlinear and nonstationary system in the weight-space of artificial neural networks

We propose a novel interpretation and usage of Neural Network (NN) in modeling physiological signals, which are allowed to be nonlinear and/or nonstationary. The method consists of training a NN for the k-step prediction of a physiological signal, and then examining the connection-weight-space (CWS) of the NN to extract information about the signal generator mechanism. We de. ne a novel feature, Normalized Vector Separation (gamma(ij)), to measure the separation of two arbitrary states i and j in the CWS and use it to track the state changes of the generating system. The performance of the method is examined via synthetic signals and clinical EEG. Synthetic data indicates that gamma(ij) can track the system down to a SNR of 3.5 dB. Clinical data obtained from three patients undergoing carotid endarterectomy of the brain showed that EEG could be modeled (within a root-means-squared-error of 0.01) by the proposed method, and the blood perfusion state of the brain could be monitored via gamma(ij), with small NNs having no more than 21 connection weight altogether.

Tracking the states of a nonlinear system in the weight-space of a feed-forward neural network

Nonlinear, non-stationary signals are commonly found in a variety of disciplines such as biology, medicine, geology and financial modeling. The complexity (e.g. nonlinearity and non-stationarity) of such signals and their low signal to noise ratios often make it a challenging task to use them in critical applications. In this paper we propose a new neural network based technique to address those problems. We show that a feed forward, multi-layered neural network can conveniently capture the states of a nonlinear system in its connection weight-space, after a process of supervised training. The performance of the proposed method is investigated via computer simulations.

Non-unitary-weight Space-Time Block Codes with Minimum Decoding Complexity

Space-Time Block Codes (STBCs) from Complex Orthogonal Designs (CODs) are single-symbol decodable/symbol-by-symbol decodable (SSD); however, SSD codes are obtainable from designs that are not CODs. Recently, two such classes of SSD codes have been studied: (i) Coordinate Interleaved Orthogonal Designs (CIODs) and (ii) Minimum-Decoding-Complexity (MDC) STBCs from Quasi-ODs (QODs). The class of CIODs have non-unitary weight matrices when written as a Linear Dispersion Code (LDC) proposed by Hassibi and Hochwald, whereas the other class of SSD codes including CODs have unitary weight matrices. In this paper, we construct a large class of SSD codes with nonunitary weight matrices. Also, we show that the class of CIODs is a special class of our construction.

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.

We don’t want your must-see TV: Transatlantic television and the failed “Coupling” format

NBC's failed attempt to remake the BBC's Coupling generated a significant amount of press coverage in summer 2003. At the core of the debate was a struggle to reconcile an increasingly integrated transatlantic television market with traditional assumptions about culture and its authentic connection to space and place. The interest in the remake not only created a space where certain national differences were played out and performed but also facilitated an equally compelling transatlantic dialogue about creative ownership, appropriation, and a network's responsibility to its audiences. In doing so, the media attention highlighted how television formats are best understood not as innocuous commodities of international trade but as potential sites of articulation, contestation, and community in an increasingly transnational television environment.

Uma contribuição ao estudo do transformador com nucleo de metal amorfo para aplicação em sistemas elétricos de potência de alta frequência

Pós-graduação em Engenharia Elétrica - FEIS

Code-specific learning rules improve action selection by populations of spiking neurons

Population coding is widely regarded as a key mechanism for achieving reliable behavioral decisions. We previously introduced reinforcement learning for population-based decision making by spiking neurons. Here we generalize population reinforcement learning to spike-based plasticity rules that take account of the postsynaptic neural code. We consider spike/no-spike, spike count and spike latency codes. The multi-valued and continuous-valued features in the postsynaptic code allow for a generalization of binary decision making to multi-valued decision making and continuous-valued action selection. We show that code-specific learning rules speed up learning both for the discrete classification and the continuous regression tasks. The suggested learning rules also speed up with increasing population size as opposed to standard reinforcement learning rules. Continuous action selection is further shown to explain realistic learning speeds in the Morris water maze. Finally, we introduce the concept of action perturbation as opposed to the classical weight- or node-perturbation as an exploration mechanism underlying reinforcement learning. Exploration in the action space greatly increases the speed of learning as compared to exploration in the neuron or weight space.

Dominance Measuring Method Performance under Incomplete Information about Weights.

In multi-attribute utility theory, it is often not easy to elicit precise values for the scaling weights representing the relative importance of criteria. A very widespread approach is to gather incomplete information. A recent approach for dealing with such situations is to use information about each alternative?s intensity of dominance, known as dominance measuring methods. Different dominancemeasuring methods have been proposed, and simulation studies have been carried out to compare these methods with each other and with other approaches but only when ordinal information about weights is available. In this paper, we useMonte Carlo simulation techniques to analyse the performance of and adapt such methods to deal with weight intervals, weights fitting independent normal probability distributions orweights represented by fuzzy numbers.Moreover, dominance measuringmethod performance is also compared with a widely used methodology dealing with incomplete information on weights, the stochastic multicriteria acceptability analysis (SMAA). SMAA is based on exploring the weight space to describe the evaluations that would make each alternative the preferred one.

Preference intensity in MCDM when an additive utility function represents DM preferences

We propose a new method for ranking alternatives in multicriteria decision-making problems when there is imprecision concerning the alternative performances, component utility functions and weights. We assume decision maker?s preferences are represented by an additive multiattribute utility function, in which weights can be modeled by independent normal variables, fuzzy numbers, value intervals or by an ordinal relation. The approaches are based on dominance measures or exploring the weight space in order to describe which ratings would make each alternative the preferred one. On the one hand, the approaches based on dominance measures compute the minimum utility difference among pairs of alternatives. Then, they compute a measure by which to rank the alternatives. On the other hand, the approaches based on exploring the weight space compute confidence factors describing the reliability of the analysis. These methods are compared using Monte Carlo simulation.

Transformación del espacio cinemático Laban para la evaluación del movimiento

Este proyecto tiene como objetivo la implementación de un sistema capaz de analizar el movimiento corporal a partir de unos puntos cinemáticos. Estos puntos cinemáticos se obtienen con un programa previo y se captan con la cámara kinect. Para ello el primer paso es realizar un estudio sobre las técnicas y conocimientos existentes relacionados con el movimiento de las personas. Se sabe que Rudolph Laban fue uno de sus mayores exponentes y gracias a sus observaciones se establece una relación entre la personalidad, el estado anímico y la forma de moverse de un individuo. Laban acuñó el término esfuerzo, que hace referencia al modo en que se administra la energía que genera el movimiento y de qué manera se modula en las secuencias, es una manera de describir la intención de las expresiones internas. El esfuerzo se divide en 4 categorías: peso, espacio, tiempo y flujo, y cada una de estas categorías tiene una polaridad denominada elemento de esfuerzo. Con estos 8 elementos de esfuerzo un movimiento queda caracterizado. Para poder cuantificar los citados elementos de esfuerzo se buscan movimientos que representen a alguno de ellos. Los movimientos se graban con la cámara kinect y se guardan sus valores en un archivo csv. Para el procesado de estos datos se establece que el sistema más adecuado es una red neuronal debido a su flexibilidad y capacidad a la hora de procesar entradas no lineales. Para la implementación de la misma se requiere un amplio estudio que incluye: topologías, funciones de activación, tipos de aprendizaje, algoritmos de entrenamiento entre otros. Se decide que la red tenga dos capas ocultas, para mejor procesado de los datos, que sea estática, siga un proceso de cálculo hacia delante (Feedforward) y el algoritmo por el que se rija su aprendizaje sea el de retropropagación (Backpropagation) En una red estática las entradas han de ser valores fijos, es decir, no pueden variar en el tiempo por lo que habrá que implementar un programa intermedio que haga una media aritmética de los valores. Una segunda prueba con la misma red trata de comprobar si sería capaz de reconocer movimientos que estuvieran caracterizados por más de un elemento de esfuerzo. Para ello se vuelven a grabar los movimientos, esta vez en parejas de dos, y el resto del proceso es igual. ABSTRACT. The aim of this project is the implementation of a system able to analyze body movement from cinematic data. This cinematic data was obtained with a previous program. The first step is carrying out a study about the techniques and knowledge existing nowadays related to people movement. It is known that Rudolf Laban was one the greatest exponents of this field and thanks to his observations a relation between personality, mood and the way the person moves was made. Laban coined the term effort, that refers to the way energy generated from a movement is managed and how it is modulated in the sequence, this is a method of describing the inner intention of the person. The effort is divided into 4 categories: weight, space, time and flow, and each of these categories have 2 polarities named elements of effort. These 8 elements typify a movement. We look for movements that are made of these elements so we can quantify them. The movements are recorded with the kinect camera and saved in a csv file. In order to process this data a neural network is chosen owe to its flexibility and capability of processing non-linear inputs. For its implementation it is required a wide study regarding: topology, activation functions, different types of learning methods and training algorithms among others. The neural network for this project will have 2 hidden layers, it will be static and follow a feedforward process ruled by backpropagation. In a static net the inputs must be fixed, this means they cannot vary in time, so we will have to implement an intermediate program to calculate the average of our data. A second test for our net will be checking its ability to recognize more than one effort element in just one movement. In order to do this all the movements are recorded again but this time in pairs, the rest of the process remains the same.

Dynamic stabilization of a plasma column.

"This report was prepared in connection with Space Technology Laboratories Program of General Research."

Formulation of the theory of turbulence in an incompressible fluid.

"This report was prepared in connection with Space Technology Laboratories Program of General Research."

The 'moving targets' training algorithm

A simple method for training the dynamical behavior of a neural network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The algorithm resembles back-propagation in that an error function is minimized using a gradient-based method, but the optimization is carried out in the hidden part of state space either instead of, or in addition to weight space. Computational results are presented for some simple dynamical training problems, one of which requires response to a signal 100 time steps in the past.

The 'moving targets' training algorithm

A simple method for training the dynamical behavior of a neural network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The method resembles back-propagation in that it is a least-squares, gradient-based optimization method, but the optimization is carried out in the hidden part of state space instead of weight space. A straightforward adaptation of this method to feedforward networks offers an alternative to training by conventional back-propagation. Computational results are presented for simple dynamical training problems, with varied success. The failures appear to arise when the method converges to a chaotic attractor. A patch-up for this problem is proposed. The patch-up involves a technique for implementing inequality constraints which may be of interest in its own right.

Creating new narratives through shared time and space : the performer/audience connection in multi-site dance events

Site-specific performance provides choices in audience experience via degrees of scale, proximity, levels of immersion and viewing perspectives. Beyond these choices, multi-site promenade events also form a connected audience/performer relationship in which moving together in time and space can produce a shared narrative and aesthetic sensibility of collective, yet individuated and shifting meanings. This paper interrogates this notion through audience/performer experiences in two separate multi-site, dance-led events. here/there/then/now occurred in four intimate sites within the Brisbane Powerhouse, providing a theatricalised platform for audiences to create linked narratives through open-ended and fragmented intertextuality. Accented Body, based on the concept of “the body as site and in site” and notions of connectivity, provided a more expansive platform for a similar, but heightened, shared engagement. Audiences traversed 6 outdoor and 2 indoor Brisbane sites moving to varying levels of a large complex. Eleven, predominantly interactive, screens provided links to other sites as well as to distributed presences in Seoul and London. The differentiation in scale and travel time between sites deepened the immersive experiences of audiences who reported transformative engagements with both site and architecture, accompanied by a sense of extended and yet quickened time.