Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
This article presents the implementation of position control of a mobile inverted pendulum(MIP) system by using the radial basis function network(RBF). The MIP has two wheels to move on the plane and to balance the pendulum. The MIP is known as a nonlinear system whose dynamics is non-holonomic. The goal is to control the MIP to maintain the balance of the pendulum while tracking a desired position...
The incremental learning system for a feature extraction unit in the character recognition system is described and experimental results are shown. The relationship between this learning system and neural networks (NN) are explained and the specifications of this method are described as an NN application. The improved version of this system which is related to the Gabor filter was tested and an accuracy...
Estimation of plant Jacobian is necessary for successful control of nonlinear systems using neural networks with the specialized learning scheme. Our previous study showed that neuro-emulators provide a better estimation of the plant Jacobian using a new cost function for learning during the course of dynamic modeling and control. This paper presents an approach for further enhancing the estimation...
Human cognition is characterized by three important features: productivity, dynamics and grounding. These features can be integrated in a neural architecture. The representations in this architecture are not symbol tokens, that can be copied and transported. Instead, the representations always remain ldquoin siturdquo, because they are grounded in perception, action, emotion, associations and (semantic)...
Conventional cost functions of adaptive filtering are usually related to the errorpsilas dispersion, such as errorpsilas moments or errorpsilas entropy, but neglect the shape aspects (peaks, kurtosis, tails, etc.) of the error distribution. In this work, we propose a new notion of filtering (or estimation) in which the errorpsilas probability density function (PDF) is shaped into a desired one. As...
Negative Correlation Learning (NCL) has been showing to outperform other ensemble learning approaches in off-line mode. A key point to the success of NCL is that the learning of an ensemble member is influenced by the learning of the others, directly encouraging diversity. However, when applied to on-line learning, NCL presents the problem that part of the diversity has to be built a priori, as the...
This paper employs two types of neural networks to control a single-link flexible arm. To train each network, we utilize a gradient-based approach with adaptive learning rate. We first apply the diagonal recurrent neural network (DRNN) to a single-link flexible arm, which is a challenging control problem, in order to investigate the ability of this type of recurrent neural network. We then apply a...
Increasing dependence on car-based travel has led to the daily occurrence of freeway congestions around the world. In order to improve the worse and worse traffic congestion situation and solve the problems brought with it, a new kind of effective, fast, and robust method should be presented. Ramp metering has been developed as a traffic management strategy to alleviate congestion on freeways. But,...
In this paper, neural network based ensemble learning methods are introduced in predicting activities of COX-2 inhibitors in Chinese medicine quantitative structure-activity relationship (QSAR) research. Three different ensemble learning methods: bagging, boosting and random subspace are tested using neural networks as basic regression rules. Experiments show that all three methods, especially boosting,...
It is often that the learned neural networks end with different decision boundaries under the variations of training data, learning algorithms, architectures, and initial random weights. Such variations are helpful in designing neural network ensembles, but are harmful for making unstable performances, i.e., large variances among different learnings. This paper discusses how to reduce such variances...
Artificial intelligence research is now flourishing which aims at achieving general, human-level intelligence. Accordingly, cognitive architectures are increasingly employed as blueprints for building intelligent agents to be endowed with various perceptive and cognitive abilities. This paper presents a novel integrated neuro-cognitive architecture (INCA) which emulate the putative functional aspects...
An adaptive tracking controller for a discrete-time direct current (DC) motor model in presence of bounded disturbances is presented. A high order neural network is used to identify the plant model; this network is trained with an extended Kalman filter. Then, the discrete-time block control and sliding modes techniques are used to develop the reference tracking control. This paper includes also the...
Almost all learning machines used in computational intelligence are not regular but singular statistical models, because they are nonidentifiable and their Fisher information matrices are singular. In singular learning machines, neither the Bayes a posteriori distribution converges to the normal distribution nor the maximum likelihood estimator satisfies the asymptotic normality, resulting that it...
In this paper, the application of iterative learning control (ILC) in two-dimensional systems is considered and a method of ILC for 2-D systems is introduced so that the output of the process follows a desired trajectory. In this method the input of process in each iteration is determined by an innovative method called two-dimensional method by means of the obtained error between the output of the...
This work combines several established regression and meta-learning techniques to give a holistic regression model and presents the proposed learnt topology gating artificial neural networks (LTGANN) model in the context of a general architecture previously published by the authors. The applied regression techniques are artificial neural networks, which are on one hand used as local experts for the...
In this paper, we propose a novel method for incremental semi-supervised learning. Unlike the traditional way of incremental learning or semi-supervised learning, we try to answer a more challenging question: given inadequate labeled training data, can one use the unlabeled testing data to improve the learning and prediction accuracy? The objective here is to reinforce the learning system trained...
Anomaly detection provides an early warning of unusual behavior in units in a fleet operating in a dynamic environment by learning system characteristics from normal operational data and flagging any unanticipated or unseen patterns. For a complex system such as an aircraft engine, normal operation might consist of multiple modes in a high dimensional space. Therefore, anomaly detection approaches...
Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural models known as fusion architecture for learning, cognition and navigation (FALCON) can incorporate a priori knowledge and perform knowledge refinement and expansion through reinforcement learning. Symbolic rules are formulated...
This article argues for the new solution of personal recommender systems that can provide learners with suitable learning objects to learn in group learning. In order to improve the ldquoeducational provisionrdquo to implement the e-learning recommender system, we propose a new recommendation approach which has been proven to be more suitable to realize personalized recommendation based on not only...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.