The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A conventional weight in an artificial neural network has a single trainable real value and produces a linear relationship between the weight input and the weight output. A real synaptic cleft is also trainable but provides a more complex relationship. It is obvious to wonder if adding extra complexity to the conventional weight response would lead to more capable networks. This work describes a weight...
Echo State Networks ESNs are specific kind of recurrent networks providing a black box modeling of dynamic non-linear problems. Their architecture is distinguished by a randomly recurrent hidden infra-structure called dynamic reservoir. Coming up with an efficient reservoir structure depends mainly on selecting the right parameters including the number of neurons and connectivity rate within it. Despite...
Many works have attempted to characterize the complexity of classification problems by measures extracted from their learning datasets. These indexes provide indicatives of the inherent difficulty in solving a given classification problem. Although regression problems are equally frequent, there is a lack of studies in Machine Learning dedicated to understanding their complexity. This paper proposes...
Epileptic seizure detection using EEGs is a heavy workload of traditional visual inspection for diagnosing epilepsy. Therefore, more and more research on automatic seizure detection have been developed in recent years. The appropriate feature extraction method and efficient classifier are recognized to be crucial in the successful realization. In this paper, we first create a novel feature extraction...
Traditional supervised machine learning tests the learned classifiers on data which are drawn from the same distribution as the data used for the learning. In practice, this hypothesis does not always hold and the learned classifier has to be transferred from the space of learning data (also called source data) to the space of test data (also called target data) where it is not directly applicable...
Clustering has raised as an important problem in many different domains like biology, computer vision, text analysis and robotics. Thus, many different clustering techniques were developed to address this essential problem and propose astonishing solutions to conquer it. However, traditional clustering techniques suffer either from their limitations to detect specific shapes like K-means and PAM or...
The nearest subspace classifier (NSC) assumes that the samples of every class lie on a separate subspace and it is possible to classify a test sample by computing the distance between the test sample and the subspaces. The sparse representation based classification (SRC) generalizes the NSC - it assumes that the samples of any class can lie on a union of subspaces. By calculating the distance between...
Research on pedestrian detection still presents a lot of space for improvements, both on speed and detection accuracy. State-of-the-art object proposals approach has shown the very effective computational efficiency in object detection. In this paper, we present a framework for pedestrian detection based on the object proposals. Instead of scaling the test image to different sizes, we generate a pyramid...
Active matrix completion (AMC) is an effective approach to improve the performance of matrix completion. It actively acquires certain missing entries of a target matrix, with the aim of quickly improving the completion accuracy of the rest. Although this topic is attracting an increasing attention, all existing solutions are heuristic. In this paper, we propose a new active matrix completion approach...
Complex-valued (CV) B-spline neural network approach offers a highly effective means for identification and inversion of Hammerstein systems. Compared to its conventional CV polynomial based counterpart, CV B-spline neural network has superior performance in identifying and inverting CV Hammerstein systems, while imposing a similar complexity. In this paper, we review the optimality of CV B-spline...
A new non-parametric method for reducing the number of dimensions in binary and continuous data, and for measuring the complexity of binary and continuous datasets, is introduced. The method, named Structural Manifold Analysis (SMA), is based on “Generalized Invariance Structure Theory” [1–6], a theory that has been successful in characterizing and accurately predicting human concept learning and...
Tool use constitutes a range of complex behaviors that generally require a sophisticated level of cognition, and is only found in higher mammals and a number of avian species. In this paper, we will examine how different strategies for using a tool emerge during the simulated evolution of a two degree-of-freedom articulated limb in a reaching task environment. The limb is controlled by recurrent neural...
Different dynamic classifier selection techniques have been proposed in the literature to determine among diverse classifiers available in a pool which should be used to classify a test instance. The individual competence of each classifier in the pool is usually evaluated taking into account its accuracy on the neighborhood of the test instance in a validation dataset. In this work we investigate...
The attractor-based complexity of a Boolean neural network is a measure which refers to the ability of the network to perform more or less complicated classification tasks of its inputs via the manifestation of meaningful or spurious attractor dynamics. Here, we study the attractor-based complexity of a Boolean model of the basal ganglia-thalamocortical network. We show that the regulation of the...
The problem of finding nearest neighbours in terms of Euclidean distance, Hamming distance or other distance metric is a very common operation in computer vision and pattern recognition. In order to accelerate the search for the nearest neighbour in large collection datasets, many methods rely on the coarse-fine approach. In this paper we propose to combine Product Quantization (PQ) and binary neural...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.