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.
Oja's neuron is extended to find the dominant eigenvalue alongside the computation of the dominant eigenvector. This is achieved through a stochastic gradient descent learning rule that computes the second moment of the neuron output. The effectiveness of this family of learning rules is further demonstrated in a network that verifies the law of total variance. The inputs are generated by a doubly...
In this paper we propose a modification of the Cognitive Architectures for Sensory Processing proposed by Chalasani and Principe. Here we keep the bottom-up data representation through generative models as before, but propose a top-down flow based on backpropagation of gradients for recognition. By treating the bottom-up procedure involved in the inference step as a recursive neural network, we show...
Dimensionality reduction methods compute a mapping from a high-dimensional space to a space with lower dimensions while preserving important information. The idea of hybridizing dimensionality reduction with evolution strategies is that the search in a space that employs a larger dimensionality than the original solution space may be easier. We propose a dimensionality reduction evolution strategy...
Recently, DNNs have achieved great improvement for acoustic modeling in speech recognition tasks. However, it is difficult to train the models well when the depth grows. One main reason is that when training DNNs with traditional sigmoid units, the derivatives damp sharply while back-propagating between layers, which restrict the depth of model especially with insufficient training data. To deal with...
Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train such deep networks is a major drawback. We tackled this problem by reusing a previously trained network...
The development of fast and mobile drug detection is an important aspect of personalized medicine. It enables the quick assessment of inter-individual differences in drug metabolism and corresponding adjustments of the dose. Recent developments of amperometric biosensors using cytochrome P450 (CYP) show great promise, by lowering the detection limit to physiological range for several drugs via the...
When dealing with a Support Vector Machine (SVM) with a strictly positive definite kernel, a common misconception is that the main handle for controlling the nonlinearity of the classification surface is the set of kernel hyperparameters. We show here that this is not the case: in particular, we prove that, regardless of the value of the kernel hyperparameter, it is always possible to tune the nonlinearity...
The paper deals with a simplified model of the HP TiO2 memristor, which can be used for identifying the parameters of built-in memristors, i.e. in cases where there is only a limited set of measurements possible. The memristor is excited by a rectangular voltage waveform and the built-in measuring device can measure the times when the memristor current crosses several thresholds. The proposed approach...
Linear and nonlinear models for time series analysis and prediction are well-established. Clustering methods have also been applied to this area. This paper explores a framework that can be used to cluster time series data. The range of values of a time series is clustered. Then the time series is clustered by data windows that flow into the initial set of value clusters. This allows predictive temporal...
In this paper, we apply our approach of Neurohydrodynamics (NHD) to a Hopfield neural network by introducing a one-dimensional spacial diffusion term. This reaction-diffusion equation includes an auxiliary equation that “guides” the weights of the network using the divergence of neuron's activation amplitude, which we call the neuropotential. This guiding principle is similar to de Broglie's “pilot...
A Particle Swarm Optimization (PSO) technique, in conjunction with Fuzzy Adaptive Resonance Theory (ART), was implemented to adapt vigilance values to appropriately compensate for a disparity in data sparsity. Gaining the ability to optimize a vigilance threshold over each cluster as it is created is useful because not all conceivable clusters have the same sparsity from the cluster centroid. Instead...
Recently Deep neural networks (DNN) have achieved a lot of success and become the most popular approach for speech recognition. DNN training for speech recognition is a difficult process due to its large number of parameters and speech dataset size. Using DNNs in a modeling task can be improved when pre-training is done using additional information. In this paper, we propose a new approach namely...
A growing number of noise reduction algorithms based on supervised learning have begun to emerge in recent years and show great promise. In this study, we focus on the problem of speech denoising at very low signal-to-noise ratio (SNR) conditions using artificial neural networks. The overall objective is to increase speech intelligibility in the presence of noise. Inspired by multitask learning (MTL),...
A class of memristor circuits is obtained by cascading a static nonlinear two-port with a dynamical one-port. The terminals of the input port of the static nonlinearity represent the access nodes for each memristor in the class. The class may be splitted into two sub-classes, namely the current- and voltagecontrolled memristors. Two further sets of memristors may be identied within each of such sub-classes,...
Classification of large amount of images calls for diverse types of features, but employing all possible feature types will create unnecessary computation burden, and may result in reduced classification accuracy. Selecting feature vectors individually is not a feasible solution in this scenario due to the high amount of feature vectors needed for reasonable performance. Instead, this paper proposes...
In this paper we present a model of saliency as the driving force behind endogenous attention in auditory processing using a competitive winner take all process. The model uses frequency, amplitude and spatial location bound together by temporal correlations in an oscillatory network to create unified perceptual objects that are consistent. The model also implements the interaction with exogenous...
A single-wheel mobile robot called Gyrocycle has been developed for carrying a human driver. Since a single-wheel mobile robot carries a human driver, the size and weight are designed to be larger compared with other single-wheel mobile robots. To maximize the balancing force, Gyrocycle is designed to have two flywheels required to be synchronized. Since a simple PD control lacks the robusteness,...
Generally, in order to learn sparse representations for raw inputs via an auto-encoder, the Kullback-Leibler (KL) divergence as a sparsity regularizer is introduced to the loss function for penalizing active code units. In fact, there exist other sparsity regularizers except the KL divergence. This paper introduces some classical sparsity regularizers into auto-encoders, and empirically gives a survey...
The purpose of this paper was to evaluate the performance of pedotransfer functions generated by Radial Base Function (RBF) Artificial Neural Network (ANN) to estimate soil water retention at field capacity (FC, suction at −30 kPa) and Permanent Wilting Point (PWP, −1500 kPa) for soils at PROJIR area -RJ/BR. The raw data used was type of soil horizon, texture, bulk density, soil organic carbon content...
In this study, we compared several classifiers for the supervised distinction between normal elderly and Alzheimer's disease individuals, based on resting state electroencephalographic markers, age, gender and education. Three main preliminary procedures served to perform features dimensionality reduction were used and discussed: a Support Vector Machines Recursive Features Elimination, a Principal...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.