Advertisement

Topics

PubMed Journal Database | Neural networks : the official journal of the International Neural Network Society RSS

09:09 EDT 27th May 2019 | BioPortfolio

The US National Library of Medicine and National Institutes of Health manage PubMed.gov which comprises of more than 29 million records, papers, reports for biomedical literature, including MEDLINE, life science and medical journals, articles, reviews, reports and  books.

BioPortfolio aims to cross reference relevant information on published papers, clinical trials and news associated with selected topics - speciality.

For example view all recent relevant publications on Epigenetics and associated publications and clincial trials.

Showing PubMed Articles 1–25 of 415 from Neural networks : the official journal of the International Neural Network Society

BoSR: A CNN-based aurora image retrieval method.

The deep learning models especially the CNN have achieved amazing performance on natural image retrieval. However, remote sensing images captured with anamorphic lens are still retrieved via manual selection or traditional SIFT-based methods. How to leverage the advanced CNN models for remote sensing image retrieval is a new task of significance. This paper focuses on the aurora images captured with all-sky-imagers (ASI). By analyzing the imaging principle of ASI and characteristics of aurora, a salient reg...

Some generalized global stability criteria for delayed Cohen-Grossberg neural networks of neutral-type.

This paper carries out a theoretical investigation into the stability problem for the class of neutral-type Cohen-Grossberg neural networks with discrete time delays in states and discrete neutral delays in time derivative of states. By employing a more general type of suitable Lyapunov functional, a set of new generalized sufficient criteria are derived for the global asymptotic stability of delayed neural networks of neutral-type. The proposed stability criteria are independently of the values of the time...

Subrecursive neural networks.

It has been known for discrete-time recurrent neural networks (NNs) that binary-state models using the Heaviside activation function (with Boolean outputs 0 or 1) are equivalent to finite automata (level 3 in the Chomsky hierarchy), while analog-state NNs with rational weights, employing the saturated-linear function (with real-number outputs in the interval [0,1]), are Turing complete (Chomsky level 0) even for three analog units. However, it is as yet unknown whether there exist subrecursive (i.e. sub-...

Evolving neural networks to follow trajectories of arbitrary complexity.

Many experiments have been performed that use evolutionary algorithms for learning the topology and connection weights of a neural network that controls a robot or virtual agent. These experiments are not only performed to better understand basic biological principles, but also with the hope that with further progress of the methods, they will become competitive for automatically creating robot behaviors of interest. However, current methods are limited with respect to the (Kolmogorov) complexity of evolved...

Multivariate LSTM-FCNs for time series classification.

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiri...

Bayesian rank penalization.

Rank minimization is a key component of many computer vision and machine learning methods, including robust principal component analysis (RPCA) and low-rank representations (LRR). However, usual methods rely on optimization to produce a point estimate without characterizing uncertainty in this estimate, and also face difficulties in tuning parameter choice. Both of these limitations are potentially overcome with Bayesian methods, but there is currently a lack of general purpose Bayesian approaches for rank ...

A neural network-evolutionary computational framework for remaining useful life estimation of mechanical systems.

This paper presents a framework for estimating the remaining useful life (RUL) of mechanical systems. The framework consists of a multi-layer perceptron and an evolutionary algorithm for optimizing the data-related parameters. The framework makes use of a strided time window along with a piecewise linear model to estimate the RUL for each mechanical component. Tuning the data-related parameters in the optimization framework allows for the use of simple models, e.g. neural networks with few hidden layers and...

Photomontage detection using steganography technique based on a neural network.

This article presents a steganographic method StegoNN based on neural networks. The method is able to identify a photomontage from presented signed images. Unlike other academic approaches using neural networks primarily as classifiers, the StegoNN method uses the characteristics of neural networks to create suitable attributes which are then necessary for subsequent detection of modified photographs. This also results in a fact that if an image is signed by this technique, the detection of modifications do...

Flexible non-greedy discriminant subspace feature extraction.

Recently, L-norm-based non-greedy linear discriminant analysis (NLDA-L) for feature extraction has been shown to be effective for dimensionality reduction, which obtains projection vectors by a non-greedy algorithm. However, it usually acquires unsatisfactory performances due to the utilization of L-norm distance measurement. Therefore, in this brief paper, we propose a flexible non-greedy discriminant subspace feature extraction method, which is an extension of NLDA-L by maximizing the ratio of L-norm inte...

The place cell activity is information-efficient constrained by energy.

Spatial representation is a crucial function of animal's brain. However, there is still no uniform explanation of how the spatial code is formed in different dimensional spaces to date. The main reason why place cell exhibits unique activity pattern is that the animal needs to retrieve and process spatial information. In this paper, we constructed a constrained optimization model based on information theory to explain the place field formation across species in different dimensional spaces. We proposed the ...

Phase relations of theta oscillations in a computer model of the hippocampal CA1 field: Key role of Schaffer collaterals.

The hippocampal theta rhythm (4-12 Hz) is one of the most important electrophysiological processes in the hippocampus, it participates in cognitive hippocampal functions, such as navigation in space, novelty detection, and declarative memory. We use neural network modeling to study the mechanism of theta rhythm emergence in the CA1 microcircuitry. Our model of the CA1 field includes biophysical representation of major cell types related to the theta rhythm emergence: excitatory pyramidal cells and two types...

Fixed-time pinning-controlled synchronization for coupled delayed neural networks with discontinuous activations.

This paper deals with the fixed-time synchronization problem of coupled delayed neural networks with discontinuous activations. Based on pinning control, a discontinuous controller is firstly proposed to guarantee that coupled neural networks achieve synchronization with a desired trajectory in finite time. Then, a discontinuous fixed-time controller is designed. With the fixed-time controller, the settling time can be estimated regardless of initial conditions. By providing a topology-dependent Lyapunov fu...

Deep neural-kernel blocks.

This paper introduces novel deep architectures using the hybrid neural-kernel core model as the first building block. The proposed models follow a combination of a neural networks based architecture and a kernel based model enriched with pooling layers. In particular, in this context three kernel blocks with average, maxout and convolutional pooling layers are introduced and examined. We start with a simple merging layer which averages the output of the previous representation layers. The maxout layer on th...

Continuous learning in single-incremental-task scenarios.

It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LW...

Identification of piecewise linear dynamical systems using physically-interpretable neural-fuzzy networks: Methods and applications to origami structures.

Self-locking origami structures are characterized by their piecewise linear constitutive relations between force and deformation, which, in practice, are always completely opaque and unmeasurable: the number of piecewise segments, the positions of non-smooth points, and the linear parameters of each segment are unknown a priori. However, acquiring this information is of fundamental importance for understanding the origami structure's dynamic folding process and predicting its dynamic behaviors. This, theref...

Stability of stochastic impulsive reaction-diffusion neural networks with S-type distributed delays and its application to image encryption.

In this paper, we study stochastic impulsive reaction-diffusion neural networks with S-type distributed delays, aiming to obtain the sufficient conditions for global exponential stability. First, an impulsive inequality involving infinite delay is introduced and the asymptotic behaviour of its solution is investigated by the truncation method. Then, global exponential stability in the mean-square sense of the stochastic impulsive reaction-diffusion system is studied by constructing a simple Lyapunov-Krasovs...

On-line prediction of ferrous ion concentration in goethite process based on self-adjusting structure RBF neural network.

Outlet ferrous ion concentration is an essential indicator to manipulate the goethite process in the zinc hydrometallurgy plant. However, it cannot be measured on-line, which leads to the delay of this feedback information. In this study, a self-adjusting structure radial basis function neural network (SAS-RBFNN) is developed to predict the outlet ferrous ion concentration on-line. First, a supervised cluster algorithm is proposed to initialize the RBFNN. Then, the network structure is adjusted by the devel...

An optimal time interval of input spikes involved in synaptic adjustment of spike sequence learning.

The supervised learning methods for spiking neurons based on temporal encoding are important foundation for the development of spiking neural networks. During the learning process, the synaptic weights of a spiking neuron are adjusted to make the neuron emit a specific spike train. Because various learning methods use the information of input spikes to calculate the adjustment of synaptic weights, how many input spikes participated in the calculation is a critical factor that can influence learning performa...

Semi-supervised deep learning of brain tissue segmentation.

Brain image segmentation is of great importance not only for clinical use but also for neuroscience research. Recent developments in deep neural networks (DNNs) have led to the application of DNNs to brain image segmentation, which required extensive human annotations of whole brain images. Annotating three-dimensional brain images requires laborious efforts by expert anatomists because of the differences among images in terms of their dimensionality, noise, contrast, or ambiguous boundaries that even preve...

Recent advances in physical reservoir computing: A review.

Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and clas...

Equivalence between dropout and data augmentation: A mathematical check.

The great achievements of deep learning can be attributed to its tremendous power of feature representation, where the representation ability comes from the nonlinear activation function and the large number of network nodes. However, deep neural networks suffer from serious issues such as slow convergence, and dropout is an outstanding method to improve the network's generalization ability and test performance. Many explanations have been given for why dropout works so well, among which the equivalence bet...

Asynchronous event-based sampling data for impulsive protocol on consensus of non-linear multi-agent systems.

In this paper, we discuss the consensus problem of non-linear multi-agent systems where an impulsive protocol with event-based asynchronously sampled data is adopted. Systems that communicate by data asynchronously sampled in limited time intervals are constructed. By separating time instants at which the sampling and communication occur into different ones, resources for such activations that every agent must execute can be reallocated to reduce the system load at communication instants. Event-based scheme...

Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: Deterministic convergence and its application.

Conjugate gradient method has been verified to be one effective strategy for training neural networks due to its low memory requirements and fast convergence. In this paper, we propose an efficient conjugate gradient method to train fully complex-valued network models in terms of Wirtinger differential operator. Two ways are adopted to enhance the training performance. One is to construct a sufficient descent direction during training by designing a fine tuning conjugate coefficient. Another technique is to...

Flexible unsupervised feature extraction for image classification.

Dimensionality reduction is one of the fundamental and important topics in the fields of pattern recognition and machine learning. However, most existing dimensionality reduction methods aim to seek a projection matrix W such that the projection Wx is exactly equal to the true low-dimensional representation. In practice, this constraint is too rigid to well capture the geometric structure of data. To tackle this problem, we relax this constraint but use an elastic one on the projection with the aim to revea...

Short-term cognitive networks, flexible reasoning and nonsynaptic learning.

While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive Maps (FCMs) are recurrent neural networks that can be exploited towards this goal because of their flexibility to handle external knowledge. However, FCMs suffer from a number of issues that range from the limited prediction horizon to the absence of theoretically sound lea...


Advertisement
Quick Search
Advertisement
Advertisement