journal
MENU ▼
Read by QxMD icon Read
search

Neural Networks: the Official Journal of the International Neural Network Society

journal
https://read.qxmd.com/read/30753963/a-stochastic-variational-framework-for-recurrent-gaussian-processes-models
#1
César Lincoln C Mattos, Guilherme A Barreto
Gaussian Processes (GPs) models have been successfully applied to the problem of learning from sequential observations. In such context, the family of Recurrent Gaussian Processes (RGPs) have been recently introduced with a specifically designed structure to handle dynamical data. However, RGPs present a limitation shared by most GP approaches: they become computationally infeasible when facing very large datasets. In the present work, with the aim of improving scalability, we modify the original variational approach used with RGPs in order to enable inference via stochastic mini-batch optimization, giving rise to the Stochastic Recurrent Variational Bayes (S-REVARB) framework...
February 1, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30753962/a-robust-outlier-control-framework-for-classification-designed-with-family-of-homotopy-loss-function
#2
Yidan Wang, Liming Yang, Chao Yuan
We propose a new homotopy loss, where practitioners can tune the parameter to derive different loss functions such as l1 -norm loss, logarithmic loss, Geman-Reynolds loss, Geman-McClure loss and correntropy-based loss. Moreover, we illustrate that the proposed loss satisfies Fisher consistency, and we analyze the robustness of the proposed homotopy loss from different perspectives: M-estimation and adversarial perturbations. Then, we represent a new evaluation standard to measure robustness and demonstrate its upper bound to ensure the validity of this measure...
January 30, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30753964/disturbance-and-uncertainty-rejection-performance-for-fractional-order-complex-dynamical-networks
#3
P Selvaraj, O M Kwon, R Sakthivel
This paper investigates the synchronization issue for a family of time-delayed fractional-order complex dynamical networks (FCDNs) with time delay, unknown bounded uncertainty and disturbance. A novel fractional uncertainty and disturbance estimator (FUDE) based feedback control strategy is proposed to not only synchronize the considered FCDNs but also guaranteeing the precise rejection of unmodelled system uncertainty and external disturbance. Especially, in FUDE-based approach, model uncertainties and external disturbance are integrated as a lumped disturbance and it does not require a completely known system model or a disturbance model...
January 29, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30735914/dreaming-neural-networks-forgetting-spurious-memories-and-reinforcing-pure-ones
#4
Alberto Fachechi, Elena Agliari, Adriano Barra
The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is α∼0.14, far from the theoretical bound for symmetric networks, i.e. α=1. Inspired by sleeping and dreaming mechanisms in mammal brains, we propose an extension of this model displaying the standard on-line (awake) learning mechanism (that allows the storage of external information in terms of patterns) and an off-line (sleep) unlearning&consolidating mechanism (that allows spurious-pattern removal and pure-pattern reinforcement): this obtained daily prescription is able to saturate the theoretical bound α=1, remaining also extremely robust against thermal noise...
January 29, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30716617/robust-dimensionality-reduction-via-feature-space-to-feature-space-distance-metric-learning
#5
Bo Li, Zhang-Tao Fan, Xiao-Long Zhang, De-Shuang Huang
Images are often represented as vectors with high dimensions when involved in classification. As a result, dimensionality reduction methods have to be developed to avoid the curse of dimensionality. Among them, Laplacian eigenmaps (LE) have attracted widespread concentrations. In the original LE, point to point (P2P) distance metric is often adopted for manifold learning. Unfortunately, they show few impacts on robustness to noises. In this paper, a novel supervised dimensionality reduction method, named feature space to feature space distance metric learning (FSDML), is presented...
January 21, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30735913/a-small-world-topology-enhances-the-echo-state-property-and-signal-propagation-in-reservoir-computing
#6
Yuji Kawai, Jihoon Park, Minoru Asada
Cortical neural connectivity has been shown to exhibit a small-world (SW) network topology. However, the role of the topology in neural information processing remains unclear. In this study, we investigated the learning performance of an echo state network (ESN) that includes the SW topology as a reservoir. To elucidate the potential of the SW topology, we limited the numbers of the input and output nodes in the ESN and spatially segregated the output nodes from the input nodes. We tested the ESNs in two benchmark tasks: memory capacity and nonlinear time-series prediction...
January 16, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30690287/image-based-velocity-estimation-of-rock-using-convolutional-neural-networks
#7
Sadegh Karimpouli, Pejman Tahmasebi
Digital images of rock samples have been using extensively in Digital Rock Physics (DRP) to evaluate physical parameters of rock such as permeability, P- and S-wave velocities and formation factor. The parameters are numerically computed by simulation of the corresponding physical processes through segmented image of rock, which provide a direct and accurate evaluation of rock properties. However, recent advances in machine learning and Convolutional Neural Networks (CNN) allow using images as input. Such networks, however, require a considerable number of images as input...
January 9, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30690286/neuo-exploiting-the-sentimental-bias-between-ratings-and-reviews-with-neural-networks
#8
Yuanbo Xu, Yongjian Yang, Jiayu Han, En Wang, Fuzhen Zhuang, Jingyuan Yang, Hui Xiong
Traditional recommender systems rely on user profiling based on either user ratings or reviews through bi-sentimental analysis. However, in real-world scenarios, there are two common phenomena: (1) users only provide ratings for items but without detailed review comments. As a result, the historical transaction data available for recommender systems are usually unbalanced and sparse; (2) in many cases, users' opinions can be better grasped in their reviews than ratings. For the reason that there is always a bias between ratings and reviews, it is really important that users' ratings and reviews should be mutually reinforced to grasp the users' true opinions...
January 8, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30690285/classification-of-gait-patterns-between-patients-with-parkinson-s-disease-and-healthy-controls-using-phase-space-reconstruction-psr-empirical-mode-decomposition-emd-and-neural-networks
#9
Wei Zeng, Chengzhi Yuan, Qinghui Wang, Fenglin Liu, Ying Wang
Parkinson's disease (PD) is a common neurodegenerative disorder that affects human's quality of life, especially leading to locomotor deficits such as postural instability and gait disturbances. Gait signal is one of the best features to characterize and detect movement disorders caused by a malfunction in parts of the brain and nervous system of the patients with PD. Various classification approaches using spatiotemporal gait variables have been presented earlier to classify Parkinson's gait. In this study we propose a novel method for gait pattern classification between patients with PD and healthy controls, based upon phase space reconstruction (PSR), empirical mode decomposition (EMD) and neural networks...
January 6, 2019: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30660101/learning-a-discriminant-graph-based-embedding-with-feature-selection-for-image-categorization
#10
Ruifeng Zhu, Fadi Dornaika, Yassine Ruichek
Graph-based embedding methods are very useful for reducing the dimension of high-dimensional data and for extracting their relevant features. In this paper, we introduce a novel nonlinear method called Flexible Discriminant graph-based Embedding with feature selection (FDEFS). The proposed algorithm aims to classify image sample data in supervised learning and semi-supervised learning settings. Specifically, our method incorporates the Manifold Smoothness, Margin Discriminant Embedding and the Sparse Regression for feature selection...
December 27, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30654138/an-extensive-experimental-survey-of-regression-methods
#11
REVIEW
M Fernández-Delgado, M S Sirsat, E Cernadas, S Alawadi, S Barro, M Febrero-Bande
Regression is a very relevant problem in machine learning, with many different available approaches. The current work presents a comparison of a large collection composed by 77 popular regression models which belong to 19 families: linear and generalized linear models, generalized additive models, least squares, projection methods, LASSO and ridge regression, Bayesian models, Gaussian processes, quantile regression, nearest neighbors, regression trees and rules, random forests, bagging and boosting, neural networks, deep learning and support vector regression...
December 21, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30599419/research-on-a-learning-rate-with-energy-index-in-deep-learning
#12
Huizhen Zhao, Fuxian Liu, Han Zhang, Zhibing Liang
The stochastic gradient descent algorithm (SGD) is the main optimization solution in deep learning. The performance of SGD depends critically on how learning rates are tuned over time. In this paper, we propose a novel energy index based optimization method (EIOM) to automatically adjust the learning rate in the backpropagation. Since a frequently occurring feature is more important than a rarely occurring feature, we update the features to different extents according to their frequencies. We first define an energy neuron model and then design an energy index to describe the frequency of a feature...
December 19, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30682710/deep-learning-in-spiking-neural-networks
#13
REVIEW
Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothée Masquelier, Anthony Maida
In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter...
December 18, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30616099/response-prediction-of-nonlinear-hysteretic-systems-by-deep-neural-networks
#14
Taeyong Kim, Oh-Sung Kwon, Junho Song
Nonlinear hysteretic systems are common in many engineering problems. The maximum response estimation of a nonlinear hysteretic system under stochastic excitations is an important task for designing and maintaining such systems. Although a nonlinear time history analysis is the most rigorous method to accurately estimate the responses in many situations, high computational costs and modelingtime hamper adoption of the approach in a routine engineering practice. Thus, various simplified regression equations are often introduced to replace a nonlinear time history analysis in engineering practices, but the accuracy of the estimated responses is limited...
December 18, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30597446/a-hypothetical-neural-network-model-for-generation-of-human-precision-grip
#15
Yuki Moritani, Naomichi Ogihara
Humans can stably hold and skillfully manipulate an object by coordinated control of a complex, redundant musculoskeletal system. However, how the human central nervous system actually accomplishes precision grip tasks by coordinated control of fingertip forces remains unclear. In the present study, we aimed to construct a hypothetical neural network model that can spontaneously generate humanlike precision grip. The nervous system was modeled as a recurrent neural network model prescribing kinematic and kinetic constraints that must be satisfied in precision grip tasks in the form of energy functions...
December 17, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30616096/particle-swarm-optimization-for-network-based-data-classification
#16
Murillo G Carneiro, Ran Cheng, Liang Zhao, Yaochu Jin
Complex networks provide a powerful tool for data representation due to its ability to describe the interplay between topological, functional, and dynamical properties of the input data. A fundamental process in network-based (graph-based) data analysis techniques is the network construction from original data usually in vector form. Here, a natural question is: How to construct an "optimal" network regarding a given processing goal? This paper investigates structural optimization in the context of network-based data classification tasks...
December 14, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30597445/a-compact-network-learning-model-for-distribution-regression
#17
Connie Khor Li Kou, Hwee Kuan Lee, Teck Khim Ng
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an entire function in a single network node. To that end, we design a compact network representation that encodes and propagates functions in single nodes for the distribution regression task. Our proposed distribution regression network (DRN) achieves higher prediction accuracies while using fewer parameters than traditional neural networks...
December 14, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30594757/synchronization-in-uncertain-fractional-order-memristive-complex-valued-neural-networks-with-multiple-time-delays
#18
Weiwei Zhang, Hai Zhang, Jinde Cao, Fuad E Alsaadi, Dingyuan Chen
This paper considers the global asymptotical synchronization of fractional-order memristive complex-valued neural networks (FOMCVNN), with both parameter uncertainties and multiple time delays. Sufficient conditions of uncertain FOMCVNN, with multiple time delays, are established through the employment of comparison principle and Lyapunov direct method. A numerical example is used to show the effectiveness of the proposed methods.
December 12, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30616095/a-comparison-of-deep-networks-with-relu-activation-function-and-linear-spline-type-methods
#19
Konstantin Eckle, Johannes Schmidt-Hieber
Deep neural networks (DNNs) generate much richer function spaces than shallow networks. Since the function spaces induced by shallow networks have several approximation theoretic drawbacks, this explains, however, not necessarily the success of deep networks. In this article we take another route by comparing the expressive power of DNNs with ReLU activation function to linear spline methods. We show that MARS (multivariate adaptive regression splines) is improper learnable by DNNs in the sense that for any given function that can be expressed as a function in MARS with M parameters there exists a multilayer neural network with O(Mlog(M∕ε)) parameters that approximates this function up to sup-norm error ε...
December 4, 2018: Neural Networks: the Official Journal of the International Neural Network Society
https://read.qxmd.com/read/30562650/ensemble-neural-networks-enn-a-gradient-free-stochastic-method
#20
Yuntian Chen, Haibin Chang, Jin Meng, Dongxiao Zhang
In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are calculated by the ensemble randomized maximum likelihood algorithm (EnRML), which is an inverse modeling method. The ENN is able to simultaneously provide estimations and perform uncertainty quantification since it is built under the Bayesian framework. The ENN is also robust to small training data size because the ensemble of stochastic realizations essentially enlarges the training dataset...
December 3, 2018: Neural Networks: the Official Journal of the International Neural Network Society
journal
journal
29823
1
2
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read
×

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"