![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Bifurcation Analysis of Delayed Complex-Valued Neural Network with Diffusions
In this paper, a class of delayed complex-valued neural network with diffusion under Dirichlet boundary conditions is considered. By using the properties of the Laplacian operator and separating the neural net...
-
Article
Dynamic Optimization of Neuron Systems with Leakage Delay and Distributed Delay via Hybrid Control
This paper proposes a neuron system with both leakage delay and distributed delay. Typical dynamics including the local stability and Hopf bifurcation analysis are investigated. Then, a hybrid controller is de...
-
Article
Online Learning for Time Series Prediction of AR Model with Missing Data
Recently online learning algorithm is applied to time series prediction with missing data without the strict assumption on the noise terms. The existing algorithm only uses the observed data to predict time se...
-
Article
Hessian Regularized Distance Metric Learning for People Re-Identification
Distance metric learning is a vital issue in people re-identification. Although numerous algorithms have been proposed, it is still challenging especially when the labeled information is few. Manifold regulari...
-
Article
Domain Adaptation with Few Labeled Source Samples by Graph Regularization
Domain Adaptation aims at utilizing source data to establish an exact model for a related but different target domain. In recent years, many effective models have been proposed to propagate label information a...
-
Article
A Feature Selection Algorithm Based on Equal Interval Division and Minimal-Redundancy–Maximal-Relevance
Minimal-redundancy–maximal-relevance (mRMR) algorithm is a typical feature selection algorithm. To select the feature which has minimal redundancy with the selected features and maximal relevance with the clas...
-
Article
Feature-Based Learning in Drug Prescription System for Medical Clinics
Rapid increases in data volume and variety pose a challenge to safe drug prescription for health professionals like doctors and dentists. This is addressed by our study, which presents innovative approaches in...
-
Article
Output Layer Multiplication for Class Imbalance Problem in Convolutional Neural Networks
Convolutional neural networks (CNNs) have demonstrated remarkable performance in the field of computer vision. However, they are prone to suffer from the class imbalance problem, in which the number of some cl...
-
Article
Event-Based Projective Synchronization for Different Dimensional Complex Dynamical Networks with Unknown Dynamics by Using Data-Driven Scheme
In this paper, the projective synchronization problem for different dimensional complex networks (CNs) with unknown dynamics is investigated. First, by selecting a projective matrix, the error system is obtain...
-
Article
Filippov FitzHugh-Nagumo Neuron Model with Membrane Potential Threshold Control Policy
In this paper, a novel FitzHugh-Nagumo (FHN) neuron model with membrane potential threshold control policy is proposed. As the membrane potential threshold control policy is a switching control policy, our pro...
-
Article
Semi-Supervised Clustering for Financial Risk Analysis
Many methods have been developed for financial risk analysis. In general, the conventional unsupervised approaches lack sufficient accuracy and semantics for the clustering, and the supervised approaches rely ...
-
Article
An Adaptive Learning Rate Schedule for SIGNSGD Optimizer in Neural Networks
SIGNSGD is able to dramatically improve the performance of training large neural networks by transmitting the sign of each minibatch stochastic gradient, which achieves gradient communication compression and k...
-
Article
A Feature Selection Algorithm Based on Equal Interval Division and Conditional Mutual Information
The performance of many feature selection algorithms is affected because of ignoring three-dimensional mutual information among features. Three-dimensional mutual information includes conditional mutual inform...
-
Article
Privacy Enhanced Cloud-Based Facial Recognition
Homomorphic encryption is a significant method to protect user privacy in cloud computing environment. Due to the computation efficiency issue, there is still not many homomorphic encryption applications for c...
-
Article
A Robust Cost-Sensitive Feature Selection Via Self-Paced Learning Regularization
Feature selection is a useful and important process, which has a widely use in high-dimensional data processing and artificial intelligence. Its goal is to select a relatively small and representative subset o...
-
Article
BDKM: A Blockchain-Based Secure Deduplication Scheme with Reliable Key Management
Secure deduplication aims to efficiently eliminate redundant data in cloud storage system, where convergent encryption (CE) is widely-used to provide the data confidentiality. As the number of convergent keys ...
-
Article
A Fine-Grained Entity Ty** Method Combined with Features
Using the fine-grained entity ty** method of distant supervision, when assigning type labels to entity mention, since the knowledge base contains all type labels of the entity, noisy labels will be introduce...
-
Article
Triaxial Squeeze Attention Module and Mutual-Exclusion Loss Based Unsupervised Monocular Depth Estimation
Monocular depth estimation plays a crucial role in scene perception and 3D reconstruction. Supervised learning based depth estimation needs vast amounts of ground-truth depth data for training, which seriously...
-
Chapter and Conference Paper
Research on Double Input Electric Load Forecasting Model Based on Feature Fusion
Electric load forecasting is a relatively basic work in the world’s power industry, which has an important impact on the operation of the control power system.
-
Chapter and Conference Paper
Nucleus Beam Search for Machine Translation Decoding
Beam search is the most widely-used decoding algorithm for machine translation. Its success, however, may be attributed to the inadvertent implementation of the Uniform Information Density (UID) hypothesis. Th...