A5102026457- Complexity and Algorithms in Graphs
- Stochastic Gradient Optimization Techniques
- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Privacy-Preserving Technologies in Data
- Remote Sensing and Land Use
- Neural Networks and Applications
- Advanced Algorithms and Applications
- Machine Learning and ELM
Anhui University of Technology
2021
Underwater target detection (UTD) is one of the most attractive research topics in hyperspectral imagery (HSI) processing. Most existing methods are presented to predict signatures desired targets an underwater context but ignore depth information which position-sensitive and contributes significantly distinguishing background pixels. So as take full advantage information, this paper a self-improving framework proposed perform joint estimation detection, exploits results alternately boost...
In recent years, the amount of available data is growing exponentially, and large-scale becoming ubiquitous. Machine learning a key to deriving insight from this deluge data. paper, we focus on analysis, especially classification data, propose an online conjugate gradient (CG) descent algorithm. Our algorithm draws improved Fletcher-Reeves (IFR) CG method proposed in Jiang Jian[13] as well approach reduce variance for stochastic Johnson Zhang [15]. theory, prove that achieves linear...
Aiming at the problem that it is easily trapped into a local optimum when applying steepest gradient descent method to train feedforward neural network, in this paper we propose an algorithm based on non-monotone conjugate optimize training process of network used multiple classification task. More specifically, proposed combines and linear search technique, makes full use information loss function its gradients, resulting faster convergence rate without increasing memory consumption than...