A New Adaptive Feedback Learning Algorithm for Multitask Learning

2012 ◽  
Author(s):  
Zhenxing Li ◽  
Yong Qi ◽  
Weihua Li
Keyword(s):  
Learning Algorithm ◽  
Multitask Learning ◽  
Adaptive Feedback ◽  
Feedback Learning

scholarly journals Remote Judgment Method of Painting Image Style Plagiarism Based on Wireless Network Multitask Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Zhijun Wang
Keyword(s):  
Wireless Network ◽  
Kernel Function ◽  
Digital Image ◽  
Learning Algorithm ◽  
Deep Level ◽  
Multitask Learning ◽  
Experimental Results ◽  
Spatial Consistency ◽  
Discrimination Rate ◽  
Edge Sampling

Since the artistry of the work cannot be accurately described, the identification of reproducible plagiarism is more difficult. The identification of reproducible plagiarism of digital image works requires in-depth research on the artistry of artistic works. In this paper, a remote judgment method for plagiarism of painting image style based on wireless network multitask learning is proposed. According to this new method, the uncertainty of painting image samples is removed based on multitask learning algorithm edge sampling. The deep-level details of the painting image are extracted through the multitask classification kernel function, and most of the pixels in the image are eliminated. When the clustering density is greater than the judgment threshold, it can be considered that the two images have spatial consistency. It can also be judged based on this that the two images are similar, that is, there is plagiarism in the painting. The experimental results show that the discrimination rate is always close to 100%, the misjudgment rate of plagiarism of painting images has been reduced, and the various indicators in the discrimination process are the lowest, which fully shows that a very satisfactory discrimination result can be obtained.

Adaptive Feedback Linearization Control of SISO Nonlinear Processes Using a Self-Generating Neural Network-Based Approach

2011 ◽  
Vol 6 (1) ◽  
Author(s):  
Karim Salahshoor ◽  
Amin Sabet Kamalabady
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Adaptive Control ◽  
Feedback Linearization ◽  
Learning Algorithm ◽  
Rbf Neural Networks ◽  
Adaptive Feedback ◽  
Control Scheme ◽  
Feedback Linearization Control ◽  
Adaptive Control Scheme

This paper presents a new adaptive control scheme based on feedback linearization technique for single-input, single-output (SISO) processes with nonlinear time-varying dynamic characteristics. The proposed scheme utilizes a modified growing and pruning radial basis function (MGAP-RBF) neural network (NN) to adaptively identify two self-generating RBF neural networks for online realization of a well-known affine model structure. An extended Kalman filter (EKF) learning algorithm is developed for parameter adaptation of the MGAP-RBF neural networks. The MGAP-RBF growing and pruning criteria have been endeavored to enhance its performance for online dynamic model identification purposes. A stability analysis has been provided to ensure the asymptotic convergence of the proposed adaptive control scheme using Lyapunov criterion. Capabilities of the adaptive feedback linearization control scheme is evaluated on two nonlinear CSTR benchmark processes, demonstrating good performances for both set-point tracking and disturbance rejection objectives.

scholarly journals Confidence Weighted Multitask Learning

2019 ◽  
Vol 33 ◽  
pp. 5636-5643
Author(s):  
Peng Yang ◽  
Peilin Zhao ◽  
Jiayu Zhou ◽  
Xin Gao
Keyword(s):  
Gaussian Distribution ◽  
Learning Process ◽  
Learning Algorithm ◽  
Multitask Learning ◽  
Local Component ◽  
Label Prediction ◽  
Learning Efficacy ◽  
Regret Bounds ◽  
The Mean ◽  
Theoretical Results

Traditional online multitask learning only utilizes the firstorder information of the datastream. To remedy this issue, we propose a confidence weighted multitask learning algorithm, which maintains a Gaussian distribution over each task model to guide online learning process. The mean (covariance) of the Gaussian Distribution is a sum of a local component and a global component that is shared among all the tasks. In addition, this paper also addresses the challenge of active learning on the online multitask setting. Instead of requiring labels of all the instances, the proposed algorithm determines whether the learner should acquire a label by considering the confidence from its related tasks over label prediction. Theoretical results show the regret bounds can be significantly reduced. Empirical results demonstrate that the proposed algorithm is able to achieve promising learning efficacy, while simultaneously minimizing the labeling cost.

scholarly journals Lung and Tumor Characterization in the Machine Learning Era

2021 ◽  
Vol 10 (5) ◽  
pp. 131-134
Author(s):  
R. Subalakshmi ◽  
G. Baskar
Keyword(s):  
Machine Learning ◽  
Feature Fusion ◽  
Learning Algorithm ◽  
Multitask Learning ◽  
Machine Learning Algorithm ◽  
Tumor Characterization ◽  
Feature Representations ◽  
Aided Diagnosis ◽  
Radiology Image

Danger characterization of tumors from radiology image container to be much precise and quicker with computer aided diagnosis (CAD) implements. Tumor portrayal via such devices can likewise empower non-intrusive prognosis, and foster personalized, and treatment arranging as a piece of accuracy medication. In this study , in cooperation machine learning algorithm strategies to better tumor characterization. Our methodological analysis depends on directed erudition for which we exhibit critical increases with machine learning algorithm, particularly by exploitation a 3D Convolutional Neural Network and Transfer Learning. Disturbed by the radiologists' understandings of the outputs, we at that point tell the best way to fuse task subordinate feature representations into a CAD framework by means of a diagram regularized inadequate MultiTask Learning (MTL) system with the help of feature fusion.

scholarly journals Clinical outcome prediction from analysis of microelectrode recordings using deep learning in subthalamic deep brain stimulation for Parkinson`s disease

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244133
Author(s):  
Kwang Hyon Park ◽  
Sukkyu Sun ◽  
Yong Hoon Lim ◽  
Hye Ran Park ◽  
Jae Meen Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Deep Brain Stimulation ◽  
Clinical Outcome ◽  
General Anesthesia ◽  
Brain Stimulation ◽  
Learning Algorithm ◽  
Multitask Learning ◽  
Stn Dbs ◽  
Updrs Part ◽  
Deep Brain

Background Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for improving the motor symptoms of advanced Parkinson’s disease (PD). Accurate positioning of the stimulation electrodes is necessary for better clinical outcomes. Objective We applied deep learning techniques to microelectrode recording (MER) signals to better predict motor function improvement, represented by the UPDRS part III scores, after bilateral STN DBS in patients with advanced PD. If we find the optimal stimulation point with MER by deep learning, we can improve the clinical outcome of STN DBS even under restrictions such as general anesthesia or non-cooperation of the patients. Methods In total, 696 4-second left-side MER segments from 34 patients with advanced PD who underwent bilateral STN DBS surgery under general anesthesia were included. We transformed the original signal into three wavelets of 1–50 Hz, 50–500 Hz, and 500–5,000 Hz. The wavelet-transformed MER was used for input data of the deep learning. The patients were divided into two groups, good response and moderate response groups, according to DBS on to off ratio of UPDRS part III score for the off-medication state, 6 months postoperatively. The ratio were used for output data in deep learning. The Visual Geometry Group (VGG)-16 model with a multitask learning algorithm was used to estimate the bilateral effect of DBS. Different ratios of the loss function in the task-specific layer were applied considering that DBS affects both sides differently. Results When we divided the MER signals according to the frequency, the maximal accuracy was higher in the 50–500 Hz group than in the 1–50 Hz and 500–5,000 Hz groups. In addition, when the multitask learning method was applied, the stability of the model was improved in comparison with single task learning. The maximal accuracy (80.21%) occurred when the right-to-left loss ratio was 5:1 or 6:1. The area under the curve (AUC) was 0.88 in the receiver operating characteristic (ROC) curve. Conclusion Clinical improvements in PD patients who underwent bilateral STN DBS could be predicted based on a multitask deep learning-based MER analysis.

MARES: multitask learning algorithm for Web-scale real-time event summarization

2018 ◽  
Vol 22 (2) ◽  
pp. 499-515 ◽  
Author(s):  
Min Yang ◽  
Wenting Tu ◽  
Qiang Qu ◽  
Kai Lei ◽  
Xiaojun Chen ◽  
...  
Keyword(s):  
Real Time ◽  
Learning Algorithm ◽  
Multitask Learning ◽  
Event Summarization

scholarly journals Maneuvering Target Tracking Using Simultaneous Optimization and Feedback Learning Algorithm Based on Elman Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1596 ◽  
Author(s):  
Huajun Liu ◽  
Liwei Xia ◽  
Cailing Wang
Keyword(s):  
Neural Network ◽  
Target Tracking ◽  
Unscented Kalman Filter ◽  
Learning Algorithm ◽  
Simultaneous Optimization ◽  
Optimization Strategy ◽  
Maneuvering Target Tracking ◽  
Elman Neural Network ◽  
Maneuvering Target ◽  
Feedback Learning

Tracking maneuvering targets is a challenging problem for sensors because of the unpredictability of the target’s motion. Unlike classical statistical modeling of target maneuvers, a simultaneous optimization and feedback learning algorithm for maneuvering target tracking based on the Elman neural network (ENN) is proposed in this paper. In the feedback strategy, a scale factor is learnt to adaptively tune the dynamic model’s error covariance matrix, and in the optimization strategy, a corrected component of the state vector is learnt to refine the final state estimation. These two strategies are integrated in an ENN-based unscented Kalman filter (UKF) model called ELM-UKF. This filter can be trained online by the filter residual, innovation and gain matrix of the UKF to simultaneously achieve maneuver feedback and an optimized estimation. Monte Carlo experiments on synthesized radar data showed that our algorithm had better performance on filtering precision compared with most maneuvering target tracking algorithms.

Sign in / Sign up

Export Citation Format

Share Document