Semisupervised Multitask Learning With Gaussian Processes

Skolidis, Grigorios; Sanguinetti, Guido

doi:10.1109/tnnls.2013.2272403

Cited by 20 publications

(31 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning addresses the problems where, for each input x, there is a corresponding observed output y, whereas, in the case of the latter two categories, this correspondence cannot be found due to the lack of data. Unsupervised learning explores interesting patterns in the input data without a need for explicit supervision [122]. Reinforcement learning assumes that the dynamics of the system under consideration follows a particular class of model [123].…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

2018

View full text Add to dashboard Cite

Abstract:Retinal vessels identification and localization aim to separate the different retinal vasculature structure tissues, either wide or narrow ones, from the fundus image background and other retinal anatomical structures such as optic disc, macula, and abnormal lesions. Retinal vessels identification studies are attracting more and more attention in recent years due to non-invasive fundus imaging and the crucial information contained in vasculature structure which is helpful for the detection and diagnosis of a variety of retinal pathologies included but not limited to: Diabetic Retinopathy (DR), glaucoma, hypertension, and Age-related Macular Degeneration (AMD). With the development of almost two decades, the innovative approaches applying computer-aided techniques for segmenting retinal vessels are becoming more and more crucial and coming closer to routine clinical applications. The purpose of this paper is to provide a comprehensive overview for retinal vessels segmentation techniques. Firstly, a brief introduction to retinal fundus photography and imaging modalities of retinal images is given. Then, the preprocessing operations and the state of the art methods of retinal vessels identification are introduced. Moreover, the evaluation and validation of the results of retinal vessels segmentation are discussed. Finally, an objective assessment is presented and future developments and trends are addressed for retinal vessels identification techniques.

show abstract

Section: Machine Learning Techniquesmentioning

confidence: 99%

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

2018

View full text Add to dashboard Cite

show abstract

“…3 we include the real part of the prediction in (14) and the grey shaded area that represents the point-wise mean plus and minus two times the standard deviation. The mean of the prediction for the proper case (14) Proper CGPR mean (20) Noisy training samples Proper CGPR mean (20) Training samples Fig. 4: Imaginary parts of the sample function of the process f (x), the predictive CGPR mean (14), and the predictive mean for the proper CGPR case (20), versus the real part of the input x r , for x j = −0.1515.…”

Section: Hyperparameters Estimationmentioning

confidence: 99%

“…The mean of the prediction for the proper case (14) Proper CGPR mean (20) Noisy training samples Proper CGPR mean (20) Training samples Fig. 4: Imaginary parts of the sample function of the process f (x), the predictive CGPR mean (14), and the predictive mean for the proper CGPR case (20), versus the real part of the input x r , for x j = −0.1515. in (20) is plotted as a dashed line.…”

Section: Hyperparameters Estimationmentioning

confidence: 99%

“…The Gaussian process (GP) [16] is a Bayesian nonparametric framework for inference. It has has attracted increasing attention from the machine learning community for its many applications, such as in regression, classification [17], [18], adaptive control [19], multitask learning [20], or data association [21], among others. Gaussian processes for regression (GPR) [16], [22], [23] are kernel methods that provide a full conditional statistical description for the predicted variable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Complex Gaussian Processes for Regression

Boloix-Tortosa

Murillo-Fuentes

Payán-Somet

et al. 2018

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

In this paper, we propose a novel Bayesian solution for nonlinear regression in complex fields. Previous solutions for kernels methods usually assume a complexification approach, where the real-valued kernel is replaced by a complex-valued one. This approach is limited. Based on the results in complex-valued linear theory and Gaussian random processes, we show that a pseudo-kernel must be included. This is the starting point to develop the new complex-valued formulation for Gaussian process for regression (CGPR). We face the design of the covariance and pseudo-covariance based on a convolution approach and for several scenarios. Just in the particular case where the outputs are proper, the pseudo-kernel cancels. Also, the hyperparameters of the covariance can be learned maximizing the marginal likelihood using Wirtinger's calculus and patterned complex-valued matrix derivatives. In the experiments included, we show how CGPR successfully solves systems where the real and imaginary parts are correlated. Besides, we successfully solve the nonlinear channel equalization problem by developing a recursive solution with basis removal. We report remarkable improvements compared to previous solutions: a 2-4-dB reduction of the mean squared error with just a quarter of the training samples used by previous approaches.

show abstract

“…The Gaussian process is drawing more attention from the category of different approaches in the machine learning due to its inherent compatibility for widespread application likewise in regression, classification, 26 adaptive control, multiclass learning, 27 data association, and a semi-definite programming solution. 28 Grande et al 29 explain the Gaussian process regression (GPR) framework as a complete mathematical explanation regarding the usual complex value solution.…”

mentioning

confidence: 99%

A novel approach to estimate fault location in current source converter–based HVDC transmission line by Gaussian process regression

Ankar

Yadav

2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary This paper presents a novel approach to estimate fault location in current source converter (CSC) based bipolar high‐voltage direct current (HVDC) transmission line by Gaussian process regression (GPR) algorithm. The proposed work uses AC voltage, DC current, and voltage on both poles available at only the rectifier end of the line as inputs to the proposed GPR model. A large number of simulations have been done using PSCAD to manifest the effectiveness and accuracy of the proposed algorithm to locate all types of faults in HVDC model. The attainment of the proposed algorithm is measured in terms of mean percentage error of 0.0414%, which conveys a very lesser value in comparison with traditional and recently studied methods in the literature. The validity of the efficacy of the GPR‐based scheme has been established by considering the effect of variation in the fault resistance and the presence of noise. The advantage of this scheme is that it does not require any communication link as it uses only rectifier end measurements.

show abstract

Semisupervised Multitask Learning With Gaussian Processes

Cited by 20 publications

References 25 publications

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

Complex Gaussian Processes for Regression

A novel approach to estimate fault location in current source converter–based HVDC transmission line by Gaussian process regression

Contact Info

Product

Resources

About