The Experts below are selected from a list of 249978 Experts worldwide ranked by ideXlab platform
Xiaocong Yuan - One of the best experts on this subject based on the ideXlab platform.
-
does deep learning always outperform simple linear regression in Optical Imaging
Optics Express, 2020Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
-
does deep learning always outperform simple linear regression in Optical Imaging
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
Shuming Jiao - One of the best experts on this subject based on the ideXlab platform.
-
does deep learning always outperform simple linear regression in Optical Imaging
Optics Express, 2020Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
-
does deep learning always outperform simple linear regression in Optical Imaging
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
Ting Lei - One of the best experts on this subject based on the ideXlab platform.
-
does deep learning always outperform simple linear regression in Optical Imaging
Optics Express, 2020Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
-
does deep learning always outperform simple linear regression in Optical Imaging
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
Jun Feng - One of the best experts on this subject based on the ideXlab platform.
-
does deep learning always outperform simple linear regression in Optical Imaging
Optics Express, 2020Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
-
does deep learning always outperform simple linear regression in Optical Imaging
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
Yang Gao - One of the best experts on this subject based on the ideXlab platform.
-
does deep learning always outperform simple linear regression in Optical Imaging
Optics Express, 2020Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
-
does deep learning always outperform simple linear regression in Optical Imaging
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Shuming Jiao, Yang Gao, Jun Feng, Ting Lei, Xiaocong YuanAbstract:Deep learning has been extensively applied in many Optical Imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in Optical Imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box Optical Imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many Optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.