-
1.发明申请公开(公告)号：US20220366253A1
公开(公告)日：2022-11-17
申请号：US17843720
申请日：2022-06-17
Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
Inventor： Aydogan Ozcan , Yair Rivenson , Xing Lin , Deniz Mengu , Yi Luo
Abstract: An all-optical Diffractive Deep Neural Network (D2NN) architecture learns to implement various functions or tasks after deep learning-based design of the passive diffractive or reflective substrate layers that work collectively to perform the desired function or task. This architecture was successfully confirmed experimentally by creating 3D-printed D2NNs that learned to implement handwritten classifications and lens function at the terahertz spectrum. This all-optical deep learning framework can perform, at the speed of light, various complex functions and tasks that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs. In alternative embodiments, the all-optical D2NN is used as a front-end in conjunction with a trained, digital neural network back-end.
-
2.发明授权公开(公告)号：US12086717B2
公开(公告)日：2024-09-10
申请号：US18316474
申请日：2023-05-12
Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
Inventor： Aydogan Ozcan , Yair Rivenson , Xing Lin , Deniz Mengu , Yi Luo
IPC: G06N3/082 , G02B5/18 , G02B27/42 , G06F18/214 , G06F18/2431 , G06N3/04 , G06N3/08 , G06V10/94
CPC classification number: G06N3/082 , G02B5/1866 , G02B27/4205 , G02B27/4277 , G06F18/214 , G06F18/2431 , G06N3/04 , G06N3/08 , G06V10/95
Abstract: An all-optical Diffractive Deep Neural Network (D2NN) architecture learns to implement various functions or tasks after deep learning-based design of the passive diffractive or reflective substrate layers that work collectively to perform the desired function or task. This architecture was successfully confirmed experimentally by creating 3D-printed D2NNs that learned to implement handwritten classifications and lens function at the terahertz spectrum. This all-optical deep learning framework can perform, at the speed of light, various complex functions and tasks that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs. In alternative embodiments, the all-optical D2NN is used as a front-end in conjunction with a trained, digital neural network back-end.
-
3.发明授权公开(公告)号：US11694082B2
公开(公告)日：2023-07-04
申请号：US17843720
申请日：2022-06-17
Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
Inventor： Aydogan Ozcan , Yair Rivenson , Xing Lin , Deniz Mengu , Yi Luo
IPC: G06N3/08 , G06N3/082 , G02B5/18 , G02B27/42 , G06N3/04 , G06V10/94 , G06F18/214 , G06F18/2431
CPC classification number: G06N3/082 , G02B5/1866 , G02B27/4205 , G02B27/4277 , G06F18/214 , G06F18/2431 , G06N3/04 , G06N3/08 , G06V10/95
Abstract: An all-optical Diffractive Deep Neural Network (D2NN) architecture learns to implement various functions or tasks after deep learning-based design of the passive diffractive or reflective substrate layers that work collectively to perform the desired function or task. This architecture was successfully confirmed experimentally by creating 3D-printed D2NNs that learned to implement handwritten classifications and lens function at the terahertz spectrum. This all-optical deep learning framework can perform, at the speed of light, various complex functions and tasks that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs. In alternative embodiments, the all-optical D2NN is used as a front-end in conjunction with a trained, digital neural network back-end.
-
4.发明公开公开(公告)号：US20230401447A1
公开(公告)日：2023-12-14
申请号：US18316474
申请日：2023-05-12
Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
Inventor： Aydogan Ozcan , Yair Rivenson , Xing Lin , Deniz Mengu , Yi Luo
IPC: G06N3/082 , G02B5/18 , G02B27/42 , G06N3/04 , G06N3/08 , G06V10/94 , G06F18/214 , G06F18/2431
CPC classification number: G06N3/082 , G02B5/1866 , G02B27/4205 , G02B27/4277 , G06N3/04 , G06N3/08 , G06V10/95 , G06F18/214 , G06F18/2431
Abstract: An all-optical Diffractive Deep Neural Network (D2NN) architecture learns to implement various functions or tasks after deep learning-based design of the passive diffractive or reflective substrate layers that work collectively to perform the desired function or task. This architecture was successfully confirmed experimentally by creating 3D-printed D2NNs that learned to implement handwritten classifications and lens function at the terahertz spectrum. This all-optical deep learning framework can perform, at the speed of light, various complex functions and tasks that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs. In alternative embodiments, the all-optical D2NN is used as a front-end in conjunction with a trained, digital neural network back-end.
-
-
-
Search Results
4
records
(took 0.017 seconds)
