公开(公告)号：US09102750B2

公开(公告)日：2015-08-11

申请号：US14171932

申请日：2014-02-04

Applicant: Stowers Institute for Medical Research

Inventor： Arcady Mushegian ,  Congrong Yu ,  Joel Schwartz ,  Limei Ma

IPC: C07K14/435

CPC classification number: C07K14/43504

Abstract: The present invention provides compositions, combinations, methods, sequences and kits for use of novel fluorescent proteins derived from the genus Branchiostoma. Specifically, polynucleotide and polypeptide sequences encoding fluorescent proteins isolated from Branchiostoma floridae, including harmonized sequences, which permit enhanced expression of the encoded polypeptides in mammalian cells in vivo are provided.

Abstract translation: 本发明提供了用于衍生自分枝杆菌属的新型荧光蛋白的组合物，组合，方法，序列和试剂盒。 具体地说，提供了编码从分枝杆菌分离的荧光蛋白的多核苷酸和多肽序列，包括协调序列，其允许体内哺乳动物细胞中编码的多肽的表达增强。

公开(公告)号：US20230360370A1

公开(公告)日：2023-11-09

申请号：US18343557

申请日：2023-06-28

Applicant: STOWERS INSTITUTE FOR MEDICAL RESEARCH

Inventor： Congrong Yu ,  Rishabh Raj

IPC: G06V10/77 ,  G06V10/82

CPC classification number: G06V10/7715 ,  G06V10/82

Abstract: This disclosure relates to improved systems, methods, and techniques for constructing and employing neural network architectures to solve computer vision and other problems. The neural network architectures can have two or three layers with all nodes in the first layer connected to all nodes in the second layer. The nodes in the second layer can be connected to each other. The weights or values of the various connections between these nodes in the first two layers can also be updated between the processing of inputs to the neural network architectures. These neural network architectures do not require extensive training and can learn continuously. Other embodiments are disclosed herein as well.

公开(公告)号：US20230360367A1

公开(公告)日：2023-11-09

申请号：US18343577

申请日：2023-06-28

Applicant: STOWERS INSTITUTE FOR MEDICAL RESEARCH

Inventor： Congrong Yu ,  Rishabh Raj

IPC: G06V10/764 ,  G06V10/82

CPC classification number: G06V10/764 ,  G06V10/82

Abstract: This disclosure relates to improved systems, methods, and techniques for constructing and employing neural network architectures to solve computer vision and other problems. The neural network architectures can have two or three layers with all nodes in the first layer connected to all nodes in the second layer. The nodes in the second layer can be connected to each other. The weights or values of the various connections between these nodes in the first two layers can also be updated between the processing of inputs to the neural network architectures. These neural network architectures do not require extensive training and can learn continuously. Other embodiments are disclosed herein as well.