公开(公告)号：US12128189B2

公开(公告)日：2024-10-29

申请号：US18604162

申请日：2024-03-13

Applicant: CALIFORNIA INSTITUTE OF TECHNOLOGY

Inventor： Tingtao Zhou ,  Xuan Wan ,  Paul W. Sternberg ,  Chiara Daraio ,  Zhengyu Huang ,  Zongyi Li ,  Zhiwei Peng ,  John F. Brady ,  Animashree Anandkumar

IPC: A61M25/00

CPC classification number: A61M25/0017 ,  A61M2025/006

Abstract: Systems and methods for altering the geometry of a fluid channel to prevent upstream mobility of bacteria, using angled obstacles on the interior of the channel that among other things creates vortices that restrict the mobility. An optimized geometry can be realized by an artificial intelligence algorithm or similar methods based on performance of various configurations of obstacle parameters.

公开(公告)号：US12220539B2

公开(公告)日：2025-02-11

申请号：US18896646

申请日：2024-09-25

Applicant: CALIFORNIA INSTITUTE OF TECHNOLOGY

Inventor： Tingtao Zhou ,  Xuan Wan ,  Paul W. Sternberg ,  Chiara Daraio ,  Zhengyu Huang ,  Zongyi Li ,  Zhiwei Peng ,  John F. Brady ,  Animashree Anandkumar

IPC: A61M25/00

Abstract: Systems and methods for altering the geometry of a fluid channel to prevent upstream mobility of bacteria, using angled obstacles on the interior of the channel that among other things creates vortices that restrict the mobility. An optimized geometry can be realized by an artificial intelligence algorithm or similar methods based on performance of various configurations of obstacle parameters.

公开(公告)号：US11693373B2

公开(公告)日：2023-07-04

申请号：US16709775

申请日：2019-12-10

Applicant: California Institute of Technology

Inventor： Guanya Shi ,  Xichen Shi ,  Michael O'Connell ,  Animashree Anandkumar ,  Yisong Yue ,  Soon-Jo Chung

IPC: G05B13/02 ,  G06N3/04 ,  G06N3/084

CPC classification number: G05B13/027 ,  G06N3/04 ,  G06N3/084

Abstract: Systems and methods for learning based control in accordance with embodiments of the invention are illustrated. One embodiment includes a method for training an adaptive controller. The method includes steps for receiving a set of training data that includes several training samples, wherein each training sample includes a state and a true uncertain effect value. The method includes steps for computing an uncertain effect value based on the state, computing a set of one or more losses based on the true uncertain effect value and the computed uncertain effect value, and updating the adaptive controller based on the computed set of losses.

公开(公告)号：US20220165364A1

公开(公告)日：2022-05-26

申请号：US17332951

申请日：2021-05-27

Applicant: California Institute of Technology ,  Entos, Inc.

Inventor： Zhuoran Qiao ,  Animashree Anandkumar ,  Thomas Francis Miller ,  Matthew Gregory Welborn ,  Frederick Roy Manby ,  Feizhi Ding ,  Daniel George Smith ,  Peter John Bygrave ,  Sai Krishna Sirumalla ,  Anders Steen Christensen

IPC: G16C10/00 ,  G16C20/70

Abstract: Systems and methods for determining molecular structures based on atomic-orbital-based features are described. Atomic-orbital-based features can be utilized in combination with machine-learning methods to predict accurate properties, such as quantum mechanical energy, of molecular systems.

公开(公告)号：US20200183339A1

公开(公告)日：2020-06-11

申请号：US16709775

申请日：2019-12-10

Applicant: California Institute of Technology

Inventor： Guanya Shi ,  Xichen Shi ,  Michael O'Connell ,  Animashree Anandkumar ,  Yisong Yue ,  Soon-Jo Chung

IPC: G05B13/02 ,  G06N3/08 ,  G06N3/04

Abstract: Systems and methods for learning based control in accordance with embodiments of the invention are illustrated. One embodiment includes a method for training an adaptive controller. The method includes steps for receiving a set of training data that includes several training samples, wherein each training sample includes a state and a true uncertain effect value. The method includes steps for computing an uncertain effect value based on the state, computing a set of one or more losses based on the true uncertain effect value and the computed uncertain effect value, and updating the adaptive controller based on the computed set of losses.