TY - PAT
T1 - Deep model reference adaptive controller
AU - Chowdhary, Girish
AU - Joshi, Girish
AU - Virdi, Jasvir
N1 - STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT This invention was made with government support under contract DE-NA-0003525 awarded by the U.S. Department of Energy's National Nuclear Security Administration. The government has certain rights in the invention.
PY - 2025/3/25
Y1 - 2025/3/25
N2 - Aspects of the subject disclosure may include, for example, determining, at a slower time-scale, inner layer weights of an inner layer of a deep neural network; providing periodically to an outer layer of the deep neural network from the inner layer, a feature vector based upon the inner layer weights; and determining, at a faster time-scale, outer layer weights of the outer layer, wherein the outer layer weights are determined in accordance with a Model Reference Adaptive Control (MRAC) update law that is based upon the feature vector from the inner layer, and wherein the outer layer weights are determined more frequently than the inner layer weights. Other embodiments are disclosed.
AB - Aspects of the subject disclosure may include, for example, determining, at a slower time-scale, inner layer weights of an inner layer of a deep neural network; providing periodically to an outer layer of the deep neural network from the inner layer, a feature vector based upon the inner layer weights; and determining, at a faster time-scale, outer layer weights of the outer layer, wherein the outer layer weights are determined in accordance with a Model Reference Adaptive Control (MRAC) update law that is based upon the feature vector from the inner layer, and wherein the outer layer weights are determined more frequently than the inner layer weights. Other embodiments are disclosed.
M3 - Patent
M1 - 12259735
Y2 - 2021/06/22
ER -