-
公开(公告)号：US20220299948A1
公开(公告)日：2022-09-22
申请号：US17572606
申请日：2022-01-10
Inventor： Sang Wan LEE , Dongjae KIM
Abstract: Various embodiments relate to an electronic device for brain-inspired adaptive control of resolving the bias-variance tradeoff and a method thereof. The method may include estimating a prediction error baseline for an environment, based on a first prediction error of a low-variance intelligent system for the environment and a second prediction error of a low-bias intelligent system for the environment; and implementing an adaptive control system by combining the low-variance intelligent system and the low-bias intelligent system based on the estimated prediction error baseline.
-
公开(公告)号：US20220207360A1
公开(公告)日：2022-06-30
申请号：US17547166
申请日：2021-12-09
Inventor： Sang Wan LEE , Geon Yeong PARK
Abstract: Various embodiments relate to a computer system for multi-source domain adaptative training based on a single neural network without overfitting and a method thereof. The various embodiments may configured to regularize data sets of a plurality of domains, extract information shared between the regularized data sets, and implement a training model by performing training based on the extracted information.
-
公开(公告)号：US20220067487A1
公开(公告)日：2022-03-03
申请号：US17411853
申请日：2021-08-25
Inventor： Sang Wan LEE , Chang Hwa LEE
Abstract: Various embodiments provide an electronic device for generating data and improving task performance by using only a very small amount of data without prior knowledge of an associative domain and an operating method thereof. According to various embodiments, the electronic device may be configured to construct a plurality of data pairs from at least three data points, acquire relative information between the data points with respect to each of the data pairs, and learn a transformation function between the data points based on the relative information. According to various embodiments, the transformation function which can be learnt without a data overfitting problem even in a very small amount of data can be provided.
-
Patent Agency Ranking
4.发明申请公开(公告)号：US20240403606A1
公开(公告)日：2024-12-05
申请号：US18541962
申请日：2023-12-15
Inventor： Sang Wan LEE , Yujin Cha
Abstract: Disclosed is a method and system for estimating output uncertainty of a deterministic artificial neural network (ANN). An output uncertainty estimation method of a deterministic ANN may include generating a dataset by combining training data used for training of a deterministic ANN model and output of the deterministic ANN model trained with the training data; and estimating output uncertainty of the deterministic ANN model based on output for test data of a proxy Gaussian process model trained through the generated dataset.
-
公开(公告)号：US20220164948A1
公开(公告)日：2022-05-26
申请号：US17229747
申请日：2021-04-13
Inventor： Sang Wan LEE , Young Ho KANG , Fengkai KE
Abstract: Provided are a computer system for automatically searching for a mental disorder diagnosis protocol and an method thereof that may determine at least one test region to be examined for a predetermined mental disorder diagnosis in a brain image of a patient based on a first artificial neural network, may determine a test process for the mental disorder diagnosis for the patient based on a second artificial neural network, and may provide a test protocol for the mental disorder diagnosis for the patient based on the test region and the test process. The computer system may visualize at least one of a position, a shape, a size, and an importance of the test region in the brain image. The test process may include test order of a plurality of test stages in which the brain image is to be used for the mental disorder diagnosis.
-
6.发明公开公开(公告)号：US20230215133A1
公开(公告)日：2023-07-06
申请号：US17901148
申请日：2022-09-01
Inventor： Sang Wan LEE , Shin Young JOO
CPC classification number: G06V10/70 , G06N3/0454
Abstract: Disclosed is a method for self-supervised reinforcement learning (RL) by analogy executed by a computer device, the method including configuring a self-supervised RL with analogical reasoning (SRAR) model; and learning a policy for problem solving in a situation in which a task domain changes using the configured SRAR model.
-
公开(公告)号：US20220172125A1
公开(公告)日：2022-06-02
申请号：US17404156
申请日：2021-08-17
Inventor： Sang Wan LEE , Yujin CHA
Abstract: Provided is a computer system and method for inferring a human uncertainty that may estimate a predictive uncertainty of a human about input data based on a proxy ensemble network configured for each individual human and may infer an uncertainty range including the predictive uncertainty for the human. The proxy ensemble network may be configured using uncertainty measurement values for the respective data items evaluated by the human.
-
公开(公告)号：US20210279547A1
公开(公告)日：2021-09-09
申请号：US17141841
申请日：2021-01-05
Inventor： Sang Wan LEE , Dongjae KIM , Jae Hoon SHIN
Abstract: Provided are an electronic device for precision behavior profiling for transplanting humans' intelligence into AI and an operating method thereof, which may be configured to theoretically design at least one environmental factor, fit a first level model from human's processing data for a task based on the environmental factor, fit a second level model from processing data of the first level model for the task based on the environmental factor, and determine the second level model as a transplant model for humans' intelligence based on a correlation between the first level model and the second level model through profiling for the first level model and the second level model. According to various embodiments, the human's processing data may include at least any one of behavioral data or a brain signal generated while the human processes the task.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.017 seconds)
