-
公开(公告)号：US20230186107A1
公开(公告)日：2023-06-15
申请号：US17550551
申请日：2021-12-14
CPC分类号： G06N5/003 , G06K9/6257
摘要： A system and method can be provided for constructing and training a decision tree for machine learning. A training set can be received. The decision tree can be initialized by constructing a root node and a root solver can be trained with the training set. A processor can grow the decision tree by iteratively splitting nodes of the decision tree, where at a node of the decision tree, dimension reduction is performed on features of data of the training set received at the node, and the data having reduced dimension is split based on a routing function, for routing to another node of the decision tree. The dimension reduction and the split can be performed together at the node based on solving a nonlinear optimization problem.
-
公开(公告)号：US20230128821A1
公开(公告)日：2023-04-27
申请号：US17491494
申请日：2021-09-30
发明人： Dzung Tien Phan , Lam Minh Nguyen , Jayant R. Kalagnanam , Chandrasekhara K. Reddy , Srideepika Jayaraman
IPC分类号： G06N20/10
摘要： A computer implemented method of generating a classifier engine for machine learning includes receiving a set of data points. A semi-supervised k-means process is applied to the set of data points from each class. The set of data points in a class is clustered into multiple clusters of data points, using the semi-supervised k-means process. Multi-polytopes are constructed for one or more of the clusters from all classes. A support vector machine (SVM) process is run on every pair of clusters from all classes. Separation hyperplanes are determined for the clustered classes. Labels are determined for each cluster based on the separation by hyperplanes.
-
公开(公告)号：US20240119274A1
公开(公告)日：2024-04-11
申请号：US17951587
申请日：2022-09-23
发明人： Lam Minh Nguyen
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： Select an initial weight vector for a convex optimization sub-problem associated with a neural network having a non-convex network architecture loss surface. With at least one processor, approximate a solution to the convex optimization sub-problem that obtains a search direction, to learn a common classifier from training data. With the at least one processor, update the initial weight vector by subtracting the approximate solution to the convex optimization sub-problem times a first learning rate. With the at least one processor, repeat the approximating and updating steps, for a plurality of iterations, with the updated weight vector from a given one of the iterations taken as the initial weight vector for a next one of the iterations, to obtain a final weight vector for the neural network, until convergence to a global minimum is achieved, to implement the common classifier.
-
公开(公告)号：US20230267339A1
公开(公告)日：2023-08-24
申请号：US17675202
申请日：2022-02-18
发明人： Dzung Tien Phan , Connor Aram Lawless , Jayant R. Kalagnanam , Lam Minh Nguyen , Chandrasekhara K. Reddy
IPC分类号： G06N5/02
CPC分类号： G06N5/022
摘要： In unsupervised interpretable machine learning, one or more datasets having multiple features can be received. A machine can be trained to jointly cluster and interpret resulting clusters of the dataset by at least jointly clustering the dataset into clusters and generating hyperplanes in a multi-dimensional feature space of the dataset, where the hyperplanes separate pairs of the clusters, where a hyperplane separates a pair of clusters. Jointly clustering the dataset into clusters and generating hyperplanes can repeat until convergence, where the clustering in a subsequent iteration uses the generated hyperplanes from a previous iteration to optimize performance of the clustering. The hyperplanes can be adjusted to further improve the performance of the clustering. The clusters and interpretation of the clusters can be provided, where a cluster's interpretation is provided based on hyperplanes that construct a polytope containing the cluster.
-
公开(公告)号：US20230161629A1
公开(公告)日：2023-05-25
申请号：US17534385
申请日：2021-11-23
发明人： Surya Shravan Kumar Sajja , Kanthi Sarpatwar , Lam Minh Nguyen , Yuan Yuan Jia , Stephane Michel , Roman Vaculin
CPC分类号： G06F9/5038 , G06F9/5088 , G06N7/005 , G06F9/5033 , G06F2209/504 , G06F2209/508
摘要： A computer implemented method using an artificial intelligence (A.I.) module to explain large scale scheduling solutions includes receiving an original instance of a resource constrained scheduling problem. The instance includes a set of tasks and a variety of resource requirements and a variety of constraints. An optimizer process determines a schedule for the set of tasks while minimizing a makespan of the schedule. A minimal set of resource links is generated based on resource dependencies between tasks. The resource links are added to the original instance of scheduling problem, as precedence constraints. All the resource constraints are removed from the original instance of the resource constrained scheduling problem. A set of critical tasks is computed using a non-resource constrained critical path. Schedules are provided with an explanation of an optimized order of the set of tasks based on the use of the non-resource constrained critical path.
-
公开(公告)号：US20220171996A1
公开(公告)日：2022-06-02
申请号：US17109112
申请日：2020-12-01
发明人： Lam Minh Nguyen , Dung Tien Phan
摘要： A computer-implemented method for a shuffling-type gradient for training a machine learning model using a stochastic gradient descent (SGD) includes the operations of uniformly randomly distributing data samples or coordinate updates of a training data, and calculating the learning rates for a no-shuffling scheme and a shuffling scheme. A combined operation of the no-shuffling scheme and the shuffling scheme of the training data is performed using a stochastic gradient descent (SGD) algorithm. The combined operation is switched to performing only the shuffling scheme from the no-shuffling scheme based on one or more predetermined criterion; and training the machine learning models with the training data based on the combined no-shuffling scheme and shuffling scheme.
-
公开(公告)号：US20240249018A1
公开(公告)日：2024-07-25
申请号：US18158299
申请日：2023-01-23
发明人： Ambrish Rawat , Naoise Holohan , Heiko H. Ludwig , Ehsan Degan , Nathalie Baracaldo Angel , Alan Jonathan King , Swanand Ravindra Kadhe , Yi Zhou , Keith Coleman Houck , Mark Purcell , Giulio Zizzo , Nir Drucker , Hayim Shaul , Eyal Kushnir , Lam Minh Nguyen
IPC分类号： G06F21/62
CPC分类号： G06F21/6245 , G06F21/6227
摘要： One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process for privacy-enhanced machine learning and inference. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a processing component that generates an access rule that modifies access to first data of a graph database, wherein the first data comprises first party information identified as private, a sampling component that executes a random walk for sampling a first graph of the graph database while employing the access rule, wherein the first graph comprises the first data, and an inference component that, based on the sampling, generates a prediction in response to a query, wherein the inference component avoids directly exposing the first party information in the prediction.
-
8.发明公开公开(公告)号：US20240119298A1
公开(公告)日：2024-04-11
申请号：US17951870
申请日：2022-09-23
发明人： Nhan Huu Pham , Lam Minh Nguyen , Jie Chen , Thanh Lam Hoang , Subhro Das
IPC分类号： G06N3/092
CPC分类号： G06N3/092
摘要： In aspects of the disclosure, a method comprises training, by a computing system, a dynamics model of a cooperative multi-agent reinforcement learning (c-MARL) environment. The method further comprises processing, by the computing system, a perturbation optimizer to generate a state perturbation of the c-MARL environment, based on the dynamics model. The method further comprises selecting one or more agents of the c-MARL system as having enhanced vulnerability. The method further comprises attacking, by the computing system, the c-MARL system based on the state perturbation and the selected one or more agents.
-
公开(公告)号：US20240103959A1
公开(公告)日：2024-03-28
申请号：US17949731
申请日：2022-09-21
CPC分类号： G06F11/0793 , G06F11/008
摘要： In example aspects of this disclosure, a method includes generating, by one or more computing devices, a parametric model that expresses condition states for each of a plurality of assets, and the probability of the assets transitioning between the condition states; generating, by the one or more computing devices, stochastic degradation predictions of a group of the assets, based on the condition states and the probability of transitioning between the condition states for at least some of the assets; and generating, by the one or more computing devices, a maintenance schedule based on: the stochastic degradation predictions of the group of the assets, costs of corrective maintenance for assets in a failed state, and costs of scheduled maintenance for the assets.
-
公开(公告)号：US20240096057A1
公开(公告)日：2024-03-21
申请号：US17933473
申请日：2022-09-19
发明人： Lam Minh Nguyen , Wang Zhang , Subhro Das , Pin-Yu Chen , Alexandre Megretski , Luca Daniel
IPC分类号： G06V10/764 , G06V10/774
CPC分类号： G06V10/764 , G06V10/774
摘要： A computer implemented method for certifying robustness of image classification in a neural network is provided. The method includes initializing a neural network model. The neural network model includes a problem space and a decision boundary. A processor receives a data set of images, image labels, and a perturbation schedule. Images are drawn from the data set in the problem space. A distance from the decision boundary is determined for the images in the problem space. A re-weighting value is applied to the images. A modified perturbation magnitude is applied to the images. A total loss function for the images in the problem space is determined using the re-weighting value. A confidence level of the classification of the images in the data set is evaluated for certifiable robustness.
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.021 秒)
