-
公开(公告)号：US11574679B2
公开(公告)日：2023-02-07
申请号：US17736695
申请日：2022-05-04
发明人： Wei Yi , Charles Martin , Soheil Kolouri , Praveen Pilly
摘要： A memory circuit configured to perform multiply-accumulate (MAC) operations for performance of an artificial neural network includes a series of synapse cells arranged in a cross-bar array. Each cell includes a memory transistor connected in series with a memristor. The memory circuit also includes input lines connected to the source terminal of the memory transistor in each cell, output lines connected to an output terminal of the memristor in each cell, and programming lines coupled to a gate terminal of the memory transistor in each cell. The memristor of each cell is configured to store a conductance value representative of a synaptic weight of a synapse connected to a neuron in the artificial neural network, and the memory transistor of each cell is configured to store a threshold voltage representative of a synaptic importance value of the synapse connected to the neuron in the artificial neural network.
-
公开(公告)号：US11288498B2
公开(公告)日：2022-03-29
申请号：US16931420
申请日：2020-07-16
发明人： Amir M. Rahimi , Hyukseong Kwon , Heiko Hoffmann , Soheil Kolouri
摘要： Described is a system for learning actions for image-based action recognition in an autonomous vehicle. The system separates a set of labeled action image data from a source domain into components. The components are mapped onto a set of action patterns, thereby creating a dictionary of action patterns. For each action in the set of labeled action data, a mapping is learned from the action pattern representing the action onto a class label for the action. The system then maps a set of new unlabeled target action image data onto a shared embedding feature space in which action patterns can be discriminated. For each target action in the set of new unlabeled target action image data, a class label for the target action is identified. Based on the identified class label, the autonomous vehicle is caused to perform a vehicle maneuver corresponding to the identified class label.
-
公开(公告)号：US11037030B1
公开(公告)日：2021-06-15
申请号：US16593572
申请日：2019-10-04
发明人： Soheil Kolouri
摘要： A method for computing classifications of raw tomographic data includes: supplying the raw tomographic data to a sinogram-convolutional neural network including blocks, at least one of the blocks being configured to perform a convolution of the raw tomographic data in Radon space with a convolutional kernel by: slicing the raw tomographic data into a plurality of one-dimensional tomographic data slices along an angle dimension of the raw tomographic data; slicing the convolutional kernel into a plurality of one-dimensional kernel slices along the angle dimension of the convolutional kernel; for each angle, computing a one-dimensional convolution between: a corresponding one of the one-dimensional tomographic data slices at the angle; and a corresponding one of the one-dimensional kernel slices at the angle; and collecting the one-dimensional convolutions at the angles; computing a plurality of features from the convolution; and computing the classifications of the raw tomographic data based on the features.
-
公开(公告)号：US11023789B2
公开(公告)日：2021-06-01
申请号：US15936403
申请日：2018-03-26
摘要： Described is a system for classifying objects and scenes in images. The system identifies salient regions of an image based on activation patterns of a convolutional neural network (CNN). Multi-scale features for the salient regions are generated by probing the activation patterns of the CNN at different layers. Using an unsupervised clustering technique, the multi-scale features are clustered to identify key attributes captured by the CNN. The system maps from a histogram of the key attributes onto probabilities for a set of object categories. Using the probabilities, an object or scene in the image is classified as belonging to an object category, and a vehicle component is controlled based on the object category causing the vehicle component to perform an automated action.
-
公开(公告)号：US20210019632A1
公开(公告)日：2021-01-21
申请号：US16875852
申请日：2020-05-15
摘要： Described is a system for continual learning using experience replay. In operation, the system receives a plurality of tasks sequentially, from which a current task is fed to an encoder. The current task has data points associated with the current task. The encoder then maps the data points into an embedding space, which reflects the data points as discriminative features. A decoder then generates pseudo-data points from the discriminative features, which are provided back to the encoder. The discriminative features are updated in the embedding space based on the pseudo-data points. The encoder then learns (updates) a classification of a new task by matching the new task with the discriminative features in the embedding space.
-
公开(公告)号：US10755424B2
公开(公告)日：2020-08-25
申请号：US15971982
申请日：2018-05-04
IPC分类号： G06K9/62 , G06T7/262 , G06T7/277 , G06N3/00 , G06N20/00 , G06K9/00 , A63B69/00 , G08G5/00 , G08G9/00 , A63B24/00
摘要： Described is a system for predicting multi-agent movements. A Radon Cumulative Distribution Transform (Radon-CDT) is applied to pairs of signature-formations representing agent movements. Canonical correlation analysis (CCA) components are identified for the pairs of signature-formations. Then, a relationship between the pairs of signature formations is learned using the CCA components. A counter signature-formation for a new dataset is predicted using the learned relationship and a new signature-formation. Control parameters of a device can be adjusted based on the predicted counter signature-formation.
-
公开(公告)号：US10755149B2
公开(公告)日：2020-08-25
申请号：US15949896
申请日：2018-04-10
发明人： Soheil Kolouri , Shankar R. Rao , Kyungnam Kim
IPC分类号： G06K9/72 , G06K9/62 , G06N3/04 , G06N3/08 , B60W10/20 , G05D1/00 , B60W10/18 , G06K9/46 , G06K9/00
摘要： Described is a system that can recognize novel objects that the system has never before seen. The system uses a training image set to learn a model that maps visual features from known images to semantic attributes. The learned model is used to map visual features of an unseen input image to semantic attributes. The unseen input image is classified as belonging to an image class with a class label. A device is controlled based on the class label.
-
公开(公告)号：US20180293736A1
公开(公告)日：2018-10-11
申请号：US15949013
申请日：2018-04-09
IPC分类号： G06T7/20
摘要： Described is a system for implicitly predicting movement of an object. In an aspect, the system includes one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of providing an image of a first trajectory to a predictive autoencoder, and using the predictive autoencoder, generating a predicted tactical response that comprises a second trajectory based on images of previous tactical responses that were used to train the predictive autoencoder, and controlling a device based on the predicted tactical response.
-
公开(公告)号：US11625557B2
公开(公告)日：2023-04-11
申请号：US17080673
申请日：2020-10-26
发明人： Heiko Hoffmann , Soheil Kolouri
摘要： Described is a system for learning object labels for control of an autonomous platform. Pseudo-task optimization is performed to identify an optimal pseudo-task for each source model of one or more source models. An initial target network is trained using the optimal pseudo-task. Source image components are extracted from source models, and an attribute dictionary of attributes is generated from the source image components. Using zero-shot attribution distillation, the unlabeled target data is aligned with the source models similar to the unlabeled target data. The unlabeled target data are mapped onto attributes in the attribute dictionary. A new target network is generated from the mapping, and the new target network is used to assign an object label to an object in the unlabeled target data. The autonomous platform is controlled based on the object label.
-
公开(公告)号：US11494486B1
公开(公告)日：2022-11-08
申请号：US16684382
申请日：2019-11-14
发明人： Hyun (Tiffany) J. Kim , Rajan Bhattacharyya , Samuel D. Johnson , Soheil Kolouri , Christian Lebiere , Jiejun Xu
摘要： Described is a system for continuously predicting and adapting optimal strategies for attacker elicitation. The system includes a global bot controlling processor unit and one or more local bot controlling processor units. The global bot controlling processor unit includes a multi-layer network software unit for extracting attacker features from diverse, out-of-band (OOB) media sources. The global controlling processing unit further includes an adaptive behavioral game theory (GT) software unit for determining a best strategy for eliciting identifying information from an attacker. Each local bot controlling processor unit includes a cognitive model (CM) software unit for estimating a cognitive state of the attacker and predicting attacker behavior. A generative adversarial network (GAN) software unit predicts the attacker's strategies. The global bot controlling processor unit and the one or more local bot controlling processor units coordinate to predict the attacker's next action and use the prediction to disrupt an attack.
-
-
-
-
-
-
-
-
-
搜索结果
39 条记录 (耗时 0.026 秒)