公开(公告)号：US11429862B2

公开(公告)日：2022-08-30

申请号：US16133446

申请日：2018-09-17

Applicant: SRI International

Inventor： Sek Meng Chai ,  Aswin Nadamuni Raghavan ,  Samyak Parajuli

IPC: G06N3/08 ,  G06N3/10 ,  G06N3/04

Abstract: Techniques are disclosed for training a deep neural network (DNN) for reduced computational resource requirements. A computing system includes a memory for storing a set of weights of the DNN. The DNN includes a plurality of layers. For each layer of the plurality of layers, the set of weights includes weights of the layer and a set of bit precision values includes a bit precision value of the layer. The weights of the layer are represented in the memory using values having bit precisions equal to the bit precision value of the layer. The weights of the layer are associated with inputs to neurons of the layer. Additionally, the computing system includes processing circuitry for executing a machine learning system configured to train the DNN. Training the DNN comprises optimizing the set of weights and the set of bit precision values.

公开(公告)号：US20170364792A1

公开(公告)日：2017-12-21

申请号：US15625578

申请日：2017-06-16

Applicant: SRI International

Inventor： Sek M. Chai ,  David C. Zhang ,  Mohamed R. Amer ,  Timothy J. Shields ,  Aswin Nadamuni Raghavan ,  Bhaskar Ramamurthy

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/063

CPC classification number: G06N3/0454 ,  G06F9/46 ,  G06F9/50 ,  G06N3/0445 ,  G06N3/063 ,  G06N3/08

Abstract: Operations of computing devices are managed using one or more deep neural networks (DNNs), which may receive, as DNN inputs, data from sensors, instructions executed by processors, and/or outputs of other DNNs. One or more DNNs, which may be generative, can be applied to the DNN inputs to generate DNN outputs based on relationships between DNN inputs. The DNNs may include DNN parameters learned using one or more computing workloads. The DNN outputs may be, for example, control signals for managing operations of computing devices, predictions for use in generating control signals, warnings indicating an acceptable state is predicted, and/or inputs to one or more neural networks. The signals enhance performance, efficiency, and/or security of one or more of the computing devices. DNNs can be dynamically trained to personalize operations by updating DNN weights or other parameters.

公开(公告)号：US11328206B2

公开(公告)日：2022-05-10

申请号：US15625578

申请日：2017-06-16

Applicant: SRI International

Inventor： Sek M. Chai ,  David C. Zhang ,  Mohamed R. Amer ,  Timothy J. Shields ,  Aswin Nadamuni Raghavan ,  Bhaskar Ramamurthy

IPC: G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06F9/46 ,  G06F9/50

Abstract: Operations of computing devices are managed using one or more deep neural networks (DNNs), which may receive, as DNN inputs, data from sensors, instructions executed by processors, and/or outputs of other DNNs. One or more DNNs, which may be generative, can be applied to the DNN inputs to generate DNN outputs based on relationships between DNN inputs. The DNNs may include DNN parameters learned using one or more computing workloads. The DNN outputs may be, for example, control signals for managing operations of computing devices, predictions for use in generating control signals, warnings indicating an acceptable state is predicted, and/or inputs to one or more neural networks. The signals enhance performance, efficiency, and/or security of one or more of the computing devices. DNNs can be dynamically trained to personalize operations by updating DNN weights or other parameters.

公开(公告)号：US10789755B2

公开(公告)日：2020-09-29

申请号：US16230945

申请日：2018-12-21

Applicant: SRI International

Inventor： Mohamed R. Amer ,  Timothy J. Meo ,  Aswin Nadamuni Raghavan ,  Alex C. Tozzo ,  Amir Tamrakar ,  David A. Salter ,  Kyung-Yoon Kim

IPC: G06T13/80 ,  G06N3/04 ,  G06N3/08 ,  G06K9/00 ,  G06F16/738 ,  G06N20/00 ,  G06K9/62 ,  G06F16/34 ,  G06F16/901 ,  G06T13/40 ,  G06T7/246 ,  G06F40/205

Abstract: This disclosure describes techniques that include generating, based on a description of a scene, a movie or animation that represents at least one possible version of a story corresponding to the description of the scene. This disclosure also describes techniques for training a machine learning model to generate predefined data structures from textual information, visual information, and/or other information about a story, an event, a scene, or a sequence of events or scenes within a story. This disclosure also describes techniques for using GANs to generate, from input, an animation of motion (e.g., an animation or a video clip). This disclosure also describes techniques for implementing an explainable artificial intelligence system that may provide end users with information (e.g., through a user interface) that enables an understanding of at least some of the decisions made by the AI system.

公开(公告)号：US20190304157A1

公开(公告)日：2019-10-03

申请号：US16230945

申请日：2018-12-21

Applicant: SRI International

Inventor： Mohamed R. Amer ,  Timothy J. Meo ,  Aswin Nadamuni Raghavan ,  Alex C. Tozzo ,  Amir Tamrakar ,  David A. Salter ,  Kyung-Yoon Kim

IPC: G06T13/80 ,  G06F17/27 ,  G06K9/00 ,  G06N3/08 ,  G06N3/04

Abstract: This disclosure describes techniques that include generating, based on a description of a scene, a movie or animation that represents at least one possible version of a story corresponding to the description of the scene. This disclosure also describes techniques for training a machine learning model to generate predefined data structures from textual information, visual information, and/or other information about a story, an event, a scene, or a sequence of events or scenes within a story. This disclosure also describes techniques for using GANs to generate, from input, an animation of motion (e.g., an animation or a video clip). This disclosure also describes techniques for implementing an explainable artificial intelligence system that may provide end users with information (e.g., through a user interface) that enables an understanding of at least some of the decisions made by the AI system.

公开(公告)号：US20240062042A1

公开(公告)日：2024-02-22

申请号：US18451692

申请日：2023-08-17

Applicant: SRI International

Inventor： Aswin Nadamuni Raghavan ,  Saurabh Farkya ,  Jesse Albert Hostetler ,  Avraham Joshua Ziskind ,  Michael Piacentino ,  Ajay Divakaran ,  Zhengyu Chen

IPC: G06N3/045 ,  G06F21/56 ,  G06N3/098

CPC classification number: G06N3/045 ,  G06F21/566 ,  G06N3/098 ,  G06F2221/033

Abstract: In general, the disclosure describes techniques for implementing an MI-based attack detector. In an example, a method includes training a neural network using training data, applying stochastic quantization to one or more layers of the neural network, generating, using the trained neural network, an ensemble of neural networks having a plurality of quantized members, wherein at least one of weights or activations of each of the plurality of quantized members have different bit precision, and combining predictions of the plurality of quantized members of the ensemble to detect one or more adversarial attacks and/or determine performance of the ensemble of neural networks.

公开(公告)号：US11676024B2

公开(公告)日：2023-06-13

申请号：US15999769

申请日：2017-02-24

Applicant: SRI International

Inventor： Sek Meng Chai ,  David Zhang ,  Mohamed Amer ,  Timothy J. Shields ,  Aswin Nadamuni Raghavan

IPC: G06N3/04 ,  G06N3/084 ,  G06V10/52 ,  G06F18/00 ,  G06F18/21 ,  G06F18/24 ,  G06F18/2413 ,  G06N3/045 ,  G06V10/764 ,  G06V10/82 ,  G06N3/082 ,  G06N3/086 ,  G06N3/044

CPC classification number: G06N3/084 ,  G06F18/00 ,  G06F18/21 ,  G06F18/24 ,  G06F18/2413 ,  G06N3/045 ,  G06V10/52 ,  G06V10/764 ,  G06V10/82 ,  G06N3/044 ,  G06N3/082 ,  G06N3/086

Abstract: Artificial neural network systems involve the receipt by a computing device of input data that defines a pattern to be recognized (such as faces, handwriting, and voices). The computing device may then decompose the input data into a first subband and a second subband, wherein the first and second subbands include different characterizing features of the pattern in the input data. The first and second subbands may then be fed into first and second neural networks being trained to recognize the pattern. Reductions in power expenditure, memory usage, and time taken, for example, allow resource-limited computing devices to perform functions they otherwise could not.

公开(公告)号：US20200302339A1

公开(公告)日：2020-09-24

申请号：US16825953

申请日：2020-03-20

Applicant: SRI International

Inventor： Aswin Nadamuni Raghavan ,  Jesse Hostetler ,  Indranil Sur ,  Abrar Abdullah Rahman ,  Sek Meng Chai

IPC: G06N20/00 ,  G06N3/08 ,  G06K9/62 ,  G06F9/48 ,  G06F9/38

Abstract: Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.

公开(公告)号：US20230394413A1

公开(公告)日：2023-12-07

申请号：US18330930

申请日：2023-06-07

Applicant: SRI International

Inventor： Subhodev Das ,  Aswin Nadamuni Raghavan ,  Avraham Joshua Ziskind ,  Timothy J. Meo ,  Bhoram Lee ,  Chih-hung Yeh ,  John Cadigan ,  Ali Chaudhry ,  Jonathan C. Balloch

IPC: G06Q10/0637

CPC classification number: G06Q10/06375

Abstract: In general, the disclosure describes techniques for Artificial Intelligence (AI) models that can automatically generate diverse, explainable, interpretable, reactive, and coordinated behaviors for a team. In an example, a method includes receiving multimodal input data within a simulator configured to simulate solving a predefined problem by a team including a plurality of agents; generating one or more generative neural network models based on the multimodal input data and based on a predetermined threshold of success of problem solving in the simulator; outputting, by the one or more generative neural network models, one or more multi-agent controllers, wherein each of the one or more multi-agent controllers comprises recommended behaviors for each of the plurality of agents to solve the predefined problem in a manner that is consistent with the multimodal input data.

公开(公告)号：US11494597B2

公开(公告)日：2022-11-08

申请号：US16825953

申请日：2020-03-20

Applicant: SRI International

Inventor： Aswin Nadamuni Raghavan ,  Jesse Hostetler ,  Indranil Sur ,  Abrar Abdullah Rahman ,  Sek Meng Chai

IPC: G06K9/62 ,  G06N20/00 ,  G06N3/08 ,  G06F9/38 ,  G06F9/48 ,  G06F3/06 ,  G06Q40/08 ,  G06N3/04

Abstract: Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.