Vmware, Inc.

Nvidia Corporation

Enlitic, Inc.

Castlight Health, Inc.

John R Zedlewski

Carl Alan Waldspurger

Andrei Dorofeev

Minwoo Park

Pekka Janis

Zuoguan Wang

Gordon Grigor

Miguel Sainz

Davide Onofrio

Chia-Chih Chen

Yifang Xu

Carolina Parada

Vijay Chintalapudi

Ozan Tonkal

Xin Liu

Mehdi Sajjadi Mohammadabadi

Jan Nikolaus Fritsch

I-Kuei Chen

Kevin Lyman

Li Yao

Anthony Upton

Ben Covington

Gary D Hicok

Michael Brian Cox

Minwen Ji

Devon Bernard

Rev Lebaredian

Tony Tamasi

Brian Basham

Diogo Almeida

Jeremy Howard

Greg Heinrich

Claire Delaunay

Clement Farabet

Zachary Taylor

Mark Daly

Matthew Campbell

David Auld

Jan Kautz

Ole Agesen

Ming-Yu Liu

Xiaoxin Chen

Boris Weissman

Tal Garfinkel

Timothy P Mann

Ting-Chun Wang

Ramesh Dharan

Rajit S Kambo

Stephen Muckle

Curtis A Beeson

Aysegul Dundar

Matthew Vanderzee

Anshul Amar

Jim Griswold

Naveen Saxena

Naomi Allen

Michael Craig

Curtis Beeson

In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.

Real-time detection of lanes and boundaries by autonomous vehicles

In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.

Training, testing, and verifying autonomous machines using simulated environments

In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment&#x2014;in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack&#x2014;to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.

A style transfer neural network may be used to generate stylized synthetic images, where real images provide the style (e.g., seasons, weather, lighting) for transfer to synthetic images. The stylized synthetic images may then be used to train a recognition neural network. In turn, the trained neural network may be used to predict semantic labels for the real images, providing recognition data for the real images. Finally, the real training dataset (real images and predicted recognition data) and the synthetic training dataset are used by the style transfer neural network to generate stylized synthetic images. The training of the neural network, prediction of recognition data for the real images, and stylizing of the synthetic images may be repeated for a number of iterations. The stylization operation more closely aligns a covariate of the synthetic images to the covariate of the real images, improving accuracy of the recognition neural network.

Domain stylization using a neural network model

A lung screening assessment system is operable to receive a chest computed tomography (CT) scan that includes a plurality of cross sectional images. Nodule classification data of the chest CT scan is generated by utilizing a computer vision model that is trained on a plurality of training chest CT scans to identify a nodule in the plurality of cross sectional images and determine an assessment score. A lung screening report that includes the assessment score of the nodule classification data is generated for display on a display device associated with a user of the lung screening assessment system.

Lung screening assessment system

A thread scheduling mechanism is provided that flexibly enforces performance isolation of multiple threads to alleviate the effect of anti-cooperative execution behavior with respect to a shared resource, for example, hoarding a cache or pipeline, using the hardware capabilities of simultaneous multi-threaded (SMT) or multi-core processors. Given a plurality of threads running on at least two processors in at least one functional processor group, the occurrence of a rescheduling condition indicating anti-cooperative execution behavior is sensed, and, if present, at least one of the threads is rescheduled such that the first and second threads no longer execute in the same functional processor group at the same time.

Mechanism for scheduling execution of threads for fair resource allocation in a multi-threaded and/or multi-core processing system

Processes are balanced among multiple computer systems. The allocation policies and resource demands of multiple processes executing on multiple computer systems are used to determine the resource imbalance of the computer systems. Resource imbalance can be used to determine whether a process should be migrated from one computer system to another. Resource imbalance of multiple resources can be combined to determine overall imbalance of the computer systems. Overall imbalance can be used to determine whether a process should be migrated from one computer system to another. Imbalance of resources can be determined for resources such as processor time, memory, network bandwidth, and storage. Virtual machines can be balanced among multiple computer systems operating in a cluster.

Use of dynamic entitlement and adaptive threshold for cluster process balancing

Embodiments of methods and systems for predicting provider negotiated rates are disclosed. One method includes obtaining claims data and provider data, grouping the claims data into priceable units, computing prices for each of the priceable units based on the claims data and the provider data, and estimating provider negotiated rates based on the priceable units and the computed prices for the priceable units.

Predicting provider negotiated rates

Management of contexts that execute on a computer system is described. More specifically, context scheduling in a virtual machine environment is described. Times at which a context transitions from a scheduled state to a descheduled state and times at which the context transitions from a descheduled state to a scheduled state are recorded for each context. Skew is detected using the recorded times. The amount of skew can be quantified, and a corrective action is triggered if the amount of skew fails to satisfy a threshold value.

Defining and measuring skew between coscheduled contexts

Management of contexts that execute on a computer system is described. More specifically, context scheduling in a virtual machine environment is described. A set of coscheduled contexts is monitored. If a skew metric associated with a first context of the coscheduled contexts fails to satisfy a condition, then a subset of the coscheduled contexts is descheduled although the first context remains scheduled.

Detecting and responding to skew between coscheduled contexts

Management of contexts that execute on a computer system is described. More specifically, context scheduling in a virtual machine environment is described. A set of coscheduled contexts, including at least a first context and a second context, are monitored. The first and second contexts are alternately scheduled and descheduled so that both the first context and the second context are not concurrently scheduled.

Alternating scheduling and descheduling of coscheduled contexts

Management of contexts that execute on a computer system is described. More specifically, context scheduling in a virtual machine environment is described. A set of coscheduled contexts is monitored. If a skew metric associated with any one of the coscheduled contexts fails to satisfy a condition, then all coscheduled contexts in the set of coscheduled contexts not already descheduled are descheduled. After the contexts are descheduled, a subset of the set of coscheduled contexts is scheduled before the remainder of the set of coscheduled contexts.

Scheduling selected contexts in response to detecting skew between coscheduled contexts

Growing community of inventors

Cambridge, MA, United States of America

John R Zedlewski