The Royal Institution for the Advancement of Learning/mcgill University

Mellanox Technologies, Ltd.

Walmart Apollo, LLC

Nvidia Corporation

Ford Global Technolgoies, LLC

Mcgill University

Shie Mannor

Warren Jeffrey Gross

Gal Chechik

Dotan David Levi

Saeed Sharifi Tehrani

Dror Porat

Assaf Weissman

Vadim Gechman

Ohad Markus

Vineet Abhishek

Eyal Frishman

Assaf Hallak

Eshed Ram

Saied Hemati

Francois Leduc-Primeau

Gabi Sarkis

Dimitar Petrov Filev

Gil Levy

Raj Sohmshetty

Peter A Friedman

Kevin Richard John Ellwood

Sagi Lahav

Richard Edward Chatwin

Alessandro Magnani

Abhinandan Krishnan

Marco Pavone

Rami Ailabouni

Haim Elisha

Nir Rosen

Doina Precup

Amir Rosen

David Nellans

Boris Ivanovic

Evgeny Bolotin

Arye Albahari

Ariel Szapiro

Yaosheng Fu

Gaby Vanesa Diengott

Udy Danino

Jaymin Daniel Mankowitz

Tom Ben Zion Zahavy

Jordan Frank

Katya Egert-Berg

Elad Haimovich

Adi Peled

Samir Deeb

David Slama

Zi Yan

Ohad Peres

Tamar Viclizki

Ali Naderi

Gal Dalal

Peter Karkus

Apparatuses, systems, and techniques of using one or more circuits (e.g., of a network interface) to obtain assembly code for one or more machine code segments loaded and/or injected into a process, and determine whether the assembly code is likely to perform at least one unauthorized task.

Detecting potential malware in host memory

In one embodiment, a system includes prefetcher engines to predict next memory access addresses of a memory from which to load data to a cache during execution of a software application, and load the data from the predicted next memory access addresses to the cache during execution of the software application, and a processor to assign cache replacement precedence values to cache lines based on the prefetcher engines that loaded the cache lines, and evict the cache lines from the cache based on the cache replacement precedence values of the cache lines.

Cache replacement system

In various examples, a motion planner include an analytical function to predict motion plans for a machine based on predicted trajectories of actors in an environment, where the predictions are differentiable with respect to parameters of a neural network of a motion predictor used to predict the trajectories. The analytical function may be used to determine candidate trajectories for the machine based on a predicted trajectory, to compute cost values for the candidate trajectories, and to select a reference trajectory from the candidate trajectories. For differentiability, a term of the analytical function may correspond to the predicted trajectory. A motion controller may use the reference trajectory to predict a control sequence for the machine using an analytical function trained to generate predictions that are differentiable with respect to at least one parameter of the analytical function used to compute the cost values.

Differentiable and modular prediction and planning for autonomous machines

A system includes a processing device to receive video content, metadata related to the video content, and a target bit rate for encoding the video content. The processing device further detects a content type of the video content based on the metadata and encodes hardware to perform frame encoding on the video content. The system further includes a controller coupled between the processing device and the encoding hardware. The controller is programmed with machine instructions to generate first QP values on a per-frame basis using a frame machine learning model with a first plurality of weights. The first plurality of weights depends at least in part on the content type and the target bit rate. The controller further provides the first QP values to the encoding hardware for rate control of the frame encoding.

Content-aware, machine-learning-based rate control

A system includes a processing device to receive a video content, a quality metric, and a target bit rate for encoding the video content. The system includes encoding hardware to perform frame encoding on the video content and a controller coupled between the processing device and the encoding hardware. The controller is programmed with machine instructions to generate first QP values on a per-frame basis using a frame machine learning model with a first plurality of weights. The first plurality of weights depends at least in part on the quality metric and the target bit rate. The controller is further programmed to provide the first QP values to the encoding hardware for rate control of the frame encoding.

Quality-metric-agnostic rate control

A method for data-center management includes, in a data center including multiple components, monitoring a plurality of performance measures of the components. A set of composite metrics is automatically defined, each composite metric including a respective weighted combination of two or more performance measures from among the performance measures. Baseline values are established for the composite metrics. An anomalous deviation is detected of one or more of the composite metrics from the respective baseline values.

Identifying anomalies in a data center using composite metrics and/or machine learning

A system, method, and apparatus of power management for computing systems are included herein that optimize individual frequencies of components of the computing systems using machine learning. The computing systems can be tightly integrated systems that consider an overall operating budget that is shared between the components of the computing system while adjusting the frequencies of the individual components. An example of an automated method of power management includes: (1) learning, using a power management (PM) agent, frequency settings for different components of a computing system during execution of a repetitive application, and (2) adjusting the frequency settings of the different components using the PM agent, wherein the adjusting is based on the repetitive application and one or more limitations corresponding to a shared operating budget for the computing system.

Automatic method for power management tuning in computing systems

The method of monitoring an operation includes acquiring data from sensors including images of a workspace in which the operation is to be performed, identifying a human operator and a controlled element within the workspace using the acquired images, determining whether the operation has initiated based on a known activation trigger, estimating pose of the human operator using the images, monitoring state of the controlled element based on acquired data, and determining whether an abnormality occurred based on the estimated pose, the state of the controlled element, a duration of the operation, or a combination thereof.

Method and system for monitoring manufacturing operations using computer vision for human performed tasks

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of training a source classifier with labeled source training data of a first product category from a website of an online retailer, clustering target data for a second product category into a plurality of clusters, inserting into each cluster labeled source training data of the first product category, assigning a domain discriminator score to each cluster, determining whether each cluster comprises an agreement cluster or a disagreement cluster using the domain discriminator score, receiving a product search request for a product of the second category from a user of the web site, and coordinating a display of the product on the web site to promote the product.

Systems and methods for promoting products in product search results using transfer learning with active sampling

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of receiving an online search query entered into a search field of an online ecommerce website by a user using the online ecommerce website, determining a query response to the online search query by combining a nonparametric bootstrap distribution and a mixture sequential probability ratio test, the query response comprising one or more products, and coordinating a display of the query response to the user using the online ecommerce website. The query response can be based on one of a query success rate per user session of a plurality of previous user sessions or a revenue per user session of the plurality of previous user sessions.

Combined bootstrap distribution and mixture sequential probability ratio test applications to online ecommerce websites

A multi-modal computer classification network system for use in classifying data records is described herein. The system includes a memory device, a first classification computer server, a second classification computer server, and a policy computer server. The memory device includes an item records database and a labeling database. The first classification computer server includes a first classifier program that is configured to select an item record from the item database and generate a first classification record including a first ranked list of class labels. The second classification computer server includes a second classifier program that is configured to generate a second classification record including a second ranked list of class labels. The policy computer server includes a policy network that is programmed to determine a predicted class label based on the first and second ranked lists of class labels.

Systems, method, and non-transitory computer-readable storage media for multi-modal product classification

A method for iteratively decoding a set of encoded samples received from a transmission channel is provided. A data signal indicative of a noise level of the transmission channel is received. A scaling factor is then determined in dependence upon the data signal and the encoded samples are scaled using the scaling factor. The scaled encoded samples are then iteratively decoded. Furthermore, a method for initializing edge memories is provided. During an initialization phase initialization symbols are received from a node of a logic circuitry and stored in a respective edge memory. The initialization phase is terminated when the received symbols occupy a predetermined portion of the edge memory. An iterative process is executed using the logic circuitry storing output symbols received from the node in the edge memory and a symbol is retrieved from the edge memory and provided as output symbol of the node. Yet further an architecture for a high degree variable node is provided. A plurality of sub nodes forms a variable node for performing an equality function in an iterative decoding process. Internal memory is interposed between the sub nodes such that the internal memory is connected to an output port of a respective sub node and to an input port of a following sub node, the internal memory for providing a chosen symbol if a respective sub node is in a hold state, and wherein at least two sub nodes share a same internal memory.

Methods and systems for improving iterative signal processing

Portable wireless devices are ubiquitous in modern society and many of these have integral sensors such as accelerometers, microphones, and Global Positioning Systems (GPS) that can collect data. This creates potential for intelligent applications to recognize the user, or aspects of the user and take appropriate action. According to embodiments of the invention there are presented techniques for representing such time series data which reduce the memory and computational complexity of performing the analysis and classifying the results. The techniques exploit time-delay embedding is to reconstruct the state and dynamics of an unknown dynamical system, Geometric Template Matching to build nonparametric classifiers, and algorithms to address the problem of selecting segments of data from which to build the time-delay models for classification problems.

Method of identification and devices thereof

Low-Density Parity-Check (LDPC) codes offer error correction at rates approaching the link channel capacity and reliable and efficient information transfer over bandwidth or return-channel constrained links with data-corrupting noise present. LDPC codes also offer error correction performance approaching channel capacity exponentially fast in terms of the code length, linear processing complexity, and parallelism that scales with the code length. They also offer challenges relating to the decoding complexity of the binary error-correction codes themselves and error floors limiting achievable bit-error rates. A new Relaxed Half-Stochastic (RHS) decoding algorithm is presented that reduces decoding complexity for high decoding throughput applications. The RHS algorithm uses an approach based on stochastic decoding algorithms but differs significantly from the conventional approaches of LDPC decoder implementation. The RHS algorithm also leads to a randomized decoding technique called redecoding that addresses the error floor limitation.

Method and system for decoding

Low-Density Parity-Check (LDPC) codes offer error correction at rates approaching the link channel capacity and reliable and efficient information transfer over bandwidth or return-channel constrained links with data-corrupting noise present. They also offer performance approaching channel capacity exponentially fast in terms of the code length, linear processing complexity, and parallelism that scales with code length. They also offer challenges relating to decoding complexity and error floors limiting achievable bit-error rates. Accordingly encoders with reduced complexity, reduced power consumption and improved performance are disclosed with various improvements including simplifying communications linking multiple processing nodes by passing messages where pulse widths are modulated with the corresponding message magnitude, delaying a check operation in dependence upon variable node states, running the decoder multiple times with different random number generator seeds for a constant channel value set, and employing a second decoder with a randomizing component when the attempt with the first decoder fails.

Growing community of inventors

Haifa, Israel

Shie Mannor