International Business Machines Corporation

Elbo Inc.

Visa International Service Association

Spawn Labs, Inc.

Rtscaleai Inc

Vircion LLC

Jamkazam, Inc.

Peter A Walker

Joseph R Winchester

Oswald Anthony Becca

Yu Gu

Igor V Karpenko

Elmootazbellah Nabil Elnozahy

Gili Mendel

Richard Lee Kulp

Gunturi Srimanth

Ramakrishnan Rajamony

Hao Yang

Eugen Schenfeld

Alan Frederic Benner

Craig Brian Stunkel

Yinhe Cheng

L Scott Rich

Rebecca J Schaller

Ranglin Lu

Robert Brian Christensen

Srimanth Gunturi

Subir Roy

Biswajit Das

Vivek Viswanathan Iyer

Hongqin Song

David J Wilson

Dan Wang

Jeffrey D Myers

Robert Scott Comer

Michael Seth Call

Gili Mendal

Richard J Kulp

A method for dynamically assigning an inference request is disclosed. A method for dynamically assigning an inference request may include determining at least one model to process an inference request on a plurality of computing platforms, the plurality of computing platforms including at least one Central Processing Unit (CPU) and at least one Graphics Processing Unit (GPU), obtaining, with at least one processor, profile information of the at least one model, the profile information including measured characteristics of the at least one model, dynamically determining a selected computing platform from between the at least one CPU and the at least one GPU for responding to the inference request based on an optimized objective associated with a status of the computing platform and the profile information, and routing, with at least one processor, the inference request to the selected computing platform. A system and computer program product are also disclosed.

Method, system, and computer program product for dynamically assigning an inference request to a CPU or GPU

A method, system, and computer program product for dynamically scheduling machine learning inference jobs receive or determine a plurality of performance profiles associated with a plurality of system resources, wherein each performance profile is associated with a machine learning model; receive a request for system resources for an inference job associated with the machine learning model; determine a system resource of the plurality of system resources for processing the inference job associated with the machine learning model based on the plurality of performance profiles and a quality of service requirement associated with the inference job; assign the system resource to the inference job for processing the inference job; receive result data associated with processing of the inference job with the system resource; and update based on the result data, a performance profile of the plurality of the performance profiles associated with the system resource and the machine learning model.

Method, system, and computer program product for dynamically scheduling machine learning inference jobs with different quality of services on a shared infrastructure

Embodiments of the invention are directed to systems and methods for utilizing a cache to store historical transaction data. A predictive model may be trained to identify particular identifiers associated with historical data that is likely to be utilized on a particular date and/or within a particular time period. The historical data corresponding to these identifiers may be stored in a cache of the processing computer. Subsequently, an authorization request message may be received that includes an identifier. The processing computer may utilize the identifier to retrieve historical transaction data from the cache. The retrieved data may be utilized to perform any suitable operation. By predicting the data that will be needed to perform these operations, and preemptively store such data in a cache, the latency associated with subsequent processing may be reduced and the performance of the system as a whole improved.

Techniques for utilizing a predictive model to cache processing data

A method for (of) detecting deception in an Audio-Video response of a user, using a server, in a distributed computing architecture, characterized in that the method including: enabling an Audio-Video connection with a user device upon receiving a request from a user; obtaining, from the user device, an Audio-Video response of the user corresponding to a first set of questions that are provided to the user by the server; extracting audio signals and video signals from the Audio-Video response; detecting an activity of the user by determining a plurality of Natural Language Processing (NLP) features from the extracted audio signals by (i) performing a speech to text translation and (ii) extracting the plurality of NLP features from the translated text, and determining a plurality of speech features from the extracted audio signals by (i) splitting the extracted audio signals into a plurality of short interval audio signals and (ii) extracting the plurality of speech features from the plurality of short interval audio signals; aggregating (i) the plurality of NLP features to obtain a plurality of temporal NLP features and (ii) the plurality of speech features to obtain a plurality of temporal speech features; aggregating the plurality of temporal NLP features and the plurality of temporal speech features to obtain first temporal aggregated features; detecting a plurality of micro-expressions of the user by splitting extracted video signals into a plurality of short fixed-duration video signals, detecting a plurality of Region Of Interest (ROI) in the plurality of short fixed-duration video signals, and comparing the plurality of detected ROI with video signals annotated with micro-expression labels that are stored in a database to detect the plurality of micro-expressions of the user in the plurality of short fixed-duration video signals; tracking and determining a gesture of the user from the extracted video signals; aggregating the plurality of micro-expressions and the gesture of the user to obtain second temporal aggregated features; aggregating the first temporal aggregated features and the second temporal aggregated features to obtain final temporal aggregated features; and detecting, using a machine learning model, a deception in the Audio-Video response based on the final temporal aggregated features.

System and method for detecting deception in an audio-video response of a user

A method for low-latency communication from a first device to a second device over an unreliable network using at least one predictive machine learning model includes representing at least one frame of time series data at the first device; recording at least one output stream, and a plurality of external inputs from the first device in an interaction recorder of the second device detecting, at the second device, at least one lost frame of time series data; training the at least one predictive machine learning model at the first device for predictive frame regeneration; regenerating the at least one lost frame of the time series data at the second device using the at least one predictive machine learning model; and combining an output stream from an application steam with the at least one regenerated frame of time series data to obtain a modified output stream.

System and method for low-latency communication over unreliable networks

A system for allowing a user to remotely access a game includes: a game console; a remote console client configured to receive a game control signal; and a remote console server. The remote console server includes an audio and video encoder configured to receive an audio output and a video output from the game console and to convert the audio output and the video output to a network packet. The remote console server also includes: a game controller emulation unit and a network interface configured to send and receive the network packet. The game controller emulation unit is configured to receive a game controller signal from the game console and to send the game controller signal to the remote console client and to receive a game controller input from the remote console client and send the game controller input to the game console.

System for remote game access

Aspects of the present disclosure relate to the implementation of a gaming environment including gaming servers for instantiating instances of games requested by a user. The gaming environment includes a game device for obtaining game inputs corresponding to the instantiated game. Additionally, the gaming environment includes one or more output devices for obtaining outputs generated by the processing of the inputs by the gaming server. Illustratively, the game device and one or more output devices form game device groups. Within each game device group, the inputs obtained by game device are transmitted independent of the outputs transmitted to the output devices. The transmission of input data from the game device and the transmission of the output audio data, output video data or other data from the gaming server may be individually optimized.

Network enabled game controller

Packet rate control methods and related systems are disclosed for interactive music systems. In certain embodiments, an interactive music client system combines captured audio data from audio inputs with audio input data from one or more peer interactive music client systems within an interactive music session and outputs the combined audio data to an audio output subsystem. The interactive music client system further determines performance parameters associated with the interactive music sessions and adjusts audio input/output packets based upon the performance parameters. The performance parameters can include, for example, session packet rates or other parameters. Adjustments can include aggregating audio frames, reducing packet rates, and adjusting audio frames within a jitter queue receive buffer. The jitter queue receive buffer, for example, can be adjusted so that is contents are reduced towards zero and/or to zero within a predetermined time duration. Other variations can also be implemented.

Packet rate control and related systems for interactive music systems

Network-enabled game controller

A computing system includes: a plurality of tightly coupled processing nodes; a plurality of circuit switched networks using a circuit switching mode, interconnecting the processing nodes, and handling data transfers that meet one or more criteria; and a plurality of electronic packet switched networks, also interconnecting the processing nodes, handling data transfers that do meet the at least one criteria. The circuit switched networks and the electronic packet switched networks operate simultaneously.

Dual network types solution for computer interconnects

Growing community of inventors

Fuquay Varina, NC, United States of America

Peter A Walker