International Business Machines Corporation

University of Illinois

Red Hat, Inc.

Utopus Insights, Inc.

Jinjun Xiong

Vladimir P Zolotov

Chandramouli Visweswariah

Dung Tien Phan

Peter Anton Habitz

Gary S Ditlow

Vikram Iyengar

Jeanne P Bickford

Clifford A Pickover

Huamin Chen

Wen-mei William Hwu

David E Lackey

Lingfei Wu

I-Hsin Chung

Roland Ludwig Huss

Zaid Qureshi

James R Kozloski

John Maxwell Cohn

Brian Paul Gaucher

Natesan Venkateswaran

Yada Zhu

Pin-Yu Chen

David Shing-Ki Kung

Brian A Worth

Suma Bhat

Yiyu Shi

Hongyu Gong

Hubertus Franke

Rogerio Schmidt Feris

David James Hathaway

Eric A Foreman

Chai Wah Wu

Jayant R Kalagnanam

Chuang Gan

Debjit Sinha

Yang Zhang

Alexey Y Lvov

Soumyadip Ghosh

Geert Janssen

Gary Douglas Grise

Sijia Liu

Kumar Bhaskaran

Jian Huang

Minh Do

Shiyu Chang

Soroush Abbaspour

Mayank Sharma

Bhavna Agrawal

David E Cox

Nam Sung Kim

Kaizhi Qian

Gradus Janssen

Dhiraj Joshi

Francis Woytowich

Rajarshi Haldar

Gaoyuan Zhang

Raymond Alexander Yeh

Bo Li

Julia Constanze Hockenmaier

Meng Wang

Yunan Ye

Jose M Martinez

Hanif Fatemi

Chandramouli Viswewariah

Khoi-Nguyen C Mac

Ahmed Abulila

Vikram Sharma Mailthody

Ren Wang

Carl Pearson

One or more metrics associated with performance of a serverless function chain are received. The one or more metrics are used by a reinforcement learning (RL) model to tune the serverless function chain.

Utilizing reinforcement learning for serverless function tuning

A method includes detecting, by a webhook controller, an inference serverless function invocation. The method further includes determining that the inference serverless function can be optimized. The method further includes generating an optimized version of the inference serverless function using a graph compiler, in response to the determining. The method further includes replacing, by a processing device of the webhook controller, a storage volume in an init container of the inference serverless function with a new storage volume comprising the optimized version of the inference serverless function.

Resource constraint aware deep learning model optimization for serverless-based inference systems

A computer-implemented method is provided of using a machine learning model for disentanglement of prosody in spoken natural language. The method includes encoding, by a computing device, the spoken natural language to produce content code. The method further includes resampling, by the computing device without text transcriptions, the content code to obscure the prosody by applying an unsupervised technique to the machine learning model to generate prosody-obscured content code. The method additionally includes decoding, by the computing device, the prosody-obscured content code to synthesize speech indirectly based upon the content code.

Global prosody style transfer without text transcriptions

A processor training a reinforcement learning model can include receiving a first dataset representing an observable state in reinforcement learning to train a machine to perform an action. The processor receives a second dataset. Using the second dataset, the processor trains a machine learning classifier to make a prediction about an entity related to the action. The processor extracts an embedding from the trained machine learning classifier, and augments the observable state with the embedding to create an augmented state. Based on the augmented state, the processor trains a reinforcement learning model to learn a policy for performing the action, the policy including a mapping from state space to action space.

State-augmented reinforcement learning

An exemplary method includes solving on a computing system an optimal power flow formulation for a plurality of generators in a power system. The solving includes computing using multi-threaded parallelism a plurality of constraints for the formulation, computing using multi-threaded parallelism a plurality of Jacobian functions of the constraints, and computing using multi-threaded parallelism a Hessian of Lagrangian functions. The method further includes outputting results of the solving, wherein the results comprise values of generation levels for the plurality of generators. Apparatus and program products are also disclosed.

Parallel technique for computing problem functions in solving optimal power flow

A computer-implemented method for generating an abstract meaning representation ('AMR') of a sentence, comprising receiving, by a computing device, an input sentence and parsing the input sentence into one or more syntactic and/or semantic graphs. An input graph including a node set and an edge set is formed from the one or more syntactic and/or semantic graphs. Node representations are generated by natural language processing. The input graph is provided to a first neural network to provide an output graph having learned node representations aligned with the node representations in the input graph. The method further includes predicting via a second neural network, node label and predicting, via a third neural network, edge labels in the output graph. The AMR is generated based on the predicted node labels and predicted edge labels. A system and a non-transitory computer readable storage medium are also disclosed.

Abstract meaning representation parsing with graph translation

Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Action detection by exploiting motion in receptive fields

One or more computer processors generate a plurality of adversarial perturbations associated with a model, wherein the plurality of adversarial perturbations comprises a universal perturbation and one or more per-sample perturbations. The one or more computer processors identify a plurality of neuron activations associated with the model and the plurality of generated adversarial perturbations. The one or more computer processors maximize the identified plurality of neuron activations. The one or more computer processors determine the model is a Trojan model by leveraging one or more similarities associated with the maximized neuron activations and the generated adversarial perturbations.

Detecting trojan neural networks

One or more metrics associated with performance of a serverless function chain are received. The one or more metrics are analyzed by a reinforcement learning (RL) model to determine a tuning factor in view of a goal provided to the RL model. The tuning factor is transmitted to a serverless function controller, wherein the serverless function controller is to utilize the tuning factor to tune the serverless function chain.

Embodiments for providing critical path analysis of active trace files in a cloud computing environment. A critical path may be identified using a trace of time spans and activities of a plurality of applications, wherein the critical path is a set of activities having time spans free of overlap with other activities.

Critical path analysis of activity trace files

A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.

Text style transfer using reinforcement learning

A method includes determining a first upload start timestamp and a first upload end timestamp of a video file from a client device to an object storage device. The method further includes monitoring an upload of the video file from the object storage device to a server-less framework to determine a second upload start timestamp and a second upload end timestamp of the video file. The method further includes determining, by a processing device, a latency of the upload in view of the first upload timestamp, the second upload timestamp, the first upload end timestamp, and the second upload end timestamp. The method further includes providing a latency adjustment instruction to the client device in view of the latency.

Latency control notification for edge cloud streaming analytics service

Embodiments of the invention describe a computer-implemented method that includes receiving a query that includes a query sequence having query characters grouped into query words. A segment of program code is retrieved from a database for evaluation. The program code includes a program code sequence including program code characters grouped into program code words. The query sequence, the query word, the program code sequence, and the program code word are each converted to sequence and word representations. Query sequence-level features, query word-level features, program code sequence-level features, and program code word-level features are extracted from the sequence and word representation. Similarity between the query and the segment of program code is determined by applying a similarity metric technique to the query sequence-level features, the query word-level features, the program code sequence-level features, and the program code word-level features.

Multi-perspective, multi-task neural network model for matching text to program code

A first plurality of relational tables is obtained from a relational database. Each table of the first plurality of relational tables stores connectivity information for a graph that comprises a plurality of nodes and a plurality of edges connecting the nodes, and each of the nodes is assigned an initial identifier. The nodes are clustered into a plurality of clusters. Each cluster contains a subset of the nodes, and all nodes in each subset are close to each other according to a metric. Each node is assigned a new identifier. The new identifier comprises a concatenation of an identifier associated with the cluster to which the node belongs and an identifier associated with the node. A second plurality of relational tables is constructed and stores connectivity information for the graph. The node is identified in the second plurality of relational tables by the new identifier.

Fast path traversal in a relational database-based graph structure

Growing community of inventors

White Plains, NY, United States of America

Jinjun Xiong