Emc IP Holding Company LLC

Dell Products Inc.

Carl Zeiss Meditec Ag

Emc IP Holdinq Company LLC

Jinpeng Liu

Zhen Jia

Jiacheng Ni

Zijia Wang

Pengfei Wu

Jin Li

Kun Wang

Qiang Chen

Danqing Sha

Zhi Ying

Christopher S MacLellan

Junping Zhao

Tianxiang Chen

Tao Ma

Kenneth Durazzo

Ming Zhang

Graham Keevy

Christian Siegel

Xiao Han

WuiChak Wong

Michael Estrin

Sulun Jiang

Sanping Li

Wenbin Yang

YuHong Nie

Andrew Anzhou Hou

Chao Chen

Bin He

Si Ruo Chen

Mengze Liao

Zhenzhen Lin

Anzhou Hou

Hai Long Li

Ruixue Zhang

Min Chao Zhao

Cherami Min Liu

Yongjun Shi

Sarah Evans

Quanrong Gong

Jianwei Shu

Yongjie Zhao

Wenqing Peng

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for deploying a machine learning model. The method includes: acquiring a machine learning model in accordance with an open neural network exchange format; converting the machine learning model to an intermediate representation using a multi-level intermediate representation method; and deploying a computation associated with the machine learning model to at least one computing device using the intermediate representation.

Method, electronic device, and computer program product for deploying machine learning model

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for acquiring an image. The method includes distilling an original image set through a capsule neural network model to generate a distilled image set, wherein the distilled image set includes a plurality of distilled images. The method further includes acquiring a first feature of a first image through the capsule neural network model. The method further includes acquiring a plurality of distilling features of the plurality of distilled images respectively through the capsule neural network model. The method further includes determining a plurality of similarities between the first feature and the plurality of distilling features respectively. The method further includes acquiring at least one original image matching the first image based on the plurality of similarities.

Method, electronic device, and computer program product for acquiring image

Embodiments of the present disclosure relate to a model optimization method, an electronic device, and a computer program product. This method includes: determining an initial learning rate combination for a deep learning model, wherein the initial learning rate combination includes a plurality of learning rates, each learning rate being determined for one of a plurality of layers of the deep learning model, and the plurality of learning rates including static learning rates and dynamic learning rates; and adjusting the initial learning rate combination to obtain a target learning rate combination, wherein an accuracy rate achieved when the target learning rate combination is used to train the deep learning model is higher than or equal to a first threshold accuracy rate. With the technical solution of the present disclosure, a deep learning model can be optimized by setting learning rates for each layer of the deep learning model.

Model optimization method, electronic device, and computer program product

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for distributed data processing. A method in one embodiment comprises obtaining an input for a data processing task based on a multi-head attention mechanism, the data processing task comprising a first subtask and a second subtask, the first subtask corresponding to a first attention head in the multi-head attention mechanism, and the second subtask corresponding to a second attention head in the multi-head attention mechanism. The method further comprises transmitting the input to a first dedicated computing resource and a second dedicated computing resource, the first dedicated computing resource corresponding to the first subtask, and the second dedicated computing resource corresponding to the second subtask, and performing the first subtask and the second subtask on the input for obtaining an output of the data processing task.

Method, electronic device, and computer program product for distributed data processing

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for session switching. The method includes: establishing a first session with a first terminal in response to a session request initiated by the first terminal. The method further includes: generating first response information to first request information from the first terminal. The method further includes: determining a first confidence level of the first response information; and determining, in response to the first confidence level being lower than a confidence level threshold, to switch the first session to a second session between the first terminal and a second terminal. The method for session switching according to embodiments of the present disclosure can provide a fast and satisfactory response to a request made by a user, thereby effectively satisfying the user requirements and significantly improving the user experience.

Method, electronic device, and computer program product for session switching

A decoupled artificial intelligence model management architecture comprises a front-end component, a scheduler component and a back-end component configured to enable an open and dynamic system which accepts any models from any formats to be deployed on any target devices and to dynamically change scheduling of parallelism, parameter movements and computation executions across the target devices.

Decoupled architecture for artificial intelligence model management

Embodiments of the present disclosure relate to a method, a device, and a computer program product for inference. The method includes determining, for a layer in a neural network model, whether a weight matrix of the layer is an irreversible target matrix. The method further includes partitioning, in response to determining that the weight matrix of the layer is the target matrix, the neural network model into a first part and a second part, wherein the first part includes the layer and a previous layer before the layer and is deployed inside a security space, and the second part includes a subsequent layer after the layer and is deployed outside the security space. The method further includes acquiring an inference result by using the partitioned neural network model based on encrypted inference data.

Method, device, and program product for inference

Embodiments of the present disclosure relate to a method for generating a cross-modality encoder. The method includes: extracting a sample video feature of a sample video, a sample audio feature of a sample audio, and a sample text feature of a sample text, wherein contents of the sample video, the sample audio, and the sample text are associated with each other. The method further includes: generating, by the cross-modality encoder, a first cross-modality sample feature by combining the sample video feature, the sample audio feature, and the sample text feature; generating a scrambled cross-modality sample feature by performing a scrambling operation on the cross-modality feature; generating by the cross-modality encoder a second cross-modality sample feature by encoding the scrambled cross-modality sample feature; and tuning the cross-modality encoder based on the first cross-modality sample feature and the second cross-modality sample feature.

Method, electronic device, and computer program product for generating cross-modality encoder

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for scheduling computing resources. In a method for scheduling computing resources provided by embodiments of the present disclosure, a computing graph for a neural network is acquired, wherein the computing graph includes at least a plurality of nodes, and each node includes at least an operator for forward propagation of the neural network and a gradient operator of the operator for back propagation of the neural network; and computing resources for the neural network are scheduled based on the computing graph. In this way, a correlation of operators between forward propagation and back propagation may be preserved. In addition, there is no need to schedule computing resources again during back propagation. Resource scheduling for forward propagation and back propagation may be completed simultaneously with only one scheduling operation.

Method, electronic device, and computer program product for scheduling computing resources

Methods, apparatus, and processor-readable storage media for authenticating usage data for processing by machine learning models are provided herein. An example method includes receiving, by a machine learning application installed in a user space of an operating system of a user device, a message from a software component, wherein the software component is: configured to collect usage data associated with the user device; signed with using private key corresponding to a digital certificate by an application installed on the user device; and deployed in a kernel space of the operating system, and wherein the message comprises usage data signed using the private key; authenticating, by the machine learning application, the usage data based on a public key corresponding to the digital certificate; and processing, by the machine learning application in response to a result of the authenticating, at least a portion of the authenticated usage data.

Authenticating usage data for processing by machine learning models

Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.

Training data protection for artificial intelligence model in partitioned execution environment

A method in an illustrative embodiment comprises collecting a plurality of audio signals from a plurality of sensors, and combining the plurality of audio signals to generate synthetic audio, wherein the plurality of sensors are located at different locations in the same space, and the plurality of audio signals each have a location identifier. The method further comprises analyzing the synthetic audio to find an audio subset in the plurality of audio signals, and extracting first image features of a first image of the space. The method further comprises modifying the first image features based on the location identifiers of the audio signals in the audio subset to generate second image features, and generating a second image of the space based on the second image features.

Method, electronic device, and computer program product for image processing

Embodiments of the present disclosure relate to a method, a device, and a computer program product for executing computer programs. The method includes implementing multiple executions of a deep neural network that includes a hooking portion outside a trusted execution environment (TEE), wherein an operator in the hooking portion, when executed outside the TEE, invokes a corresponding execution operator in the TEE. During the period, the method includes determining, on the basis of the invocation of the corresponding execution operator in the TEE by the operator in the hooking portion, a computation graph corresponding to the hooking portion. The method further includes executing, on the basis of the computation graph, the execution operator corresponding to the hooking portion in the TEE during the execution of the deep neural network after the multiple executions.

Method, device, and computer program product for executing computer programs

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for content recommendation. A method for content recommendation includes determining a similarity between a first recommendation result and a second recommendation result for a content set. The first recommendation result and the second recommendation result are determined based on different recommendation techniques and respectively indicative of a recommendation degree for each content in the content set. The method further includes adjusting the second recommendation result using the similarity. In addition, the method further includes determining a target recommendation result for the content set based on the first recommendation result and the adjusted second recommendation result. In this manner, the accuracy and stability of the finally obtained recommendation results can be improved.

Method, electronic device, and computer program product for content recommendation

Embodiments of the present disclosure relate to a method, a device, and a computer program product for user behavior prediction. In some embodiments, at a client, a first user behavior embedding engine in the client generates behavior prediction information of a target user based on feature information of the target user. The client sends the behavior prediction information of the target user to a server, and receives information about a target item recommended for the target user from the server. Such method enables user privacy-related information to be processed only locally, thereby not only ensuring user privacy and security, but also significantly reducing overall resource overhead.

Method, device, and computer program product for user behavior prediction

Growing community of inventors

Shanghai, China

Jinpeng Liu