International Business Machines Corporation

Vmware, Inc.

Globalfoundries Inc.

Yonghua Lin

Qing Fa Wang

Rong Yan

Chao Xue

Chao Zhu

Jianbin Tang

Junsong Wang

Jun Song Wang

Yubo Li

Yi Ge

Lin Chen

Li Li

Jian Ye Chen

Hang Liu

Yi Zhao

Shi Lei Zhang

Ke Wei Sun

Ravinder Kumar Sabhikhi

Yan Li

Jie Zhang

Liang Chen

Kang-Won Lee

Dan Li

Kai Zheng

Murtaza Zafer

Qing Bo Wang

Ji Hui Yang

Yonggang Hu

Yu Fen Yuan

Hai Zhan

Xinhao Cheng

Mingqiang Li

Zhen Bo Zhu

Wei Dong Wang

Yan Qi Wang

Zhiyong Liang

Yan Gong

Rui Xiong Tian

Qi Jun Wang

Xiaoding Bian

Jian Wen Chen

Li Hui Guo

Kuan Feng

Ting He

Haibo Lin

Yudong Yang

Sheng Xu

Yu Song

Ke Jin

Qiming Teng

Zhi Liang

You Zhou

Chang Xu

Guang Lu

Yanyan Hu

Junping Du

Hong Hua Song

Chien Dinh Vu

Bhavesh Dhanji Budhabhatti

Binbin Zhao

Qiuhui Li

Xian Wei Yi

Yan Qi Bldg 19 Zhongguancun Software Park Wang

A computer-implemented method for data augmentation is provided according an embodiment of the present disclosure. In the method, a first feature vector for input data may be obtained based on a first model. The input data may be clustered to a plurality of clusters. For each of the clusters, a second feature vector may be obtained based on the first model. Then, a similarity between the first feature vector and the second feature vector may be estimated for each of the clusters. At least one cluster of the plurality of clusters for which the similarity is lower than a threshold may be determined. Moreover, data augmentation may be performed to the at least one cluster.

Data augmentation

The present disclosure relates to methods, systems, and computer program products for implementing a deep neural network in a field-programmable gate array (FPGA). In response to receiving a network model describing a deep neural network, a plurality of layers associated with the deep neural network may be determined. With respect to a layer in the plurality of layers, a parallelism factor for processing operations associated with the layer simultaneously by processing elements in an FPGA may be determined based on a workload associated with the layer and a configuration of the FPGA.

Deep neural network implementation

Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.

Automatic monitoring and adjustment of machine learning model training

According to one embodiment, a method, computer system, and computer program product for generating anchors and selecting feature maps for a multi-scale object detection program based on analysis of the dataset is provided. The present invention may include generating a scale distribution of one or more scales of ground-truth objects, and, based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero; furthermore, the invention may include generating a ratio distribution of ratios of the ground-truth objects; based on the ratio distribution, generating a ratio for at least one of the number of anchors; determining a template scale of one or more feature maps; and assigning the number of anchors to the feature maps based on the relative size of a scale of an anchor matching the relative size of a template scale of a feature map.

Dataset driven custom learning for multi-scale object detection

A computer-implemented method for attention generation is provided. In this method, a plurality of image frames can be obtained from a video stream. An original attention for a first image frame of the plurality of image frames can be generated. Then, at least one interested area can be identified in the first image frame. A local attention for each of the at least one interested area can be generated. Moreover, a total attention for the first image frame can be generated based on the original attention of the first image frame and the local attention of each of the at least one interested area.

Attention generation

A method, computer system, and computer program product for model selection for training a new dataset is provided. The present invention may include choosing a model from a set of models to be evaluated for training the new dataset, selecting a sample input from a subset of the new dataset, calculating a model activation score for each of the sample inputs in the chosen model, calculating an accumulated model activation score for the chosen model, depending on the model activation score of each of the sample inputs in the chosen model, calculating an accumulated model activation score for each model from the set of models to be evaluated for training the new dataset, and selecting the model for training the new dataset with the highest accumulated model activation score.

Model matching and learning rate selection for fine tuning

The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.

Object detection optimization

A method comprises receiving a first received signal strength indicator (RSSI) of a first beacon in an array of beacons and receiving a second RSSI of a second beacon in an array of beacons, calculating a RSSI of the array (r) as a function of the first RSSI and the second RSSI, retrieving a calibrated RSSI value of the array (r') from a memory, determining whether r&#x3e;r&#x2032;, and outputting a signal to a user device responsive to determining that r&#x3e;r&#x2032;.

Beacon array

A computer implemented method of detecting excessive customer wait times is provided. The method includes taking a headcount in a digital image obtained by a digital video camera of a monitored area, counting the number of bodies in the digital image, and rectifying the number of heads with the number of bodies to obtain a total count of persons. The method further includes determining which persons are moving and subtracting the moving persons from the total count of persons to obtain a still count, and determining which persons are workers and subtracting the workers from the still count to identify customers in the monitored area and obtain a customer count. The method further includes identifying the number of queues present in the monitored area, assigning each customer to a queue, and determining the wait time for each of the identified customers in each of the identified queues.

Realtime video monitoring applied to reduce customer wait times

A method, system and computer program product for accelerating a deep neural network (DNN) in a field-programmable gate array (FPGA) are disclosed. The method includes receiving a DNN net file and weights, converting the received DNN net file to one or more source files, generating an executable FPGA bit file using the one or more source files, and downloading the executable FPGA bit file from the DNN conversion platform to the FPGA. Converting of the received DNN net file and the weights to the one or more source files can further include analyzing the DNN net file to identify a plurality of neural layers, decomposing one or more neural layers of the plurality of neural layers to one or more operation blocks, instantiating the one or more source files, based on the one or more operation blocks.

Accelerate deep neural network in an FPGA

Example methods are provided to perform disk assignment for multiple distributed computing clusters in a virtualized computing environment. The method may include determining whether disk assignment is required for a host to support a first virtualized computing instance from a first distributed computing cluster and a second virtualized computing instance from a second distributed computing cluster. The method may also include migrating first data placed on one or more second disks to one or more first disks, reassigning the one or more second disks from the first virtualized computing instance to the second virtualized computing instance, and placing second data on the one or more second disks. The first data may be for access by the first virtualized computing instance to execute a first distributed computing application, and the second data may be for access by the second virtualized computing instance to execute a second distributed computing application.

Disk assignment for multiple distributed computing clusters in a virtualized computing environment

Synchronization method and apparatus for a wireless wide band system in an interference environment. The method includes: obtaining interference information of a network; selecting at least one channel based at least in part on the interference information; and transmitting resource information through the at least one channel, wherein the resource information indicates a resource allocation determined at least in part on the interference information; and wherein a position of the at least one channel is indicated by a synchronization sequence. The present invention also provides another method and apparatus for synchronization.

Synchronization method and apparatus for a wireless wide band system in an interference environment

Embodiments include methods and apparatuses for allocating computing elements in a data receiving link. Aspects include receiving baseband data in the data receiving link and allocating a computing element from a resource pool of computing elements for converting the baseband data to transmission block data.

Computing element allocation in data receiving link

Growing community of inventors

Beijing, China

Yonghua Lin