International Business Machines Corporation

Globalfoundries Inc.

Chao Xue

Qing Fa Wang

Yonghua Lin

Rong Yan

Chao Zhu

Mingqiang Li

Yubo Li

Hai Zhan

Xinhao Cheng

Yong Hua Lin

Wei Dong Wang

Yu Meng Li

Ke Wei Sun

Yonggang Hu

Mingming Cai

Xin Xiong

Yu Ying Wang

Junchi Yan

Jun Song Wang

Tian Cheng Liu

Yafei Liu

Chang Xu

Weining Xi

Lin Dong

Boa Hua Yang

Tao Wang

Fan Yang

Ning Duan

Chao Zhang

Wei Shan Dong

Wei Zhao

Yue Hua Zhang

Min Gong

Yu Zheng

Yi Ge

Leonid Karlinsky

Yu Song

Yun Jie Qiu

Baohua Yang

Qing Wang

Xiaoxing Wang

J I Azhen

Using a training portion of a dataset, a set of component parameters comprising parameters of a component of an object detection model are trained. Using the trained set of component parameters, a set of backbone component weights comprising weights of component types in a backbone portion of the object detection model are trained. Using the trained set of component parameters, a set of backbone link weights comprising weights of links within the backbone portion are trained. Using the trained set of component parameters, a set of head component weights comprising weights of component types in a head portion of the object detection model are trained. Using the trained sets of component parameters, backbone component weights, backbone link weights, and head component weights, a trained object detection model is configured and trained to perform object detection.

Automated end-to-end machine learning model optimization

Methods, computer program products, and/or systems are provided that perform the following operations: obtaining a target neural network structure and constraints for a target neural network; generating a meta learning network having an associated quantization function based, at least in part, on the target neural network structure; training the meta learning network based, at least in part, on providing a hybrid quantization vector as input to the meta learning network and providing a training dataset to the target neural network; obtaining a plurality of hybrid quantization vectors; determining a new hybrid quantization vector from the plurality of hybrid quantization vectors; and retraining the trained meta learning network based, at least in part, on providing the new hybrid quantization vector as input to the trained meta learning network.

Automatic hybrid quantization for deep neural network

A one-shot neural architecture search method referred to as MergeNAS by merging different types of convolutions into a single operation. This mergence approach reduces the search cost to roughly half a GPU-day as well as alleviates the over-fitting problem caused by a traditional differentiable architecture search (DARTS) approach by reducing the number of redundant parameters.

Merge operations for darts

A method, system, and computer program product for hyper-parameter determination. In a method, a network architecture of a learning model may be determined, and the learning model may be configured for performing a computing task based on machine learning. A metric value record associated with a group of hyper-parameters may be obtained during hyper-parameter determination for the learning model. An estimation of a metric value may be obtained based on the network architecture, and the metric value record and an association relationship representing an association between network architectures and metric values for the network architectures. The group of hyper-parameters may be selected in response to the estimation of the metric value meeting a predefined criterion. With these embodiments, a group of hyper-parameters may be selected, and further the learning model may be trained based on the selected group of hyper-parameters.

Hyper-parameter management

Aspects of the invention include systems and methods to obtain meta features of a dataset for training in a deep learning application. A method includes selecting an initial search space that defines a type of deep learning architecture representation that specifies hyperparameters for two or more neural network architectures. The method also includes applying a search strategy to the initial search space. One of the two or more neural network architectures are selected based on a result of an evaluation according to the search strategy. A new search space is generated with new hyperparameters using an evolutionary algorithm and a mutation type that defines one or more changes in the hyperparameters specified by the initial search space, and, based on the mutation type, the new hyperparameters are applied to the one of the two or more neural networks or the search strategy is applied to the new search space.

Search space exploration for deep learning

Delivery robot chassis

Set of wheels for a delivery robot chassis

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

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 and a server for device positioning. The computer-implemented method includes receiving a control message from a positioning server. The control message indicates a set of channels associated with an area and time periods for monitoring the set of channels. At least one measurement of a signal from at least one of a reference device for the area and a target device is obtained, according to the control message, with the reference device being located at a predefined position with respect to the area. The at least one measurement is reported to the positioning server for determining a position of the target device with respect to the area.

Device positioning

A computer-implemented method uses a predictive time-sequence model to adapt hardware configurations at run-time for an application including multiple stages of execution. At each stage a system monitor is started at the launch of a first task in a first run to collect performance data. The system monitor is stopped at the completion of a last task in the first run, then a predictive optimal configuration is computed and applied to the remaining runs in the stage.

Adaptive hardware configuration for data analytics

A computer-implemented method and a server for device positioning. The computer-implemented method includes sending a control message to a detector. The control message indicates a set of channels associated with an area and time periods for monitoring the set of channels. A measurement of a signal from a device for the area and a target device is received from the detector. Position of the target device with respect to the area is determined based on a measurement and a radio map. The radio map indicates signal strength corresponding to positions in the area.

A home base station system and method for managing data caching. The home base station system includes: a plurality of home base stations used to provide wireless communication to at least one mobile terminal, wherein the plurality of home base stations are connected to a wide area network via a local area network, and wherein the plurality of home base stations are interconnected via a local area network; and a server, wherein the server is connected to the plurality of home base stations via the local area network, and wherein the server is used to manage caching of data in a home base station system.

Home base station system and data access processing method thereof

Growing community of inventors

Beijing, China

Chao Xue