Advanced New Technologies Co., Ltd.

Alibaba Group Holding Limited

Alipay (hangzhou) Information Technology Co., Ltd.

Alipay Information Technology Co., Ltd.

Yongchao Liu

Haitao Zhang

Guozhen Pan

Jianguo Xu

Qiyin Huang

Guanyin Zhu

Yichen Tu

Ni Zhou

Sizhong Li

Chengping Yang

Lin Wang

Yue Jin

Yufeng Guo

Bei Jia

Implementations of the present specification provide a model-based prediction method and apparatus. The method includes: a model running environment receives an input tensor of a machine learning model; the model running environment sends a table query request to an embedding running environment, the table query request including the input tensor, to request low-dimensional conversion of the input tensor; the model running environment receives a table query result returned by the embedding running environment, the table query result being obtained by the embedding running environment by performing embedding query and processing based on the input tensor; and the model running environment inputs the table query result into the machine learning model, and runs the machine learning model to complete model-based prediction.

Separate deployment of machine learning model and associated embedding

An example method for updating convolutional neural network includes: obtaining a sample with a classification label; performing a first operation on the sample based on parameters of each layer of front-end network, to obtain a first operation result; performing a second operation on the sample based on the first operation result and the parameters of each layer of back-end network that the first GPU has, to obtain a second operation result; separately sending the first operation result to the other GPUs; receiving a third operation result obtained after each other GPU performs a third operation on the sample based on their parameters of each layer of back-end network and the first operation result; combining the second and third operation results to obtain a classification result; determining a prediction error based on the classification result and the classification label; and updating the convolutional neural network based on the prediction error.

Method, apparatus and device for updating convolutional neural network using GPU cluster

The present specification discloses a trusted execution environment (TEE)-based model training method and apparatus. In one or more embodiments, the method includes: obtaining encrypted target samples from an encrypted training sample set in a first execution environment, inputting the encrypted target samples into a second execution environment that is a trusted execution environment (TEE) different from the first execution environment, decrypting the encrypted target samples in the TEE to obtain decrypted target samples, inputting the decrypted target samples into a feature extraction model in the TEE to determine sample features, determining the sample features output from the TEE as target sample features for a current iteration of a training process for a target model, and performing, based on the target sample features, the current iteration on the target model in the first execution environment.

Trusted execution environment-based model training methods and apparatuses

Embodiments of the present specification provide chips and chip-based data processing methods. In an embodiment, a method comprises: obtaining data associated with one or more neural networks transmitted from a server; for each layer of a neural network of the one or more neural networks, configuring, based on the data, a plurality of operator units based on a type of computation each operator unit performs; and invoking the plurality of operator units to perform computations, based on neurons of a layer of the neural network immediately above, of the data for each neuron to produce a value of the neuron.

Chip and chip-based data processing method

An FPGA hardware device obtains encrypted data of each participant of a secure computing system, where the FPGA hardware device stores at least one first key, where the at least one first key is at least one first key of all participants in the secure computing system or at least one first key of a predetermined number of trusted managers in the secure computing system, where the FPGA hardware device includes an FPGA chip. The FPGA hardware device decrypts the encrypted data of each participant by using a working key of each participant, to obtain plaintext data of each participant, where the working key of each participant is obtained based on a corresponding first key of the at least one first key. The FPGA hardware device performs computing based on the plaintext data of each participant to obtain a computing result. The FPGA hardware device outputs the computing result.

FPGA hardware-based secure computing method and apparatus

The present specification provides an article damage detection method, including: obtaining at least two images that are time sequentially related and show a detected article at different angles; and inputting the images to a detection model in time order, to determine a damage detection result, where the detection model includes a first sub-model and a second sub-model, the first sub-model identifies respective features of each image, a feature processing result of each image is input to the second sub-model, the second sub-model performs time series analysis on the feature processing result to determine the damage detection result, and the first sub-model and the second sub-model are obtained by performing joint training by using training samples labeled with article damage.

Article damage detection

N vehicle accident images are obtained, where N is a natural number greater than or equal to 2. N feature vectors are obtained by inputting the vehicle accident images into a trained convolutional neural network, where the N feature vectors respectively correspond to the vehicle accident images. A distance is calculated between any two feature vectors of the N feature vectors. A determination is made that two vehicle accident images of the N vehicle accident images corresponding to the distance are abnormal when the distance is greater than a first predetermined threshold.

Vehicle accident image processing method and apparatus

A computer-implemented method includes obtaining a trained convolutional neural network comprising one or more convolutional layers, each of the one or more convolutional layers comprising a plurality of filters with known filter parameters; pre-computing a reusable factor for each of the one or more convolutional layers based on the known filter parameters of the trained convolutional neural network; receiving input data to the trained convolutional neural network; computing an output of the each of the one or more convolutional layers using a Winograd convolutional operator based on the pre-computed reusable factor and the input data; and determining output data of the trained convolutional network based on the output of the each of the one or more convolutional layers.

Growing community of inventors

Hangzhou, China

Yongchao Liu