-
1.发明授权公开(公告)号：US11101029B2
公开(公告)日：2021-08-24
申请号：US16207114
申请日：2018-12-01
申请人： Petuum Inc.
发明人： Pengtao Xie , Eric Xing
IPC分类号： G16H20/10 , G16H10/60 , G06N20/00 , G16B40/00 , G16H50/20 , G16H70/60 , G06N3/08 , G16H15/00 , G16H30/40 , G06K9/46 , G06K9/62 , G06T7/00 , G06F16/36 , H04L29/08 , G06F40/284 , G16H50/70 , G16B50/00 , G06K9/72
摘要： A system for predicting medications to prescribe to a patient includes a text encoding module and a medication prediction module. The text encoding module is configured to obtain a clinical-information vector from clinical information of the patient. The medication prediction module configured to apply a machine-learned medication-prediction algorithm to the clinical-information vector to select a subset of medications to prescribe to the patient. The machine-learned medication-prediction algorithm is designed with a diversity-promoting regularization model, and is configured to simultaneously consider correlations among different medications and dependencies between patient information and medications when selecting a subset of medications to prescribe to the patient.
-
公开(公告)号：US20200293721A1
公开(公告)日：2020-09-17
申请号：US16886478
申请日：2020-05-28
申请人： PETUUM INC.
发明人： Pengtao Xie , Eric Xing
IPC分类号： G06F40/30 , G06N3/04 , G06N3/08 , G06F16/332 , G06N5/04 , G06N5/02 , G06F40/205 , G06F40/216
摘要： A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.
-
公开(公告)号：US20190026870A1
公开(公告)日：2019-01-24
申请号：US15946492
申请日：2018-04-05
申请人： Petuum Inc.
发明人： Zhiting Hu , Eric Xing , Chenyu Wang
CPC分类号： G06T5/005 , G06T5/50 , G06T11/00 , G06T2207/20084 , G06T2207/20092
摘要： A system for manipulating images according to styles chosen by a user includes a feed-forward image manipulation model for everyday use and an optimization image manipulation model for more professional use. The optimization image manipulation model optimizes directly over output image pixels to minimize both the content loss and style loss. Users can select their own content and style images, and can choose between using the feed-forward image manipulation model and optimization image manipulation model.
-
公开(公告)号：US20180300314A1
公开(公告)日：2018-10-18
申请号：US15948241
申请日：2018-04-09
申请人： Petuum Inc.
发明人： Pengtao Xie , Eric Xing
摘要： A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.
-
公开(公告)号：US11106998B2
公开(公告)日：2021-08-31
申请号：US15814394
申请日：2017-11-16
申请人： Petuum inc
摘要： A computer in a distributed computing system is disclosed. The computer includes: a graphics processing unit (GPU) memory; a central processing unit (CPU) memory comprising a Key-Value Store (KVS) module; an execution engine module configured to run a deep learning (DL) program to create a plurality of operator graph layers in the graphics processing unit memory; a client library module configured to create a GPU-CPU synchronization (GCS) module for each of the plurality of operator graph layers; a coordination service module configured to compute network cost of a first and a second communication scheme and select, based on the network cost, one of the first and second communication scheme for transmitting data associated with one of the plurality of operator graph layers from a corresponding GCS module.
-
公开(公告)号：US20210026818A1
公开(公告)日：2021-01-28
申请号：US17009883
申请日：2020-09-02
申请人： Petuum Inc.
摘要： Accordingly, a data engineering system for machine learning at scale is disclosed. In one embodiment, the data engineering system includes an ingest processing module having a schema update submodule and a feature statistics update submodule, wherein the schema update submodule is configured to discover new features and add them to a schema, and wherein the feature statistics update submodule collects statistics for each feature to be used in an online transformation, a record store to store data from a data source, and a transformation module, to receive a low dimensional data instance from the record store and to receive the schema and feature statistics from the ingest processing module, and to transform the low dimensional data instance into a high dimensional representation. One embodiment provides a method for data engineering for machine learning at scale, the method including calling a built-in feature transformation or defining a new transformation, specifying a data source and compressing and storing the data, providing ingest-time processing by automatically analyzing necessary statistics for features, and then generating a schema for a dataset for subsequent data engineering. Other embodiments are disclosed herein.
-
公开(公告)号：US10832387B2
公开(公告)日：2020-11-10
申请号：US15946492
申请日：2018-04-05
申请人： Petuum Inc.
发明人： Zhiting Hu , Eric Xing , Chenyu Wang
摘要： A system for manipulating images according to styles chosen by a user includes a feed-forward image manipulation model for everyday use and an optimization image manipulation model for more professional use. The optimization image manipulation model optimizes directly over output image pixels to minimize both the content loss and style loss. Users can select their own content and style images, and can choose between using the feed-forward image manipulation model and optimization image manipulation model.
-
公开(公告)号：US10706234B2
公开(公告)日：2020-07-07
申请号：US15948241
申请日：2018-04-09
申请人： Petuum Inc.
发明人： Pengtao Xie , Eric Xing
IPC分类号： G06F40/30 , G06N3/04 , G06N3/08 , G06F16/332 , G06N5/04 , G06N5/02 , G06F40/205 , G06F40/216
摘要： A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.
-
公开(公告)号：US10699412B2
公开(公告)日：2020-06-30
申请号：US15925998
申请日：2018-03-20
申请人： Petuum, Inc.
发明人： Wei Dai , Xiaodan Liang , Hao Zhang , Eric Xing , Joseph Doyle
摘要： Organ segmentation in chest X-rays using convolutional neural networks is disclosed. One embodiment provides a method to train a convolutional segmentation network with chest X-ray images to generate pixel-level predictions of target classes. Another embodiment will also train a critic network with an input mask, wherein the input mask is one of a segmentation network mask and a ground truth annotation, and outputting a probability that the input mask is the ground truth annotation instead of the prediction by the segmentation network, and to provide the probability output by the critic network to the segmentation network to guide the segmentation network to generate masks more consistent with learned higher-order structures.
-
公开(公告)号：US11348030B2
公开(公告)日：2022-05-31
申请号：US15849662
申请日：2017-12-20
申请人： Petuum Inc.
摘要： Methods and systems are presented for consuming different data sources, and deploying artificial intelligence and machine learning programs on different target devices or infrastructures. Many data types can be transformed into machine learning data shards (MLDS) while many machine learning programs written in various programming languages or frameworks are transformed to common operator representations. Operator representations are transformed into execution graphs (EG) for a chosen target device or infrastructure. The MLDS and EG are input to the targeted devices and infrastructures, which then execute the machine learning programs (now transformed to EGs) on the MLDS to produce trained models or predictions with trained models.
-
-
-
-
-
-
-
-
-
搜索结果
36 条记录 (耗时 0.013 秒)
