-
公开(公告)号：US20210224355A1
公开(公告)日：2021-07-22
申请号：US17301473
申请日：2021-04-05
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ioan Alexandru STEFANOVICI , Benn Charles Thomsen , Alexander Lloyd Gaunt , Antony Ian Taylor Rowstron , Reinhard Sebastian Bernhard Nowozin
Abstract: Examples are disclosed that relate to encoding data on a data-storage medium. The method comprises obtaining a representation of a measurement performed on the data-storage medium, the representation being based on a previously recorded pattern of data encoded in the data-storage medium in a layout that defines a plurality of data locations. The method further comprises inputting the representation into a data decoder comprising a trained machine-learning function, and obtaining from the data decoder, for each data location of the layout, a plurality of probability values, wherein each probability value is associated with a corresponding data value and represents the probability that the corresponding data value matches the actual data value in the previously recorded pattern of data at a same location in the layout.
-
公开(公告)号：US11816457B2
公开(公告)日：2023-11-14
申请号：US17006641
申请日：2020-08-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexander Lloyd Gaunt , Sebastian Nowozin , Marc Manuel Johannes Brockschmidt , Daniel Stefan Tarlow , Matej Balog
IPC: G06F8/35 , G06N20/00 , G06N20/20 , G06F40/18 , G06N3/044 , G06N5/01 , G06N20/10 , G06F9/445 , G06N3/084 , G06N3/045 , G06N3/048 , G06F17/17 , G06F16/10 , G06F16/903 , G06N5/022
CPC classification number: G06F8/35 , G06F9/445 , G06F40/18 , G06N3/044 , G06N3/045 , G06N3/048 , G06N3/084 , G06N5/01 , G06N20/00 , G06N20/20 , G06F16/10 , G06F16/90348 , G06F17/175 , G06N5/022 , G06N20/10
Abstract: A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.
-
公开(公告)号：US11288575B2
公开(公告)日：2022-03-29
申请号：US15599058
申请日：2017-05-18
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ryota Tomioka , Matthew Alastair Johnson , Daniel Stefan Tarlow , Samuel Alexander Webster , Dimitrios Vytiniotis , Alexander Lloyd Gaunt , Maik Riechert
Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
-
公开(公告)号：US10719239B2
公开(公告)日：2020-07-21
申请号：US15981789
申请日：2018-05-16
Applicant: Microsoft Technology Licensing, LLC
Inventor： Antony Ian Taylor Rowstron , Ioan Alexandru Stefanovici , Aaron William Ogus , Douglas Wayne Phillips , Richard John Black , Austin Nicholas Donnelly , Alexander Lloyd Gaunt , Andreas Georgiou , Ariel Gomez Diaz , Serguei Anatolievitch Legtchenko , Reinhard Sebastian Bernhard Nowozin , Benn Charles Thomsen , Hugh David Paul Williams , David Lara Saucedo , Patrick Neil Anderson , Andromachi Chatzieleftheriou , John Christopher Dainty , James Hilton Clegg , Raluca Andreea Diaconu , Rokas Drevinskas , Mengyang Yang
IPC: G11B7/0065 , G06F3/06 , G06N20/00 , G11B7/085
Abstract: A data-storage system comprises a head receiver configured to variably receive up to a number M of write heads. The data-storage system also includes an installed number N of write heads arranged in the head receiver, a substrate receiver configured to receive one or more data-storage substrates, and a positioner machine configured to adjust a relative placement of each of the M write heads with respect to at least one of the one or more data-storage substrates.
-
公开(公告)号：US12099927B2
公开(公告)日：2024-09-24
申请号：US17706586
申请日：2022-03-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ryota Tomioka , Matthew Alastair Johnson , Daniel Stefan Tarlow , Samuel Alexander Webster , Dimitrios Vytiniotis , Alexander Lloyd Gaunt , Maik Riechert
Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
-
Patent Agency Ranking
公开(公告)号：US11150875B2
公开(公告)日：2021-10-19
申请号：US16145041
申请日：2018-09-27
Applicant: Microsoft Technology Licensing, LLC
Inventor： Marc Manuel Johannes Brockschmidt , Miltiadis Allamanis , Alexander Lloyd Gaunt , Pengcheng Yin
Abstract: An editing tool is described which has a memory storing a neural network having been trained to compute a change representation from pairs, each pair comprising a representation of a first version of a content item and a second version of the content item, and for each of the change representations, predict an updated content item from the change representation and the first version of the content item. The editing tool has a processor configured to receive an input content item and to compute an updated version of the input content item according to a change representation, using the neural network.
-
公开(公告)号：US10782939B2
公开(公告)日：2020-09-22
申请号：US15671110
申请日：2017-08-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexander Lloyd Gaunt , Sebastian Nowozin , Marc Manuel Johannes Brockschmidt , Daniel Stefan Tarlow , Matej Balog
IPC: G06F8/35 , G06N20/00 , G06F9/445 , G06N5/00 , G06N3/04 , G06N20/20 , G06N3/08 , G06F40/18 , G06F17/17 , G06F16/10 , G06F16/903 , G06N5/02 , G06N20/10
Abstract: A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.
-
公开(公告)号：US10768825B2
公开(公告)日：2020-09-08
申请号：US16680865
申请日：2019-11-12
Applicant: Microsoft Technology Licensing, LLC
Inventor： Antony Ian Taylor Rowstron , Ioan Alexandru Stefanovici , Aaron William Ogus , Douglas Wayne Phillips , Richard John Black , Austin Nicholas Donnelly , Alexander Lloyd Gaunt , Andreas Georgiou , Ariel Gomez Diaz , Serguei Anatolievitch Legtchenko , Reinhard Sebastian Bernhard Nowozin , Benn Charles Thomsen , Hugh David Paul Williams , David Lara Saucedo , Patrick Neil Anderson , Andromachi Chatzieleftheriou , John Christopher Dainty , James Hilton Clegg , Raluca Andreea Diaconu , Rokas Drevinskas , Mengyang Yang
Abstract: A data-storage system comprises a head receiver configured to variably receive up to a number M of write heads. The data-storage system also includes an installed number N of write heads arranged in the head receiver, a substrate receiver configured to receive one or more data-storage substrates, and a positioner machine configured to adjust a relative placement of each of the M write heads with respect to at least one of the one or more data-storage substrates.
-
公开(公告)号：US12019705B2
公开(公告)日：2024-06-25
申请号：US17301473
申请日：2021-04-05
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ioan Alexandru Stefanovici , Benn Charles Thomsen , Alexander Lloyd Gaunt , Antony Ian Taylor Rowstron , Reinhard Sebastian Bernhard Nowozin
CPC classification number: G06F17/18 , G06F11/3692 , G06F16/2474 , G06N20/00 , G11B20/10009 , G11B20/10268 , H03M5/06 , H03M13/37
Abstract: Examples are disclosed that relate to encoding data on a data-storage medium. The method comprises obtaining a representation of a measurement performed on the data-storage medium, the representation being based on a previously recorded pattern of data encoded in the data-storage medium in a layout that defines a plurality of data locations. The method further comprises inputting the representation into a data decoder comprising a trained machine-learning function, and obtaining from the data decoder, for each data location of the layout, a plurality of probability values, wherein each probability value is associated with a corresponding data value and represents the probability that the corresponding data value matches the actual data value in the previously recorded pattern of data at a same location in the layout.
-
公开(公告)号：US10970363B2
公开(公告)日：2021-04-06
申请号：US15786347
申请日：2017-10-17
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ioan Alexandru Stefanovici , Benn Charles Thomsen , Alexander Lloyd Gaunt , Antony Ian Taylor Rowstron , Reinhard Sebastian Bernhard Nowozin
Abstract: Examples are disclosed that relate to reading stored data. The method comprises obtaining a representation of a measurement performed on a data-storage medium, the representation being based on a previously recorded pattern of data encoded in the data-storage medium in a layout that defines a plurality of data locations. The method further comprises inputting the representation into a data decoder comprising a trained machine-learning function, and obtaining from the data decoder, for each data location of the layout, a plurality of probability values, wherein each probability value is associated with a corresponding data value and represents the probability that the corresponding data value matches the actual data value in the previously recorded pattern of data at a same location in the layout.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.014 seconds)
