Microsoft Technology Licensing, LLC

Alexander Lloyd Gaunt

Antony Ian Taylor Rowstron

Reinhard Sebastian Bernhard Nowozin

Benn Charles Thomsen

Ioan Alexandru Stefanovici

Daniel Stefan Tarlow

Marc Manuel Johannes Brockschmidt

Aaron William Ogus

Andreas Georgiou

Richard John Black

Austin N Donnelly

Matthew Alastair Johnson

Sebastian Nowozin

Samuel Alexander Webster

Ariel Gomez Diaz

Patrick Neil Anderson

Rokas Drevinskas

David Lara Saucedo

James Hilton Clegg

Serguei Anatolievitch Legtchenko

Ryota Tomioka

Dimitrios Vytiniotis

Douglas Wayne Phillips

Hugh David Paul Williams

Maik Riechert

Matej Balog

Andromachi Chatzieleftheriou

John Christopher Dainty

Raluca Andreea Diaconu

Mengyang Yang

Miltiadis Allamanis

Pengcheng Yin

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.

Asynchronous neural network training

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.

Machine-learning optimization of data reading and writing

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.

Program predictor

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.

Automated content editor

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.

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.

Disaggregated data storage and retrieval system

Growing community of inventors

Cambridge, United Kingdom

Alexander Lloyd Gaunt