公开(公告)号：US20240143984A1

公开(公告)日：2024-05-02

申请号：US18491261

申请日：2023-10-20

申请人： CVS Pharmacy, Inc.

发明人： David Rimshnick ,  Grigoriy Koytiger ,  Joshua Hug

IPC分类号： G06N3/049 ,  G06N3/0455 ,  G06N3/0499 ,  G06N3/09

CPC分类号： G06N3/049 ,  G06N3/0455 ,  G06N3/0499 ,  G06N3/09

摘要： A system is provided including a data pipeline and a model pipeline. A data pipeline includes: an input that receives a first dataset representing categorical features and a second dataset representing numerical features; a feature ingestion block that generates an output corresponding to a sum of the first dataset with the second dataset; an output that provides training labels based on a processing of the summed datasets to predict a temporally isolated and discrete event; and a label creation block that receives the output and generates labels for date features in the first dataset. A model pipeline includes a neural network(s) that: receives a first input corresponding to a summation of non learned date embedding with learned feature embedding; and contextualizes the summation by date embedding historical patient data into the summation. The model pipeline includes a prediction block that receives the contextualized summation and predicts one or more outcomes.

公开(公告)号：US11972353B2

公开(公告)日：2024-04-30

申请号：US17154899

申请日：2021-01-21

申请人： Electronic Arts Inc.

发明人： Fabio Zinno ,  George Cheng ,  Hung Yu Ling ,  Michiel van de Panne

IPC分类号： G06V40/20 ,  G06N3/0455 ,  G06N3/088 ,  G06T7/55 ,  G06T7/70 ,  G06T13/40

CPC分类号： G06N3/088 ,  G06N3/0455 ,  G06T7/55 ,  G06T7/70 ,  G06T13/40 ,  G06V40/23 ,  G06T2207/30196

摘要： Some embodiments herein can include methods and systems for predicting next poses of a character within a virtual gaming environment. The pose prediction system can identify a current pose of a character, generate a gaussian distribution representing a sample of likely poses based on the current pose, and apply the gaussian distribution to the decoder. The decoder can be trained to generate a predicted pose based on a gaussian distribution of likely poses. The system can then render the predicted next pose of the character within the three-dimensional virtual gaming environment. Advantageously, the pose prediction system can apply a decoder that does not include or use input motion capture data that was used to train the decoder.

公开(公告)号：US20240135147A1

公开(公告)日：2024-04-25

申请号：US18450839

申请日：2023-08-15

申请人： SAMSUNG ELECTRONICS CO., LTD. ,  Seoul National University R&DB Foundation

发明人： Jung Ho AHN ,  Sun Jung LEE ,  Jae Wan CHOI

IPC分类号： G06N3/0455

CPC分类号： G06N3/0455

摘要： A device including processors configured to execute instructions and memories storing the instructions, which when executed by the processors configure the processors to perform an operation for training a transformer model having a plurality of encoders and a plurality of decoders by configuring the processors to identify the batches of training data into a plurality of micro-batches, select layer pairs for the plurality of micro-batches, assemble a processing order of the layer pairs, determining resource information to be allocated to the layer pairs, and allocate resources to the layer pairs based on the determined resource information to be allocated to the layer pairs, dependent con the processing order of the layer pairs.

公开(公告)号：US11954448B2

公开(公告)日：2024-04-09

申请号：US16935072

申请日：2020-07-21

申请人： Microsoft Technology Licensing, LLC

发明人： Andy Wagner ,  Tiyasa Mitra ,  Marc Tremblay

IPC分类号： G06F40/40 ,  G06N3/0455 ,  G06N5/04 ,  G06N20/00

CPC分类号： G06F40/40 ,  G06N3/0455 ,  G06N5/04 ,  G06N20/00

摘要： Embodiments of the present disclosure include systems and methods for determining position values for training data that is used to train transformer models. In some embodiments, a set of input data for training a transformer model is received. The set of input data comprises a set of tokens. Based on an offset value, a set of successive position values for the set of tokens is determined. Each position value in the set of successive position values represents a position of a token in the set of tokens relative to other tokens in the set of tokens. A set of training data is generated to comprise the set of tokens and the set of successive position values. The transformer model is trained using the set of training data.

公开(公告)号：US20240111999A1

公开(公告)日：2024-04-04

申请号：US18375960

申请日：2023-10-02

申请人： Google LLC

发明人： Itay Laish ,  Amir Reuven Feder ,  Fan Zhang ,  Ayelet Benjamini

IPC分类号： G06N3/0455 ,  G06N3/048

CPC分类号： G06N3/0455 ,  G06N3/048

摘要： A multi-task neural network system is described. The system includes a shared neural network configured to receive as input a text span from a clinical note, and for each of one or more text segments in the text span, processing the text segment to generate a set of text segment embeddings. The system further includes a segmentation neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not. The system further includes a section type classification neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to classify the text segment into a section type of a plurality of section types.

公开(公告)号：US20240104681A1

公开(公告)日：2024-03-28

申请号：US18557361

申请日：2022-05-16

申请人： Cornell University

发明人： Varsha Kishore ,  Kilian Weinberger ,  Xiangyu Chen ,  Boyi Li ,  Yan Wang ,  Ruihan Wu

IPC分类号： G06T1/00 ,  G06N3/0442 ,  G06N3/0455 ,  G06V40/16

CPC分类号： G06T1/005 ,  G06N3/0442 ,  G06N3/0455 ,  G06V40/16

摘要： A method performed by at least one processing device in an illustrative embodiment comprises applying a first image and a message to an encoder of a steganographic encoder-decoder neural network, generating in the encoder, based at least in part on the first image and the message, a perturbed image containing the message, decoding the perturbed image in a decoder of the steganographic encoder-decoder neural network, and providing information characterizing the decoded perturbed image to the encoder. The generating, decoding and providing are iteratively repeated, with different perturbations being determined in the encoder as a function of respective different instances of the provided information, until the decoded perturbed image meets one or more specified criteria relative to the message. The perturbed image corresponding to the decoded perturbed image that meets the one or more specified criteria relative to the message is output as a steganographic image containing the message.

公开(公告)号：US20240104370A1

公开(公告)日：2024-03-28

申请号：US17936338

申请日：2022-09-28

申请人： Microsoft Technology Licensing, LLC

发明人： Chao MA ,  Cheng ZHANG ,  Matthew ASHMAN ,  Marife DEFANTE ,  Karen FASSIO ,  Joel JENNINGS ,  Agrin HILMKIL

IPC分类号： G06N3/08 ,  G06N3/0455

CPC分类号： G06N3/08 ,  G06N3/0455

摘要： A method comprising: sampling a first causal graph from a first graph distribution modelling causation between variables in a feature vector, and sampling a second causal graph from a second graph distribution modelling presence of possible confounders, a confounder being an unobserved cause of both of two variables. The method further comprises: identifying a parent variable which is a cause of a selected variable according to the first causal graph, and which together with the selected variable forms a confounded pair having a respective confounder being a cause of both according to the second causal graph. A machine learning model encodes the parent to give a first embedding, and encodes information on the confounded pair give a second embedding. The embeddings are combined and then decoded to give a reconstructed value. This mechanism may be used in training the model or in treatment effect estimation.

公开(公告)号：US20240104336A1

公开(公告)日：2024-03-28

申请号：US18471257

申请日：2023-09-20

申请人： DeepMind Technologies Limited

发明人： Geoffrey Irving ,  Amelia Marita Claudia Glaese ,  Nathaniel John McAleese-Park ,  Lisa Anne Marie Hendricks

IPC分类号： G06N3/006 ,  G06F40/284 ,  G06F40/35 ,  G06N3/0455 ,  G06N3/092

CPC分类号： G06N3/006 ,  G06F40/284 ,  G06F40/35 ,  G06N3/0455 ,  G06N3/092

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling a user to conduct a dialogue. Implementations of the system learn when to rely on supporting evidence, obtained from an external search system via a search system interface, and are also able to generate replies for the user that align with the preferences of a previously trained response selection neural network. Implementations of the system can also use a previously trained rule violation detection neural network to generate replies that take account of previously learnt rules.

公开(公告)号：US11941813B2

公开(公告)日：2024-03-26

申请号：US16996068

申请日：2020-08-18

申请人： NantCell, Inc.

发明人： Bing Song ,  Nicholas James Witchey ,  Albert Wu ,  Krsto Sbutega ,  Patrick Soon-Shiong

IPC分类号： G06N3/0455 ,  G06F18/21 ,  G06F18/211 ,  G06F18/241 ,  G06N3/084 ,  G06N5/046 ,  G06T7/10 ,  G06T7/11 ,  G06T7/73 ,  G06V20/69

CPC分类号： G06T7/11 ,  G06F18/211 ,  G06F18/2163 ,  G06F18/241 ,  G06N3/0455 ,  G06N3/084 ,  G06N5/046 ,  G06T7/10 ,  G06T7/74 ,  G06V20/695 ,  G06V20/698 ,  G06T2207/20081 ,  G06T2210/22

摘要： An example system for performing segmentation of data based on tensor inputs includes memory storing computer-executable instructions defining a learning network, where the learning network includes a plurality of sequential encoder down-sampling blocks. A processor is configured to execute the computer-executable instructions to receive a multi-dimensional input tensor including at least a first dimension, a second dimension and a plurality of channels. The processor is also configured to process the received multi-dimensional input tensor by passing the received multi-dimensional input tensor through the plurality of sequential encoder down-sampling blocks of the learning network, and to generate an output tensor in response to processing the received multi-dimensional input tensor. The output tensor includes at least one segmentation classification.

公开(公告)号：US20240095499A1

公开(公告)日：2024-03-21

申请号：US18247562

申请日：2021-10-04

申请人： Telefonaktiebolaget LM Ericsson (publ)

发明人： Woonghee LEE ,  Ursula CHALLITA ,  Jingya LI

IPC分类号： G06N3/0455 ,  G06N3/048

CPC分类号： G06N3/0455 ,  G06N3/048

摘要： Methods and apparatuses for noise learning-based denoising of noisy input data Y that is equal to the original data X plus the noise N (i.e., Y=X+N). In contrast with a conventional denoising autoencoder (DAE) method that attempts to learn the original data X directly from noisy input data Y, the noise learning-based denoising learns the noise N in the noisy input data Y and then regenerates the original data X by subtracting the learned noise N from the noisy input data Y. Learning the noise N may include inputting the noisy input data Y into an encoder of a neural network, and the learned noise N may be output from a decoder of the neural network. Training the neural network may include inputting noisy training data into an encoder of the neural network and outputting training noise from a decoder of the neural network.