-
公开(公告)号:US20240386202A1
公开(公告)日:2024-11-21
申请号:US18653146
申请日:2024-05-02
Applicant: Google LLC
Inventor: Matthew Douglas Hoffman , Charles Aloysius Sutton , David Martin Dohan , Sholto Francis Alexandre Douglas , Tuan Anh Le , Van Du Phan , Aaron Thomas Parisi , Ryan Michael Rifkin , Pavel Sountsov , Sharad Vikram
IPC: G06F40/284
Abstract: Systems and methods for generative language model tuning can include training the generative language model to generate sets of output text tokens with set of intermediary text tokens with training examples that include input and output pairs. The training can include processing the input with the language model to determine a predicted output and a predicted set of intermediary text tokens. The predicted set of intermediary text tokens can then be evaluated based at least in part on the output associated with the input and the predicted output.
-
公开(公告)号:US20200372295A1
公开(公告)日:2020-11-26
申请号:US16880456
申请日:2020-05-21
Applicant: Google LLC
Inventor: Aren Jansen , Ryan Michael Rifkin , Daniel Ellis
Abstract: A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.
-
公开(公告)号:US20190012719A1
公开(公告)日:2019-01-10
申请号:US16129508
申请日:2018-09-12
Applicant: GOOGLE LLC
Inventor: John Roberts Anderson , Ryan Michael Rifkin , Jay Yagnik , Rasmus Larsen , Sarvjeet Singh , Yi-fan Chen , Anandsudhakar Kesari
Abstract: Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.
-
公开(公告)号:US11475236B2
公开(公告)日:2022-10-18
申请号:US16880456
申请日:2020-05-21
Applicant: Google LLC
Inventor: Aren Jansen , Ryan Michael Rifkin , Daniel Ellis
Abstract: A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.
-
公开(公告)号:US10320860B1
公开(公告)日:2019-06-11
申请号:US14749445
申请日:2015-06-24
Applicant: Google LLC
Inventor: Andrew Ames Bunner , Alan Lee Gardner, III , Mohammed Waleed Kadous , Brian Patrick Williams , Marc Stogaitis , Nadav Aharony , Brian Duff , Pascal Tom Getreuer , Zhentao Sun , Daniel Estrada Alva , Ami Patel , Benjamin Razon , Richard Daniel Webb , Tony Weber , Thomas Yuchin Chao , Ryan Michael Rifkin , Richard Francis Lyon , Liem Tran , Joseph A. Farfel
Abstract: The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: transmit a wakeup signal to a plurality of devices based on coarse grain location information; send a request to a first device of the plurality of devices to transmit a token using a first communication technology to determine fine grain copresence; receive a first token acknowledgment from a first subset of the plurality of devices; send a request to a second device of the first subset of the plurality of devices to transmit the token using a second communication technology to determine fine grain copresence; receive a second token acknowledgment from a second subset of the plurality of devices; and refine copresence based on receiving the first and second token acknowledgment.
-
-
-
-