-
公开(公告)号:EP4443337A1
公开(公告)日:2024-10-09
申请号:EP23819966.5
申请日:2023-03-31
发明人: ARENDT, Krzysztof , STEFANSKI, Grzegorz , MASZTALSKI, Piotr , SZUMACZUK, Artur , TKACZUK, Jakub , MATUSZEWSKI, Mateusz , SWIATEK, Michal , OLENIECKI, Tymoteusz
CPC分类号: G10L15/16 , G10L25/30 , G06N3/084 , G06N3/0455 , G06N3/0475 , G06N3/047 , G06N3/094 , G06N3/0464 , G06N3/044
摘要: An electronic apparatus is provided. The electronic apparatus includes a memory and a processor, wherein the processor is configured to, by executing the at least one instruction, acquire a plurality of training data; acquire a plurality of embedding vectors that are mappable to an embedding space for the plurality of training data, respectively; train an artificial intelligence model classifying the plurality of training data based on the plurality of embedding vectors, identify an embedding vector misclassified by the artificial intelligence model among the plurality of embedding vectors, identify an embedding vector closest to the misclassified embedding vector in the embedding space, acquire a synthetic embedding vector corresponding to a path connecting the misclassified embedding vector to the embedding vector closest to the misclassified embedding vector in the embedding space, and re-train the artificial intelligence model by adding the synthetic embedding vector to the training data.
-
2.
公开(公告)号:EP4432167A1
公开(公告)日:2024-09-18
申请号:EP24163661.2
申请日:2024-03-14
发明人: CHENG, Qisen , BALAKRISHNAN, Kaushik , QU, Shuhui , LEE, Janghwan
摘要: A method may include providing a data set including rows of data. The rows of data may include at least one row of unpaired modality including a first modality, and at least one row of paired modality may include both the first modality and a second modality. The method may further include imputing, by a modality-specific encoder, the at least one row of unpaired modality by interpolating embeddings from the second modality of the paired modality; training, in a latent space, the modality-specific encoder based on the imputation for unimodal prediction and bimodal prediction; and generating a confidence value for the unimodal prediction and the bimodal prediction.
-
3.
-
公开(公告)号:EP4425384A1
公开(公告)日:2024-09-04
申请号:EP23159239.5
申请日:2023-02-28
申请人: FUJITSU LIMITED
发明人: MAKARIOU, Savvas
IPC分类号: G06N3/082 , G06N3/045 , G06N3/047 , G06N3/0475 , G06N3/088
摘要: A computer-implemented method comprising: training a first deep belief network, DBN, using training data; adding at least one neuron to the first DBN to generate a second DBN; assigning weights to neurons in the second DBN according to weights of neurons in the trained first DBN; and training the second DBN using the training data.
-
-
公开(公告)号:EP4416643A1
公开(公告)日:2024-08-21
申请号:EP22793822.2
申请日:2022-10-17
申请人: Oxa Autonomy Ltd
发明人: KUUTTII, Sampo , PORAV, Horia , UPCROFT, Ben , NEWMAN, Paul
CPC分类号: G06N20/00 , G06N3/0464 , G06N3/0475 , G06N3/092 , G06N3/047
-
公开(公告)号:EP4416642A1
公开(公告)日:2024-08-21
申请号:EP22793821.4
申请日:2022-10-17
申请人: Oxa Autonomy Ltd
发明人: KUUTTI, Sampo , Porav, Horia , UPCROFT, Ben , NEWMAN, Paul
CPC分类号: G06N20/00 , G06N3/0464 , G06N3/0475 , G06N3/092 , G06N3/047
-
公开(公告)号:EP3704634B1
公开(公告)日:2024-08-21
申请号:EP18884959.0
申请日:2018-06-06
IPC分类号: G06N3/063 , G06T1/60 , G06F18/2413 , G06N3/045 , G06T1/20 , G06N3/08 , G06V10/82 , G06F18/214
CPC分类号: G06T1/20 , G06T2207/2002120130101 , G06T2207/3000420130101 , G06T1/60 , G06N3/08 , G06N3/063 , G06V10/82 , G06N3/047 , G06N3/044 , G06N3/045 , G06F18/24133 , G06F18/214
-
公开(公告)号:EP4413584A1
公开(公告)日:2024-08-14
申请号:EP22802812.2
申请日:2022-10-17
申请人: X Development LLC
发明人: GADHIYA, Tusharkumar , SHAH, Falak , VYAS, Nisarg , YANG, Julia , GHARAKHANYAN, Vahe , HOLIDAY, Alexander
IPC分类号: G16C20/50
-
公开(公告)号:EP4409466A1
公开(公告)日:2024-08-07
申请号:EP22715880.5
申请日:2022-03-22
发明人: PRAMOD, Siddharth , BALD, Samuel
CPC分类号: G06N3/088 , G06N3/084 , G06N20/00 , H04L63/14 , G06N7/01 , G06F21/50 , G06F2221/213320130101 , G06N3/0442 , G06N3/09 , G06N3/0455 , G06N3/0475 , G06N3/047
-
-
-
-
-
-
-
-
-