-
公开(公告)号：US12119091B1
公开(公告)日：2024-10-15
申请号：US18545438
申请日：2023-12-19
发明人： Oren Zeev Kraus , Kian Runnels Kenyon-Dean , Mohammadsadegh Saberian , Maryam Fallah , Peter Foster McLean , Jessica Wai Yin Leung , Vasudev Sharma , Ayla Yasmin Khan , Jaichitra Balakrishnan , Safiye Celik , Dominique Beaini , Maciej Sypetkowski , Chi Cheng , Kristen Rose Morse , Maureen Katherine Makes , Benjamin John Mabey , Berton Allen Earnshaw
CPC分类号： G16B45/00 , G06V10/751 , G06V10/82 , G06V20/698 , G16B20/00 , G16B40/00
摘要： The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing generative machine learning models to generate embeddings from phenomic images (or other microscopy representations). For example, the disclosed systems can train a generative machine learning model (e.g., a masked autoencoder generative model) to generate predicted (or reconstructed) phenomic images from masked version of ground truth training phenomic images. In some cases, the disclosed systems utilize a momentum-tracking optimizer while reducing a loss of the generative machine learning model to enable efficient training on large scale training image batches. Furthermore, the disclosed systems can utilize Fourier transformation losses with multi-stage weighting to improve the accuracy of the generative machine learning model on the phenomic images during training. Indeed, the disclosed systems can utilize the trained generative machine learning model to generate phenomic embeddings from input phenomic images (for various phenomic comparisons).
-
公开(公告)号：US12119090B1
公开(公告)日：2024-10-15
申请号：US18545399
申请日：2023-12-19
发明人： Oren Zeev Kraus , Kian Runnels Kenyon-Dean , Mohammadsadegh Saberian , Maryam Fallah , Peter Foster McLean , Jessica Wai Yin Leung , Vasudev Sharma , Ayla Yasmin Khan , Jaichitra Balakrishnan , Safiye Celik , Dominique Beaini , Maciej Sypetkowski , Chi Cheng , Kristen Rose Morse , Maureen Katherine Makes , Benjamin John Mabey , Berton Allen Earnshaw
CPC分类号： G16B45/00 , G06T5/73 , G16B20/00 , G16B40/00 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084
摘要： The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing generative machine learning models to generate embeddings from phenomic images (or other microscopy representations). For example, the disclosed systems can train a generative machine learning model (e.g., a masked autoencoder generative model) to generate predicted (or reconstructed) phenomic images from masked version of ground truth training phenomic images. In some cases, the disclosed systems utilize a momentum-tracking optimizer while reducing a loss of the generative machine learning model to enable efficient training on large scale training image batches. Furthermore, the disclosed systems can utilize Fourier transformation losses with multi-stage weighting to improve the accuracy of the generative machine learning model on the phenomic images during training. Indeed, the disclosed systems can utilize the trained generative machine learning model to generate phenomic embeddings from input phenomic images (for various phenomic comparisons).
-
搜索结果
2 条记录 (耗时 0.014 秒)
