Inventor · San Mateo, CA, US

Kai-How Farh

24Patents
5h-index
23Co-inventors
61Inventor score

Filing activity: Aug 22, 2016 → Sep 29, 2023

Most-cited inventions

PatentTitleAreaCited byStatus
US10423861B2 Deep learning-based techniques for training deep convolutional neural networks Emerging Cross-Sectional Technologies 39 Active
USD875773S1 Display screen or portion thereof with graphical user interface General 31 Active
US10540591B2 Deep learning-based techniques for pre-training deep convolutional neural networks Physics 26 Active
USD869489S1 Display screen or portion thereof with graphical user interface General 16 Active
USD829738S1 Display screen or portion thereof with graphical user interface General 16 Active
US11315016B2 Deep convolutional neural networks for variant classification Emerging Cross-Sectional Technologies 3 Active
US10558915B2 Deep learning-based techniques for training deep convolutional neural networks Emerging Cross-Sectional Technologies 3 Active
US10509795B2 Semantic distance systems and methods for determining related ontological data Physics 2 Active
US11488009B2 Deep learning-based splice site classification Physics 2 Active
US11538555B1 Protein structure-based protein language models Physics 1 Active
US11397889B2 Aberrant splicing detection using convolutional neural networks (CNNs) Physics 1 Active
US10607156B2 Federated systems and methods for medical data sharing Electricity 1 Active
US11515010B2 Deep convolutional neural networks to predict variant pathogenicity using three-dimensional (3D) protein structures Physics 0 Active
US11875237B2 Federated systems and methods for medical data sharing Electricity 0 Active
US11705219B2 Deep learning-based variant classifier Physics 0 Active
US11798650B2 Semi-supervised learning for training an ensemble of deep convolutional neural networks Emerging Cross-Sectional Technologies 0 Active
US12073922B2 Deep learning-based framework for identifying sequence patterns that cause sequence-specific errors (SSEs) Physics 0 Active
US11244246B2 Federated systems and methods for medical data sharing Electricity 0 Active
US11837324B2 Deep learning-based aberrant splicing detection Physics 0 Active
US11861491B2 Deep learning-based pathogenicity classifier for promoter single nucleotide variants (pSNVs) Physics 0 Active
US11386324B2 Recurrent neural network-based variant pathogenicity classifier Emerging Cross-Sectional Technologies 0 Active
US12217832B2 Deep learning-based variant classifier Physics 0 Active
US12165742B2 Splicing site classification using neural networks Physics 0 Active
US12217829B2 Artificial intelligence-based analysis of protein three-dimensional (3D) structures Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.