Brendan Frey
22Patents
8h-index
18Co-inventors
72Inventor score
Filing activity: Mar 20, 2001 → Jan 29, 2021
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US6985858B2 | Method and apparatus for removing noise from feature vectors | Physics | 169 | Expired |
| US8478535B2 | Systems and methods that utilize machine learning algorithms to facilitate assembly of aids vaccine cocktails | Physics | 41 | Active |
| US7113185B2 | System and method for automatically learning flexible sprites in video layers | Physics | 22 | Expired |
| US7940264B2 | Generative models for constructing panoramas from an image sequence | Physics | 20 | Active |
| US7750904B2 | Modeling variable illumination in an image sequence | Physics | 18 | Active |
| US8335683B2 | System for using statistical classifiers for spoken language understanding | Physics | 18 | Active |
| US10185803B2 | Systems and methods for classifying, prioritizing and interpreting genetic variants and therapies using a deep neural network | Physics | 11 | Active |
| US7451083B2 | Removing noise from feature vectors | Physics | 9 | Expired |
| US7680353B2 | Stabilization of objects within a video sequence | Physics | 8 | Active |
| US10303979B2 | System and method for classifying and segmenting microscopy images with deep multiple instance learning | Physics | 8 | Active |
| US7310599B2 | Removing noise from feature vectors | Physics | 8 | Expired |
| US10410118B2 | System and method for training neural networks | Physics | 8 | Active |
| US11322225B2 | Systems and methods for determining effects of therapies and genetic variation on polyadenylation site selection | Chemistry; Metallurgy | 2 | Active |
| US11183271B2 | Neural network architectures for linking biological sequence variants based on molecular phenotype, and systems and methods therefor | Physics | 2 | Active |
| US10885435B2 | System and method for training neural networks | Physics | 2 | Active |
| US7702489B2 | Method and apparatus for fast machine learning using probability maps and fourier transforms | Physics | 1 | Active |
| US11568960B2 | Neural network architectures for scoring and visualizing biological sequence variations using molecular phenotype, and systems and methods therefor | Physics | 1 | Active |
| US11636920B2 | Systems and methods for generating and training convolutional neural networks using biological sequences and relevance scores derived from structural, biochemical, population and evolutionary data | Physics | 1 | Active |
| US11887696B2 | Systems and methods for classifying, prioritizing and interpreting genetic variants and therapies using a deep neural network | Physics | 1 | Active |
| US7750903B2 | Modeling reflections within an image sequence | Physics | 1 | Active |
| US11769073B2 | Methods and systems for producing an expanded training set for machine learning using biological sequences | Physics | 0 | Active |
| US11681917B2 | System and method for training neural networks | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.