Jacob Subag
27Patents
4h-index
27Co-inventors
59Inventor score
Filing activity: Oct 8, 2012 → May 30, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US10372416B2 | Multiply-accumulate “0” data gating | Physics | 13 | Active |
| US11037330B2 | Low rank matrix compression | Electricity | 5 | Active |
| US11087206B2 | Smart memory handling and data management for machine learning networks | Physics | 4 | Active |
| US10467795B2 | Sub-graph in frequency domain and dynamic selection of convolution implementation on a GPU | Physics | 4 | Active |
| US10922556B2 | Storage system of DNN outputs for black box | Physics | 3 | Active |
| US10853035B2 | Multiply-accumulate “0” data gating | Physics | 2 | Active |
| US11238338B2 | Real time context dependent deep learning | Emerging Cross-Sectional Technologies | 2 | Active |
| US11704564B2 | Real time context dependent deep learning | Emerging Cross-Sectional Technologies | 1 | Active |
| US11093822B2 | Variable precision and mix type representation of multiple layers in a network | Physics | 1 | Active |
| US10606559B2 | Multiply-accumulate “0” data gating | Physics | 1 | Active |
| US9536342B2 | Automatic partitioning techniques for multi-phase pixel shading | Physics | 0 | Active |
| US11250610B2 | Sub-graph in frequency domain and dynamic selection of convolution implementation on a GPU | Physics | 0 | Active |
| US12131507B2 | Low rank matrix compression | Electricity | 0 | Active |
| US12033063B2 | Scheduling configuration for deep learning networks | Physics | 0 | Active |
| US11599777B2 | Scheduling configuration for deep learning networks | Physics | 0 | Active |
| US10559112B2 | Hybrid mechanism for efficient rendering of graphics images in computing environments | Electricity | 0 | Active |
| US9218679B2 | Reduced bitcount polygon rasterization | Physics | 0 | Active |
| US10762685B2 | Sub-graph in frequency domain and dynamic selection of convolution implementation on a GPU | Physics | 0 | Active |
| US11600035B2 | Sub-graph in frequency domain and dynamic selection of convolution implementation on a GPU | Physics | 0 | Active |
| US11886984B2 | Variable precision and mix type representation of multiple layers in a network | Physics | 0 | Active |
| US11669719B2 | Storage system of DNN outputs for black box | Physics | 0 | Active |
| US11620766B2 | Low rank matrix compression | Electricity | 0 | Active |
| US11100393B2 | Real time context dependent deep learning | General | 0 | Revoked |
| US12223427B2 | Real time context dependent deep learning | Emerging Cross-Sectional Technologies | 0 | Active |
| US11132601B2 | Real time context dependent deep learning | General | 0 | Revoked |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.