Yasushi Negishi
23Patents
3h-index
24Co-inventors
63Inventor score
Filing activity: Nov 22, 1994 → Oct 30, 2020
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US6571278B1 | Computer data sharing system and method for maintaining replica consistency | Emerging Cross-Sectional Technologies | 44 | Expired |
| US5436892A | Apparatus and method for packet communications | Electricity | 9 | Expired |
| US10268951B2 | Real-time resource usage reduction in artificial neural networks | Physics | 4 | Active |
| US10949746B2 | Efficient parallel training of a network model on multiple graphics processing units | Physics | 3 | Active |
| US10558914B2 | Real-time resource usage reduction in artificial neural networks | Physics | 2 | Active |
| US9066289B2 | Packet communication system, communication method and program | Emerging Cross-Sectional Technologies | 2 | Active |
| US7350017B2 | Magnetic disk unit, file management system, and file management method | Physics | 2 | Expired |
| US8898648B2 | Methodology for fast detection of false sharing in threaded scientific codes | Physics | 2 | Active |
| US10782897B2 | Memory reduction for neural networks with fixed structures | Physics | 2 | Active |
| US11164079B2 | Multi-GPU deep learning using CPUs | Physics | 2 | Active |
| US11362670B2 | ReLU compression to reduce GPU memory | Electricity | 1 | Active |
| US9785422B1 | Applying multiple rewriting without collision for semi-automatic program rewriting system | Physics | 1 | Active |
| US8442028B2 | Packet communication system, communication method and program | Emerging Cross-Sectional Technologies | 1 | Active |
| US10453167B1 | Estimating performance of GPU application for different GPU-link performance ratio | Physics | 1 | Active |
| US11461637B2 | Real-time resource usage reduction in artificial neural networks | Physics | 1 | Active |
| US10984014B2 | Integrating multiple distributed data processing servers with different data partitioning and routing mechanisms, resource sharing policies and lifecycles into a single process | Electricity | 0 | Active |
| US11880762B2 | Choosing execution mode of a neural network based on total memory usage | Physics | 0 | Active |
| US11176096B2 | File system for genomic data | Physics | 0 | Active |
| US10613911B2 | Integrating multiple distributed data processing servers with different data partitioning and routing mechanisms, resource sharing policies and lifecycles into a single process | Electricity | 0 | Active |
| US10884755B1 | Graph rewriting for large model support using categorized topological sort | Physics | 0 | Active |
| US9251118B2 | Scheduling computation processes including all-to-all communications (A2A) for pipelined parallel processing among plurality of processor nodes constituting network of n-dimensional space | Electricity | 0 | Active |
| US10162934B2 | Data de-duplication system using genome formats conversion | Physics | 0 | Active |
| US10169874B2 | Surface-based object identification | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.