Charles Blundell
18Patents
3h-index
33Co-inventors
56Inventor score
Filing activity: Sep 3, 2008 → Jun 16, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US11423300B1 | Selecting actions by reverting to previous learned action selection policies | Physics | 3 | Active |
| US10438114B1 | Recommending content using neural networks | Physics | 3 | Active |
| US10824946B2 | Training neural networks using posterior sharpening | Physics | 3 | Active |
| US10748065B2 | Multi-task neural networks with task-specific paths | Physics | 1 | Active |
| US11720796B2 | Neural episodic control | Physics | 1 | Active |
| US11836630B2 | Training neural networks using posterior sharpening | Physics | 0 | Active |
| US12242947B2 | Machine learning systems with memory based parameter adaptation for learning fast and slower | Physics | 0 | Active |
| US11977983B2 | Noisy neural network layers with noise parameters | Physics | 0 | Active |
| US10482997B2 | Method for determining three-dimensional structures of dynamic molecules | Physics | 0 | Active |
| US11714990B2 | Jointly learning exploratory and non-exploratory action selection policies | Physics | 0 | Active |
| US12417373B2 | Persistent message passing for graph neural networks | Physics | 0 | Active |
| US10839293B2 | Noisy neural network layers with noise parameters | Physics | 0 | Active |
| US11714993B2 | Classifying input examples using a comparison set | Physics | 0 | Active |
| US12073304B2 | Classifying input examples using a comparison set | Physics | 0 | Active |
| US10997472B2 | Classifying input examples using a comparison set | Physics | 0 | Active |
| US10664753B2 | Neural episodic control | Physics | 0 | Active |
| US11790238B2 | Multi-task neural networks with task-specific paths | Physics | 0 | Active |
| US11562209B1 | Recommending content using neural networks | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.