.png){kind=icon}
Return
Filtering inputs for efficient intelligence systems
.png){kind=icon}
PRE
AI
DOI：10.1038/s41928-026-01698-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
By deciding which visual inputs are task-relevant before computation starts, reconfigurable hardware can reduce unnecessary activations in artificial intelligence systems.
Journal
IF:
40.9
Papers:
1.7K
Citations:
2.1W
Organization
Cited Papers
ShareSaveA towards-foundry strategy for creating fully interconnected two-dimensional microprocessors.png)
Nature Electronics
Nature ElectronicsIF40.9
PREAI
ShareSaveFerroelectric gating of two-dimensional semiconductors for the integration of steep-slope logic and neuromorphic devicesNATURE ELECTRONICS
OAAI
NATURE ELECTRONICSIF40.9
OAAIShareSaveReconfigurable logic and neuromorphic circuits based on electrically tunable two-dimensional homojunctionsNATURE ELECTRONICS
NATURE ELECTRONICSIF40.9
PREAI
ShareSaveA spiking neural network-in-logic architecture based on reconfigurable molybdenum disulfide dual-gate transistors with ferroelectric gatingNature Electronics
OAAI
Nature ElectronicsIF40.9
OAAIShareSaveReconfigurable logic-in-memory architectures based on a two-dimensional van der Waals heterostructure deviceNATURE ELECTRONICS
NATURE ELECTRONICSIF40.9
PREAI
ShareSaveShareSave no more
no more