.png){kind=icon}
.png){kind=icon}
Return
Efficient training of neuromorphic electronics
.png){kind=icon}
PRE
AI
J
T
B
G
X
M
B
DOI：10.1038/s41928-026-01631-2.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neuromorphic electronics can provide in-memory computing systems with low power consumption by emulating key principles of the brain. However, their practical capabilities are limited by a number of challenges, including device non-ideality, limited training accuracy and insufficient adaptability. Here we explore the development of training approaches for neuromorphic electronics, including digital, mixed-signal and emerging neuromorphic electronics. We examine the characteristics and advantages of different training strategies, including off-chip training with on-chip inference, on-chip training and inference, and hybrid offline–online training strategies. We consider the challenges that must be addressed in terms of advanced training, standardized benchmarks and hardware–software co-design, and highlight applications where such efficient training of neuromorphic electronics could be of particular value. This Review examines the development of training strategies for neuromorphic electronics—including digital, mixed-signal and emerging neuromorphic electronics—analysing the characteristics and advantages of offline, online and hybrid training methods, and identifying key challenges and opportunities for future advances.
Journal
IF:
40.9
Papers:
1.7K
Citations:
2.1W
Organization
Cited Papers