Meta-learning Spiking Neural Networks with Surrogate Gradient Descent. (arXiv:2201.10777v1 [cs.NE])

Web: http://arxiv.org/abs/2201.10777

Adaptive "life-long" learning at the edge and during online task performance
is an aspirational goal of AI research. Neuromorphic hardware implementing
Spiking Neural Networks (SNNs) are particularly attractive in this regard, as
their real-time, event-based, local computing paradigm makes them suitable for
edge implementations and fast learning. However, the long and iterative
learning that characterizes state-of-the-art SNN training is incompatible with
the physical nature and real-time operation of neuromorphic hardware. Bi-level
learning, such as meta-learning is increasingly used in deep …

arxiv gradient learning meta meta-learning networks neural neural networks