.png){kind=icon}
.png){kind=icon}
Return
Deep unsupervised learning using spike-timing-dependent plasticity
.png){kind=icon}
OA
AI
DOI：10.1088/2634-4386/ad3a95.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spike-timing-dependent plasticity (STDP) is an unsupervised learning mechanism for spiking neural networks that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve 24.56% higher accuracy and 3.5 x faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a k-means clustering approach.
Keywords:
unsupervised learning
spiking neural networks
spike-timing-dependent plasticity
Journal
IF:
6.1
Papers:
340
Citations:
920