Title | ||
---|---|---|
Comparing SNNs and RNNs on neuromorphic vision datasets: Similarities and differences |
Abstract | ||
---|---|---|
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion. Spiking neural networks (SNNs) represent a family of event-driven models with spatiotemporal dynamics for neuromorphic computing, which are widely benchmarked on neuromorphic data. Interestingly, researchers in the machine learning community can argue that recurrent (artificial) neural networks (RNNs) also have the capability to extract spatiotemporal features although they are not event-driven. Thus, the question of “what will happen if we benchmark these two kinds of models together on neuromorphic data” comes out but remains unclear. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neunet.2020.08.001 | Neural Networks |
Keywords | DocType | Volume |
Spiking neural networks,Recurrent neural networks,Long short-term memory,Neuromorphic dataset,Spatiotemporal dynamics | Journal | 132 |
Issue | ISSN | Citations |
1 | 0893-6080 | 2 |
PageRank | References | Authors |
0.38 | 27 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weihua He | 1 | 2 | 1.06 |
Yujie Wu | 2 | 22 | 2.02 |
Lei Deng | 3 | 177 | 30.01 |
Guoqi Li | 4 | 40 | 6.92 |
Haoyu Wang | 5 | 2 | 0.38 |
Yang Tian | 6 | 2 | 0.38 |
Wei Ding | 7 | 2 | 0.72 |
Wenhui Wang | 8 | 92 | 19.23 |
Yuan Xie | 9 | 6430 | 407.00 |