Event-driven Computation
Event-Driven Computation is a computational paradigm in spiking neural networks wherein processing occurs asynchronously and selectively in response to discrete synaptic events or spikes, differing from clock-driven approaches by eliminating fixed-timestep updates and enabling computations only when input or internal state changes trigger an event.
153
Publications
11.5K
Citations
571
Authors
170
Institutions
Publications per year
2017–2026
98
Parents
153
Steve Furber, Francesco Galluppi, Steve Temple et al. · Proceedings of the IEEE · 2014 · 1.3K citations · Full text
Real-time classification and sensor fusion with a spiking deep belief network
Peter O’Connor, Daniel Neil, Shih‐Chii Liu et al. · Frontiers in Neuroscience · 2013 · 411 citations · Full text
1–5 of 153
571
9
h-index
8
h-index
7
h-index
6
h-index
6
h-index
1–5 of 571
170
University of Zurich
Zurich, Switzerland
14 h-index
45 publications
11.7K citations
ETH Zurich
Zurich, Switzerland
13 h-index
45 publications
11.8K citations

SIB Swiss Institute of Bioinformatics
Lausanne, Switzerland
12 h-index
33 publications
11.5K citations

University of Manchester
Manchester, United Kingdom
9 h-index
44 publications
7.5K citations
National University of Singapore
Singapore, Singapore
7 h-index
14 publications
465 citations
Tsinghua University
Beijing, China
6 h-index
12 publications
452 citations
Zhejiang University of Science and Technology
Hangzhou, China
6 h-index
15 publications
722 citations
University of California, Santa Barbara
Santa Barbara, United States
6 h-index
13 publications
550 citations
1–8 of 170
16 publications · 3.1K citations
16
h-index
Repository · 8 publications · 358 citations
8
h-index
7 publications · 725 citations
7
h-index
3 publications · 433 citations
3
h-index
2 publications · 191 citations
2
h-index
1–5