Noise as a Resource for Computation and Learning in Networks of Spiking Neurons

211 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System (2022, background): “Using a stochastic rather than a deterministic approach is more biologically plausible (Maass, 2014) which reduces the overlap in the snapshots of the working model and leads to more diversity in semantic memories.”
In-memory computing with resistive switching devices (2018, methodology): “Random number generation is also an enabling tool in probabilistic spiking neural networks, where noise is used as a resource to mimic the stochastic release of synaptic neurotransmitters, or the stochastic opening and closing of membrane channels 78 .”
Memory and Information Processing in Neuromorphic Systems (2015, background): “computing architectures [6], and given the clear ability of biological nervous systems to perform robust computation, using memory and computing elements that are slow, inhomogeneous, stochastic and faulty [7], [8], neuromorphic brain-inspired computing paradigms offer an”
Noise as a Resource for Learning in Knowledge Distillation (2020, background): “Recently, though, there has been a shift in neuro-science and a number of studies argue for the beneﬁcial role of noise [13, 35, 37].”