Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting

By Filip Ponulak, Andrzej J. Kasinski. Neural Computation, 2010

559 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/779b7bb1a872862fe5cbb6778f0a09fafd1d40fe

How researchers see this paper

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

In Cellular and Molecular Neuroscience

1. Filip Ponulak
2. Andrzej J. Kasinski
3. Timothée Masquelier
4. Prasad Joshi
5. Andreas Wild
6. Zhaofei Yu
7. Narayan Srinivasa
8. Wei Fang

In Cognitive Neuroscience

1. Yonghong Tian
2. Filip Ponulak
3. Andrzej J. Kasinski
4. Timothée Masquelier
5. Zhaofei Yu
6. Narayan Srinivasa
7. Wei Fang
8. Yanqing Chen

In Electrical and Electronic Engineering

1. Yonghong Tian
2. Filip Ponulak
3. Andrzej J. Kasinski
4. Timothée Masquelier
5. Prasad Joshi
6. Andreas Wild
7. Zhaofei Yu
8. Narayan Srinivasa

Citations in the corpus

• SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks (2017, unknown): “In contrast to that, ReSuMe (Ponulak and Kasi´nski, 2009) and SPAN (Mohemmed et al., 2012) are deterministic approaches which can be seen as generalizations of the Widrow-Hoff rule to spiking neurons.”
• Introduction to spiking neural networks: Information processing, learning and applications. (2011, methodology): “…several tasks that require classification of temporal signals, including classification of spike patterns (Maass et al. 2002a, Nikolic et al. 2009, Ponulak and Kasinski 2010), speech recognition (Hopfield and Brody 2000, 2001, Verstraeten et al. 2005, Gütig and Sompolinsky 2009) or epilepsy…”
• Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks (2020, methodology): “Supervised learning of SNNs SpikeProp [5] was the first supervised learning method for SNNs based on backpropagation, which used a linear approximation to overcome the non-differentiable threshold-triggered firing mechanism of SNNs. Subsequent works included Tempotron [18], ReSuMe [45], and SPAN [40”
• Loihi: A Neuromorphic Manycore Processor with On-Chip Learning (2018, methodology): “We have developed and validated the following networks in pre-silicon FPGA emulation with all learning taking place on chip: • A single-layer classifier using a supervised variant of STDP, similar to F. Ponulak and A. Kasinski, 4 as the learning method .”
• NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data (2014, unknown): “In principle, SPAN is a further development of an existing class of algorithms, including: ReSuMe (Ponulak & Kasinski, 2010); Chronotron (Florian, 2010); Tempotron (Gutig & Sompolinsky, 2006).”