On the applicability of STDP-based learning mechanisms to spiking neuron network models
Source abstract
Abstract
The ways to creating practically effective method for spiking neuron networks learning, that would be appropriate for implementing in neuromorphic hardware and at the same time based on the biologically plausible plasticity rules, namely, on STDP, are discussed. The influence of the amount of correlation between input and output spike trains on the learnability by different STDP rules is evaluated. A usability of alternative combined learning schemes, involving artificial and spiking neuron models is demonstrated on the iris benchmark task and on the practical task of gender recognition.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Neuroscience and Neural Engineering · Neural dynamics and brain function
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Nuclear University and Plekhanov Russian University of Economics 1 National Research Centre Kurchatov Institute, MEPhI National Research , Moscow, Russia
MEPhI National Research Nuclear University 2 , Moscow, Russia
National Research Centre Kurchatov Institute 3 , Moscow, Russia and Moscow Institute of Physics and Technology, Moscow, Russia
National Research Centre Kurchatov Institute 4 , Moscow, Russia
Funding
Russian Science Foundation
References (16)
Show source-provided references
1. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing
2. 2013
3. Supervised spike-timing-dependent plasticity: A spatiotemporal neuronal learning rule for function approximation and decisions10.1162/NECO_a_00520 ↗
4. Nest (neural simulation tool)10.4249/scholarpedia.1430 ↗
5. Learning input correlations through nonlinear temporally asymmetric hebbian plasticity10.1523/JNEUROSCI.23-09-03697.2003 ↗
6. The tempotron: A neuron that learns spike timing-based decisions10.1038/nn1643 ↗
7. A quantitative description of membrane current and its application to conduction and excitation in nerve10.1113/jphysiol.1952.sp004764 ↗
8. Simple model of spiking neurons10.1109/TNN.2003.820440 ↗
9. What can a neuron learn with spike-timing-dependent plasticity10.1162/0899766054796888 ↗
10. Real-time classification of complex patterns using spike-based learning in neuromorphic vlsi10.1109/TBCAS.2008.2005781 ↗
11. Phenomenological models of synaptic plasticity based on spike timing10.1007/s00422-008-0233-1 ↗
12. A quantitative method of text emotiveness evaluation on base of the psycholinguistic markers founded on morphological features10.1016/j.procs.2015.11.036 ↗
13. A comparison of learning abilities of spiking networks with different spike timing-dependent plasticity forms10.1088/1742-6596/681/1/012013 ↗
14. To the question of learnability of a spiking neuron with spike-timing-dependent plasticity in case of complex input signals
15. Stable hebbian learning from spike timing-dependent plasticity10.1523/JNEUROSCI.20-23-08812.2000 ↗
16. Elektronnyy korpus studencheskikh esse na russkom yazyke i ego vozmozhnosti dlya sovremennykh gumanitarnykh issledovaniy [electronic corpus of student essays and its applications in modern humanity studies]