Glossary - Practical Spiking Neural Networks

$i_\text{decay}$: $=$ exp $(\frac{-\Delta t}{\tau_\text{s}})$ , it is the current decay of a CUBA spiking neuron model (in their discrete-time implementation), where $\tau_\text{s}$ is the synaptic time-constant Rossbroich et al., 2022.
NoC: Network-on-Chip, a communication architecture that integrates multiple processing elements into a single chip.
ODE: Ordinary Differential Equation, a mathematical equation that describes how a function changes with respect to one or more variables.
SNN: Spiking Neural Network, a type of brain-inspired neural network that more closely mimics the behavior of biological neurons by using discrete spikes for communication.
$v_\text{decay}$: $=$ exp $(\frac{-\Delta t}{\tau_\text{m}})$ , it is the voltage decay of a CUrrent BAsed (CUBA) spiking neuron (in their discrete-time implementation), where $\tau_\text{m}$ is the membrane time-constant Bellec et al., 2018.

References¶

Rossbroich, J., Gygax, J., & Zenke, F. (2022). Fluctuation-driven initialization for spiking neural network training. Neuromorphic Computing and Engineering, 2(4), 044016.
Bellec, G., Salaj, D., Subramoney, A., Legenstein, R., & Maass, W. (2018). Long short-term memory and learning-to-learn in networks of spiking neurons. Advances in Neural Information Processing Systems, 31.