Phase shifts of membrane potential [13].

|@|~(^,^)~|@|

Hodgkin-Huxley model.

|@|~(^,^)~|@|

Leaky integrate-and-fire (LIF) model.

|@|~(^,^)~|@|

Izhikevich model [18].

|@|~(^,^)~|@|

An spike-timing-dependent plasticity (STDP) function.

|@|~(^,^)~|@|

A Synfire chain architecture [24].

|@|~(^,^)~|@|

A liquid state machine architecture [25].

|@|~(^,^)~|@|

Population coding.

|@|~(^,^)~|@|

An SNN with multiple synaptic connections [37].

|@|~(^,^)~|@|

An SNN for ReSuMe training [38].

|@|~(^,^)~|@|

An SNN for BP-STDP training [32]. L_i is the target spike train, G_i is the generated spike train at node i of the output layer, G_h is the generated spike train at node h of a hidden layer, and G_j is the spike train of node j at the input layer which encodes a scalar input value.

|@|~(^,^)~|@|

Surrogate gradient functions which lim_ai→0+h_i(u) = dg(u)/du where g(u) is an activation function [42].

|@|~(^,^)~|@|

Firing rate functions for soft-LIF (dotted curve) and LIF (solid curve) [44].

|@|~(^,^)~|@|

Sharpening of bReLU function at the Whetstone method.

|@|~(^,^)~|@|

Activation functions of ReLU, threshold ReLU, and SNN.

|@|~(^,^)~|@|

A modified ReLU function and its derivative.

|@|~(^,^)~|@|

Knowledge distillation-based SNN training [58].

© IJFIS