7895b442152e923cefd3eb8bd0346e1ae4180b14,bindsnet/network/nodes.py,DiehlAndCookNodes,step,#DiehlAndCookNodes#Any#Any#,383

Before Change

            | :code:`dt` (:code:`float`): Simulation time step.
        """
        // Decay voltages and adaptive thresholds.
        self.v -= dt * self.decay * (self.v - self.rest)
        self.theta -= dt * self.theta_decay * self.theta
        
        // Decrement refractory counters.
        self.refrac_count[self.refrac_count != 0] -= dt

        // Check for spiking neurons.
        self.s = (self.v >= self.thresh + self.theta) * (self.refrac_count == 0)

        // Refractoriness, voltage reset, and adaptive thresholds.
        self.refrac_count = self.refrac_count.masked_fill(self.s, self.refrac)
        self.v = self.v.masked_fill(self.s, self.reset)
        self.theta += self.theta_plus * self.s.float()
        
        // Choose only a single neuron to spike.
        if torch.sum(self.s) > 0:
            s = torch.zeros(self.s.size())
            s = s.view(-1)
            s[torch.multinomial(self.s.float().view(-1), 1)] = 1
            self.s = s.view(self.s.size()).byte()
        
        // Integrate inputs.
        self.v += inpts

        super().step(inpts, dt)
        

After Change

        self.refrac_count[self.refrac_count != 0] -= dt

        // Check for spiking neurons.
        self.s = (self.v >= self.thresh + self.theta) & (self.refrac_count == 0)

        // Refractoriness, voltage reset, and adaptive thresholds.
        self.refrac_count.masked_fill_(self.s, self.refrac)
        self.v.masked_fill_(self.s, self.reset)
        self.theta += self.theta_plus * self.s.float()
        
        // Choose only a single neuron to spike.
        if torch.sum(self.s) > 0:

Instances