norse.torch.functional.stdp_sensor module

class norse.torch.functional.stdp_sensor.STDPSensorParameters(eta_p: torch.Tensor = tensor(1.), eta_m: torch.Tensor = tensor(1.), tau_ac_inv: torch.Tensor = tensor(10.), tau_c_inv: torch.Tensor = tensor(10.))

Bases: tuple

Parameters of an STDP sensor as it is used for event driven plasticity rules.

Parameters

• eta_p (torch.Tensor) – correlation state

• eta_m (torch.Tensor) – anti correlation state

• tau_ac_inv (torch.Tensor) – anti-correlation sensor time constant

• tau_c_inv (torch.Tensor) – correlation sensor time constant

Create new instance of STDPSensorParameters(eta_p, eta_m, tau_ac_inv, tau_c_inv)

eta_m: torch.Tensor

Alias for field number 1

eta_p: torch.Tensor

Alias for field number 0

tau_ac_inv: torch.Tensor

Alias for field number 2

tau_c_inv: torch.Tensor

Alias for field number 3

class norse.torch.functional.stdp_sensor.STDPSensorState(a_pre: torch.Tensor, a_post: torch.Tensor)

Bases: tuple

State of an event driven STDP sensor.

Parameters

• a_pre (torch.Tensor) – presynaptic STDP sensor state.

• a_post (torch.Tensor) – postsynaptic STDP sensor state.

Create new instance of STDPSensorState(a_pre, a_post)

a_post: torch.Tensor

Alias for field number 1

a_pre: torch.Tensor

Alias for field number 0

norse.torch.functional.stdp_sensor.stdp_sensor_step(z_pre, z_post, state, p=STDPSensorParameters(eta_p=tensor(1.), eta_m=tensor(1.), tau_ac_inv=tensor(10.), tau_c_inv=tensor(10.)), dt=0.001)

Event driven STDP rule.

Parameters

• z_pre (torch.Tensor) – pre-synaptic spikes

• z_post (torch.Tensor) – post-synaptic spikes

• s (STDPSensorState) – state of the STDP sensor

• p (STDPSensorParameters) – STDP sensor parameters

• dt (float) – integration time step

Return type

STDPSensorState