nengolib.synapses.HeteroSynapse¶

class
nengolib.synapses.
HeteroSynapse
(systems, dt=None, elementwise=False, method='zoh')[source]¶ Callable class for applying different synapses to an input vector.
This is typically to be used as the
output
parameter for some intermediatenengo.Node
in a Nengo model.Parameters:  systems : (one or more)
linear_system_like
One or more linear system representations, providing each synapse.
 dt :
float
, optional Simulation timestep used to discretize each of the systems. If
dt
isNone
(the default), then all of the systems must already be digital. elementwise :
boolean
, optional If
elementwise == False
(default), each synapse is applied to every dimension, and sosize_out == size_in*len(synapses)
. The output dimensions are ordered by input dimension, such that indexi*len(synapses) + j
is thei
’th input dimension convolved with thej
’th filter.If
elementwise == True
,len(synapses)
must matchsize_in
, in which case each synapse is applied separately to each dimension, and sosize_out == size_in
.The latter can be used to connect to a population of neurons with a different synapse for each neuron. The former can be used to apply a number of synapses to each dimension in statespace.
 method :
string
, optional Method passed to
cont2discrete()
. Defaults to'zoh'
.
See also
Examples
See Heterogeneous Synapses for a notebook example.
Methods
__call__
(t, u)Node function called by simulator on each timestep. from_vector
(x)Inverse of to_vector
; recovers matrix from output vector.to_vector
(y)Inverse of from_vector
; flattens matrix into an output vector. systems : (one or more)