Neuron types¶
Build Nengo neuron types into the TensorFlow graph.

class
nengo_dl.neuron_builders.
SimNeuronsBuilder
(ops, signals)[source]¶ Builds a group of
SimNeurons
operators.Calls the appropriate subbuild class for the different neuron types.
Attributes:  TF_NEURON_IMPL : list of
NeuronType
The neuron types that have a custom implementation

build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :
 TF_NEURON_IMPL : list of

class
nengo_dl.neuron_builders.
GenericNeuronBuilder
(ops, signals)[source]¶ Builds all neuron types for which there is no custom Tensorflow implementation.
Notes
These will be executed as native Python functions, requiring execution to move in and out of TensorFlow. This can significantly slow down the simulation, so any performancecritical neuron models should consider adding a custom TensorFlow implementation for their neuron type instead.

build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
RectifiedLinearBuilder
(ops, signals)[source]¶ Build a group of
RectifiedLinear
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
SpikingRectifiedLinearBuilder
(ops, signals)[source]¶ Build a group of
SpikingRectifiedLinear
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
SigmoidBuilder
(ops, signals)[source]¶ Build a group of
Sigmoid
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
LIFRateBuilder
(ops, signals)[source]¶ Build a group of
LIFRate
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
LIFBuilder
(ops, signals)[source]¶ Build a group of
LIF
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


class
nengo_dl.neuron_builders.
SoftLIFRateBuilder
(ops, signals)[source]¶ Build a group of
SoftLIFRate
neuron operators.
build_step
(signals)[source]¶ This function builds whatever computations need to be executed in each simulation timestep.
Parameters:  signals :
signals.SignalDict
Mapping from
Signal
totf.Tensor
(updated by operations)
Returns:  list of ``tf.Tensor``, optional
If not None, the returned tensors correspond to outputs with possible sideeffects, i.e. computations that need to be executed in the TensorFlow graph even if their output doesn’t appear to be used
 signals :


nengo_dl.neuron_builders.
get_constant
(ops, attr, dtype)[source]¶ Creates a tensor representing the constant parameters of a neuron type.
Parameters:  ops : list of
SimNeurons
The operators for some merged group of neuron ops
 attr : str
The attribute of the neuron type that describes the constant parameter
 dtype :
tf.Dtype
Numeric type of the parameter
Returns:  ``tf.Tensor``
Tensor containing the values of
attr
for the given ops. This will be a scalar if all the neurons have the same parameter value, or a vector giving the parameter value for each individual neuron.
 ops : list of