devices.xylo.XyloSim

class devices.xylo.XyloSim(*args, **kwargs)[source]

Bases: rockpool.nn.modules.module.Module

A Module simulating a digital SNN on Xylo, using XyloSim as a back-end.

You should use the factory methods from_config and from_specification to build a concrete XyloSim module.

See also

See the tutorials Overview of the Xylo development kit and Training a spiking network to deploy to the Xylo digital SNN for a high-level overview of building and deploying networks for Xylo.

__init__(create_key, config: Union[Dict, Any], shape: tuple = (16, 1000, 8), dt: float = 0.001, output_mode: str = 'Spike', *args, **kwargs)[source]

Private constructor for XyloSim

Warning

Use the factory methods XyloSim.from_config() and XyloSim.from_specfication() to construct a XyloSim module.

Attributes overview

class_name

Class name of self

full_name

The full name of this module (class plus module name)

name

The name of this module, or an empty string if None

output_mode

Private key to ensure factory creation

shape

The shape of this module

size

(DEPRECATED) The output size of this module

size_in

The input size of this module

size_out

The output size of this module

spiking_input

If True, this module receives spiking input.

spiking_output

If True, this module sends spiking output.

config

(XyloConfiguration) Configuration of the Xylo module

dt

(float) Simulation time-step for this module

Methods overview

__init__(create_key,Β config[,Β shape,Β dt,Β ...])

Private constructor for XyloSim

as_graph()

Convert this module to a computational graph

attributes_named(name)

Search for attributes of this or submodules by time

evolve([input_raster,Β record])

Evolve the state of this module over input data

from_config(config[,Β dt,Β output_mode])

Creata a XyloSim based layer to simulate the Xylo hardware, from a configuration

from_specification(weights_in,Β weights_out)

Instantiate a XyloSim module from a full set of parameters

modules()

Return a dictionary of all sub-modules of this module

parameters([family])

Return a nested dictionary of module and submodule Parameters

reset_parameters()

Reset all parameters in this module

reset_state()

Reset the state of this module.

set_attributes(new_attributes)

Set the attributes and sub-module attributes from a dictionary

simulation_parameters([family])

Return a nested dictionary of module and submodule SimulationParameters

state([family])

Return a nested dictionary of module and submodule States

timed([output_num,Β dt,Β add_events])

Convert this module to a TimedModule

__create_key = <object object>
__init__(create_key, config: Union[Dict, Any], shape: tuple = (16, 1000, 8), dt: float = 0.001, output_mode: str = 'Spike', *args, **kwargs)[source]

Private constructor for XyloSim

Warning

Use the factory methods XyloSim.from_config() and XyloSim.from_specfication() to construct a XyloSim module.

_abc_impl = <_abc_data object>
_auto_batch(data: numpy.ndarray, states: typing.Tuple = (), target_shapes: typing.Optional[typing.Tuple] = None) -> (<class 'numpy.ndarray'>, typing.Tuple[numpy.ndarray])

Automatically replicate states over batches and verify input dimensions

Examples

>>> data, (state0, state1, state2) = self._auto_batch(data, (self.state0, self.state1, self.state2))

This will verify that data has the correct final dimension (i.e. self.size_in).

If data has only two dimensions (T, Nin), then it will be augmented to (1, T, Nin). The individual states will be replicated out from shape (a, b, c, ...) to (n_batches, a, b, c, ...) and returned.

If data has only a single dimension (T,), it will be expanded to (1, T, self.size_in).

state0, state1, state2 will be replicated out along the batch dimension.

>>> data, (state0,) = self._auto_batch(data, (self.state0,), ((10, -1, self.size_in),))

Attempt to replicate state0 to a specified size (10, -1, self.size_in).

Parameters
  • data (np.ndarray) – Input data tensor. Either (batches, T, Nin) or (T, Nin)

  • states (Tuple) – Tuple of state variables. Each will be replicated out over batches by prepending a batch dimension

  • target_shapes (Tuple) – A tuple of target size tuples, each corresponding to each state argument. The individual states will be replicated out to match the corresponding target sizes. If not provided (the default), then states will be only replicated along batches.

Returns

(np.ndarray, Tuple[np.ndarray]) data, states

_force_set_attributes

(bool) If True, do not sanity-check attributes when setting.

_get_attribute_family(type_name: str, family: Optional[Union[Tuple, List, str]] = None) dict

Search for attributes of this module and submodules that match a given family

This method can be used to conveniently get all weights for a network; or all time constants; or any other family of parameters. Parameter families are defined simply by a string: "weights" for weights; "taus" for time constants, etc. These strings are arbitrary, but if you follow the conventions then future developers will thank you (that includes you in six month’s time).

Parameters
  • type_name (str) – The class of parameters to search for. Must be one of ["Parameter", "SimulationParameter", "State"] or another future subclass of ParameterBase

  • family (Union[str, Tuple[str]]) – A string or list or tuple of strings, that define one or more attribute families to search for

Returns

A nested dictionary of attributes that match the provided type_name and family

Return type

dict

_get_attribute_registry() Tuple[Dict, Dict]

Return or initialise the attribute registry for this module

Returns

registered_attributes, registered_modules

Return type

(tuple)

_has_registered_attribute(name: str) bool

Check if the module has a registered attribute

Parameters

name (str) – The name of the attribute to check

Returns

True if the attribute name is in the attribute registry, False otherwise.

Return type

bool

_in_Module_init

(bool) If exists and True, indicates that the module is in the __init__ chain.

_name: Optional[str]

Name of this module, if assigned

_register_attribute(name: str, val: rockpool.parameters.ParameterBase)

Record an attribute in the attribute registry

Parameters
  • name (str) – The name of the attribute to register

  • val (ParameterBase) – The ParameterBase subclass object to register. e.g. Parameter, SimulationParameter or State.

_register_module(name: str, mod: rockpool.nn.modules.module.ModuleBase)

Register a sub-module in the module registry

Parameters
  • name (str) – The name of the module to register

  • mod (ModuleBase) – The ModuleBase object to register

_reset_attribute(name: str) rockpool.nn.modules.module.ModuleBase

Reset an attribute to its initialisation value

Parameters

name (str) – The name of the attribute to reset

Returns

For compatibility with the functional API

Return type

self (Module)

_shape

The shape of this module

_spiking_input: bool

Whether this module receives spiking input

_spiking_output: bool

Whether this module produces spiking output

_submodulenames: List[str]

Registry of sub-module names

_wrap_recorded_state(state_dict: dict, t_start: float = 0.0) dict[source]

Convert a recorded dictionary to a TimeSeries representation

This method is optional, and is provided to make the timed() conversion to a TimedModule work better. You should override this method in your custom Module, to wrap each element of your recorded state dictionary as a TimeSeries

Parameters
  • state_dict (dict) – A recorded state dictionary as returned by evolve()

  • t_start (float) – The initial time of the recorded state, to use as the starting point of the time series

Returns

The mapped recorded state dictionary, wrapped as TimeSeries objects

Return type

Dict[str, TimeSeries]

_xylo_layer: Optional[XyloLayer]

(XyloLayer) Handle to a XyloSim object

as_graph() rockpool.graph.graph_base.GraphModuleBase

Convert this module to a computational graph

Returns

The computational graph corresponding to this module

Return type

GraphModuleBase

Raises

NotImplementedError – If as_graph() is not implemented for this subclass

attributes_named(name: Union[Tuple[str], List[str], str]) dict

Search for attributes of this or submodules by time

Parameters

name (Union[str, Tuple[str]) – The name of the attribute to search for

Returns

A nested dictionary of attributes that match name

Return type

dict

property class_name: str

Class name of self

Type

str

config: Union[XyloConfiguration, Parameter]

(XyloConfiguration) Configuration of the Xylo module

dt: Union[float, SimulationParameter]

(float) Simulation time-step for this module

evolve(input_raster: Optional[numpy.ndarray] = None, record: bool = False, *args, **kwargs)[source]

Evolve the state of this module over input data

NOTE: THIS MODULE CLASS DOES NOT PROVIDE DOCUMENTATION FOR ITS EVOLVE METHOD. PLEASE UPDATE THE DOCUMENTATION FOR THIS MODULE.

Parameters
  • input_data – The input data with shape (T, size_in) to evolve with

  • record (bool) – If True, the module should record internal state during evolution and return the record. If False, no recording is required. Default: False.

Returns

(output, new_state, record)

output (np.ndarray): The output response of this module with shape (T, size_out) new_state (dict): A dictionary containing the updated state of this and all submodules after evolution record (dict): A dictionary containing recorded state of this and all submodules, if requested using the record argument

Return type

tuple

classmethod from_config(config: Union[Dict, Any], dt: float = 0.001, output_mode: str = 'Spike')[source]

Creata a XyloSim based layer to simulate the Xylo hardware, from a configuration

Parameters: dt: float

Timestep for simulation, in seconds. Default: 1ms

config: XyloConfiguration

samna.xylo.XyloConfiguration object to specify all parameters. See samna documentation for details.

classmethod from_specification(weights_in: numpy.ndarray, weights_out: numpy.ndarray, weights_rec: Optional[numpy.ndarray] = None, dash_mem: Optional[numpy.ndarray] = None, dash_mem_out: Optional[numpy.ndarray] = None, dash_syn: Optional[numpy.ndarray] = None, dash_syn_2: Optional[numpy.ndarray] = None, dash_syn_out: Optional[numpy.ndarray] = None, threshold: Optional[numpy.ndarray] = None, threshold_out: Optional[numpy.ndarray] = None, weight_shift_in: int = 0, weight_shift_rec: int = 0, weight_shift_out: int = 0, aliases: Optional[list] = None, dt: float = 0.001, verify_config: bool = True, output_mode: str = 'Spike') devices.xylo.syns61300.xylo_sim.XyloSim[source]

Instantiate a XyloSim module from a full set of parameters

Parameters
  • weights_in (np.ndarray) – An int8 matrix (Nin, Nhidden, 2), specifying input to hidden neuron connections. The final dimension specifies the inputs to the two available synapses of the hidden neurons.

  • weights_out (np.ndarray) – An int8 matrix (Nhidden, Nout), specifying hidden to output connections.

  • weights_rec (Optional[np.ndarray]) – An int8 matrix (Nhidden, Nhidden, 2), specifying recurrent connections within the hidden population. The final dimension specifies the input to the two available synapses on each hidden neuron. Default: 0, no recurrent connections.

  • dash_mem (Optional[np.ndarray]) – An int8 matrix (Nhidden), specifying the bitshift decay value for each hidden neuron membrane potential. Default: 1.

  • dash_mem_out (Optional[np.ndarray]) – An int8 matrix (Nout), specifying the bitshift decay value for each output neuron membrane potential. Default: 1.

  • dash_syn (Optional[np.ndarray]) – An int8 matrix (Nhidden), specifying the bitshift decay value for each hidden neuron synaptic current number 1. Default: 1.

  • dash_syn_2 (Optional[np.ndarray]) – An int8 matrix (Nhidden), specifying the bitshift decay value for each hidden neuron synaptic current number 2. Default: 1.

  • dash_syn_out (Optional[np.ndarray]) – An int8 matrix (Nout), specifying the bitshift decay value for each output neuron synaptic current. Default: 1.

  • threshold (Optional[np.ndarray]) – An int8 matrix (Nhidden), specifying the firing threshold for each hidden neuron. Default: 0.

  • threshold_out (Optional[np.ndarray]) – An int8 matrix (Nhidden), specifying the firing threshold for each output neuron. Default: 0.

  • weight_shift_in (int) – An integer number of bits to left-shift the input weight matrix

  • weight_shift_rec (int) – An integer number of bits to left-shift the hidden weight matrix

  • weight_shift_out (int) – An integer number of bits to left-shift the output weight matrix

  • aliases (Optional[list]) –

  • dt (float) – Simulation time step in seconds. Default: 1 ms

  • verify_config (bool) – Check for a valid configuraiton before applying it. Default True.

Returns

A Module that emulates the Xylo hardware.

Return type

XyloSim

Raises

ValueError – If verify_config is True and the configuration is not valid.

property full_name: str

The full name of this module (class plus module name)

Type

str

modules() Dict

Return a dictionary of all sub-modules of this module

Returns

A dictionary containing all sub-modules. Each item will be named with the sub-module name.

Return type

dict

property name: str

The name of this module, or an empty string if None

Type

str

output_mode = 'Spike'

Private key to ensure factory creation

parameters(family: Optional[Union[Tuple, List, str]] = None) Dict

Return a nested dictionary of module and submodule Parameters

Use this method to inspect the Parameters from this and all submodules. The optional argument family allows you to search for Parameters in a particular family β€” for example "weights" for all weights of this module and nested submodules.

Although the family argument is an arbitrary string, reasonable choises are "weights", "taus" for time constants, "biases" for biases…

Examples

Obtain a dictionary of all Parameters for this module (including submodules):

>>> mod.parameters()
dict{ ... }

Obtain a dictionary of Parameters from a particular family:

>>> mod.parameters("weights")
dict{ ... }
Parameters

family (str) – The family of Parameters to search for. Default: None; return all parameters.

Returns

A nested dictionary of Parameters of this module and all submodules

Return type

dict

reset_parameters()

Reset all parameters in this module

Returns

The updated module is returned for compatibility with the functional API

Return type

Module

reset_state() devices.xylo.syns61300.xylo_sim.XyloSim[source]

Reset the state of this module.

set_attributes(new_attributes: dict) rockpool.nn.modules.module.ModuleBase

Set the attributes and sub-module attributes from a dictionary

This method can be used with the dictionary returned from module evolution to set the new state of the module. It can also be used to set multiple parameters of a module and submodules.

Examples

Use the functional API to evolve, obtain new states, and set those states:

>>> _, new_state, _ = mod(input)
>>> mod = mod.set_attributes(new_state)

Obtain a parameter dictionary, modify it, then set the parameters back:

>>> params = mod.parameters()
>>> params['w_input'] *= 0.
>>> mod.set_attributes(params)
Parameters

new_attributes (dict) – A nested dictionary containing parameters of this module and sub-modules.

property shape: tuple

The shape of this module

Type

tuple

simulation_parameters(family: Optional[Union[Tuple, List, str]] = None) Dict

Return a nested dictionary of module and submodule SimulationParameters

Use this method to inspect the SimulationParameters from this and all submodules. The optional argument family allows you to search for SimulationParameters in a particular family.

Examples

Obtain a dictionary of all SimulationParameters for this module (including submodules):

>>> mod.simulation_parameters()
dict{ ... }
Parameters

family (str) – The family of SimulationParameters to search for. Default: None; return all SimulationParameter attributes.

Returns

A nested dictionary of SimulationParameters of this module and all submodules

Return type

dict

property size: int

(DEPRECATED) The output size of this module

Type

int

property size_in: int

The input size of this module

Type

int

property size_out: int

The output size of this module

Type

int

property spiking_input: bool

If True, this module receives spiking input. If False, this module expects continuous input.

Type

bool

property spiking_output

If True, this module sends spiking output. If False, this module sends continuous output.

Type

bool

state(family: Optional[Union[Tuple, List, str]] = None) Dict

Return a nested dictionary of module and submodule States

Use this method to inspect the States from this and all submodules. The optional argument family allows you to search for States in a particular family.

Examples

Obtain a dictionary of all States for this module (including submodules):

>>> mod.state()
dict{ ... }
Parameters

family (str) – The family of States to search for. Default: None; return all State attributes.

Returns

A nested dictionary of States of this module and all submodules

Return type

dict

timed(output_num: int = 0, dt: Optional[float] = None, add_events: bool = False)

Convert this module to a TimedModule

Parameters
  • output_num (int) – Specify which output of the module to take, if the module returns multiple output series. Default: 0, take the first (or only) output.

  • dt (float) – Used to provide a time-step for this module, if the module does not already have one. If self already defines a time-step, then self.dt will be used. Default: None

  • add_events (bool) – Iff True, the TimedModule will add events occurring on a single timestep on input and output. Default: False, don’t add time steps.

Returns: TimedModule: A timed module that wraps this module