spynnaker8.models.connectors package

Module contents

Connectors are objects that describe how neurons in Populations are connected to each other.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors instead.

class spynnaker8.models.connectors.AllToAllConnector(allow_self_connections=True, safe=True, verbose=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.all_to_all_connector.AllToAllConnector

Connects all cells in the presynaptic population to all cells in the postsynaptic population

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.AllToAllConnector instead.

Parameters:
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.ArrayConnector(array, safe=True, callback=None, verbose=False)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.array_connector.ArrayConnector

Make connections using an array of integers based on the IDs of the neurons in the pre- and post-populations.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.ArrayConnector instead.

Parameters:
  • array (ndarray(2, uint8)) – an array of integers
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.

  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
class spynnaker8.models.connectors.CSAConnector(cset, safe=True, callback=None, verbose=False)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.csa_connector.CSAConnector

A CSA (Connection Set Algebra, Djurfeldt 2012) connector.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.CSAConnector instead.

Parameters:
  • cset (csa.connset.CSet) – a connection set description
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.DistanceDependentProbabilityConnector(d_expression, allow_self_connections=True, safe=True, verbose=False, n_connections=None, rng=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.distance_dependent_probability_connector.DistanceDependentProbabilityConnector

Make connections using a distribution which varies with distance.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.DistanceDependentProbabilityConnector instead.

Parameters:
  • d_expression (str) – the right-hand side of a valid python expression for probability, involving d, e.g. "exp(-abs(d))", or "d<3", that can be parsed by eval(), that computes the distance dependent distribution
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • n_connections (int) – The number of efferent synaptic connections per neuron.
  • rng (NumpyRNG) – random number generator
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.FixedNumberPostConnector(n, allow_self_connections=True, safe=True, verbose=False, with_replacement=False, rng=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.fixed_number_post_connector.FixedNumberPostConnector

PyNN connector that puts a fixed number of connections on each of the post neurons.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.FixedNumberPostConnector instead.

Parameters:
  • n (int) – number of random post-synaptic neurons connected to pre-neurons
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • safe (bool) – Whether to check that weights and delays have valid values; if False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • with_replacement (bool) – if False, once a connection is made, it can’t be made again; if True, multiple connections between the same pair of neurons are allowed
  • rng (NumpyRNG or None) – random number generator
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.FixedNumberPreConnector(n, allow_self_connections=True, safe=True, verbose=False, with_replacement=False, rng=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.fixed_number_pre_connector.FixedNumberPreConnector

Connects a fixed number of pre-synaptic neurons selected at random, to all post-synaptic neurons.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.FixedNumberPreConnector instead.

Parameters:
  • n (int) – number of random pre-synaptic neurons connected to post-neurons
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • with_replacement (bool) – if False, once a connection is made, it can’t be made again; if True, multiple connections between the same pair of neurons are allowed
  • rng (NumpyRNG or None) – random number generator
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.FixedProbabilityConnector(p_connect, allow_self_connections=True, safe=True, verbose=False, rng=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.fixed_probability_connector.FixedProbabilityConnector

For each pair of pre-post cells, the connection probability is constant.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.FixedProbabilityConnector instead.

Parameters:
  • p_connect (float) – a number between zero and one. Each potential connection is created with this probability.
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • space (Space) – a Space object, needed if you wish to specify distance-dependent weights or delays - not implemented
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • rng (NumpyRNG or None) – random number generator
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.FromFileConnector(file, distributed=False, safe=True, callback=None, verbose=False)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.from_file_connector.FromFileConnector

Make connections according to a list read from a file.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.FromFileConnector instead.

Parameters:
  • file (str or FileIO) –

    Either an open file object or the filename of a file containing a list of connections, in the format required by FromListConnector. Column headers, if included in the file, must be specified using a list or tuple, e.g.:

    # columns = ["i", "j", "weight", "delay", "U", "tau_rec"]

    Note that the header requires # at the beginning of the line.

  • distributed (bool) –

    Basic pyNN says:

    if this is True, then each node will read connections from a file called filename.x, where x is the MPI rank. This speeds up loading connections for distributed simulations.

    Note

    Always leave this as False with sPyNNaker, which is not MPI-based.

  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.

  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
class spynnaker8.models.connectors.FromListConnector(conn_list, safe=True, verbose=False, column_names=None, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.from_list_connector.FromListConnector

Make connections according to a list.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.FromListConnector instead.

Parameters:
  • conn_list (list(tuple(int,int,..)) or ndarray) – a list of tuples, one tuple for each connection. Each tuple should contain: (pre_idx, post_idx, p1, p2, …, pn) where pre_idx is the index (i.e. order in the Population, not the ID) of the presynaptic neuron, post_idx is the index of the postsynaptic neuron, and p1, p2, etc. are the synaptic parameters (e.g., weight, delay, plasticity parameters).
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • column_names (tuple(str) or list(str) or None) – the names of the parameters p1, p2, etc. If not provided, it is assumed the parameters are weight, delay (for backwards compatibility).
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.IndexBasedProbabilityConnector(index_expression, allow_self_connections=True, rng=None, safe=True, callback=None, verbose=False)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.index_based_probability_connector.IndexBasedProbabilityConnector

Create an index-based probability connector.
The index_expression must depend on the indices i, j of the populations.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.IndexBasedProbabilityConnector instead.

Parameters:
  • index_expression (str) – A function of the indices of the populations, written as a Python expression; the indices will be given as variables i and j when the expression is evaluated.
  • allow_self_connections (bool) – allow a neuron to connect to itself
  • rng (NumpyRNG or None) – random number generator
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • callback (callable) –

    if given, a callable that display a progress bar on the terminal.

    Note

    Not supported by sPyNNaker.

  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
class spynnaker8.models.connectors.MultapseConnector(n, allow_self_connections=True, with_replacement=True, safe=True, verbose=False, rng=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.multapse_connector.MultapseConnector

Create a multapse connector. The size of the source and destination populations are obtained when the projection is connected. The number of synapses is specified. when instantiated, the required number of synapses is created by selecting at random from the source and target populations with replacement (by default). Uniform selection probability is assumed.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.MultapseConnector instead.

Parameters:
  • n (int) – This is the total number of synapses in the connection.
  • allow_self_connections (bool) – Allow a neuron to connect to itself or not.
  • with_replacement (bool) – When selecting, allow a neuron to be re-selected or not.
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • rng (NumpyRNG or None) – random number generator
class spynnaker8.models.connectors.OneToOneConnector(safe=True, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.one_to_one_connector.OneToOneConnector

Where the pre- and postsynaptic populations have the same size, connect cell i in the presynaptic population to cell i in the postsynaptic population for all i.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.OneToOneConnector instead.

Parameters:
  • safe (bool) – if True, check that weights and delays have valid values. If False, this check is skipped.
  • callback (callable) –

    a function that will be called with the fractional progress of the connection routine. An example would be progress_bar.set_level.

    Note

    Not supported by sPyNNaker.
class spynnaker8.models.connectors.SmallWorldConnector(degree, rewiring, allow_self_connections=True, n_connections=None, rng=None, safe=True, callback=None, verbose=False)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.small_world_connector.SmallWorldConnector

Create a connector that uses connection statistics based on the Small World network connectivity model. Note that this is typically used from a population to itself.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.SmallWorldConnector instead.

Parameters:
  • degree (float) – the region length where nodes will be connected locally
  • rewiring (float) – the probability of rewiring each edge
  • allow_self_connections (bool) – if the connector is used to connect a Population to itself, this flag determines whether a neuron is allowed to connect to itself, or only to other neurons in the Population.
  • n_connections (int or None) – if specified, the number of efferent synaptic connections per neuron
  • rng (NumpyRNG or None) – random number generator
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • callback (callable) – For PyNN compatibility only.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
class spynnaker8.models.connectors.KernelConnector(shape_pre, shape_post, shape_kernel, weight_kernel=None, delay_kernel=None, shape_common=None, pre_sample_steps_in_post=None, pre_start_coords_in_post=None, post_sample_steps_in_pre=None, post_start_coords_in_pre=None, safe=True, space=None, verbose=False, callback=None)[source]

Bases: spynnaker.pyNN.models.neural_projections.connectors.kernel_connector.KernelConnector

Where the pre- and post-synaptic populations are considered as a 2D array. Connect every post(row, col) neuron to many pre(row, col, kernel) through a (kernel) set of weights and/or delays.

Deprecated since version 6.0: Use spynnaker.pyNN.models.neural_projections.connectors.KernelConnector instead.

Parameters:
  • shape_pre (tuple(int,int)) – 2D shape of the pre population (rows/height, cols/width, usually the input image shape)
  • shape_post (tuple(int,int)) – 2D shape of the post population (rows/height, cols/width)
  • shape_kernel (tuple(int,int)) – 2D shape of the kernel (rows/height, cols/width)
  • weight_kernel (ndarray or NumpyRNG or int or float or list(int) or list(float) or None) – (optional) 2D matrix of size shape_kernel describing the weights
  • delay_kernel (ndarray or NumpyRNG or int or float or list(int) or list(float) or None) – (optional) 2D matrix of size shape_kernel describing the delays
  • shape_common (tuple(int,int)) – (optional) 2D shape of common coordinate system (for both pre and post, usually the input image sizes)
  • pre_sample_steps_in_post (tuple(int,int)) – (optional) Sampling steps/jumps for pre pop \(\Leftrightarrow\) \((\mathsf{step}_x, \mathsf{step}_y)\)
  • pre_start_coords_in_post (tuple(int,int)) – (optional) Starting row/col for pre sampling \(\Leftrightarrow\) \((\mathsf{offset}_x, \mathsf{offset}_y)\)
  • post_sample_steps_in_pre (tuple(int,int)) – (optional) Sampling steps/jumps for post pop \(\Leftrightarrow\) \((\mathsf{step}_x, \mathsf{step}_y)\)
  • post_start_coords_in_pre (tuple(int,int)) – (optional) Starting row/col for post sampling \(\Leftrightarrow\) \((\mathsf{offset}_x, \mathsf{offset}_y)\)
  • safe (bool) – Whether to check that weights and delays have valid values. If False, this check is skipped.
  • space (Space) – Currently ignored; for future compatibility.
  • verbose (bool) – Whether to output extra information about the connectivity to a CSV file
  • callback (callable) – (ignored)