EventFixedNumConn

class brainstate.nn.EventFixedNumConn(in_size, out_size, conn_num, conn_weight, efferent_target='post', afferent_ratio=1.0, allow_multi_conn=True, seed=None, name=None, conn_init='vmap', param_type=<class 'brainstate.ParamState'>)

The FixedProb module implements a fixed probability connection with CSR sparse data structure.

Parameters:

• in_size (int | Sequence[int] | integer | Sequence[integer]) – Number of pre-synaptic neurons, i.e., input size.

• out_size (int | Sequence[int] | integer | Sequence[integer]) – Number of post-synaptic neurons, i.e., output size.

• conn_num (int | float) –

  If it is a float, representing the probability of connection, i.e., connection probability.

  If it is an integer, representing the number of connections.

• conn_weight (Callable | Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Maximum synaptic conductance, i.e., synaptic weight.

• conn_target (str, optional) –

  The target of the connection. Default is ‘post’, meaning that each pre-synaptic neuron connects to a fixed number of post-synaptic neurons. The connection number is determined by the value of n_conn.

  If ‘pre’, each post-synaptic neuron connects to a fixed number of pre-synaptic neurons.

• conn_init (str) –

  The initialization method of the connection weight. Default is ‘vmap’, meaning that the connection weight is initialized by parallelized across multiple threads.

  If ‘for_loop’, the connection weight is initialized by a for loop.

• allow_multi_conn (bool) – Whether multiple connections are allowed from a single pre-synaptic neuron. Default is True, meaning that a value of a can be selected multiple times.

• seed (int | None) – Random seed. Default is None. If None, the default random seed will be used.

• name (str | None) – Name of the module.