rockpool.weights.reservoirweights
Utility functions for generating and manipulating networks
Functions
|
DiscretiseWeightMatrix - Discretise a weight matrix by strength |
|
|
|
combine_ff_rec_stack - Combine a FFwd and Recurrent weight matrix into a single recurrent weight matrix :param weights_ff: MxN np.ndarray :param weights_rec: NxN np.ndarray |
|
digital - Create a weight matrix that conforms the specifications of the Dynapse Chip |
|
dynapse_conform - Create a weight matrix that conforms the specifications of the Dynapse Chip |
|
Generate weight matrices that embody sparse networks with defined partition sizes |
|
iaf_sparse_net - Return a random sparse reservoir, scaled for a standard IAF spiking network |
|
in_res_digital - Create input weights and recurrent weights for reservoir, respecting dynapse specifications |
|
in_res_dynapse - Create input weights and recurrent weights for reservoir, respecting dynapse specifications |
|
in_res_dynapse_flex - Like in_res_dynapse but number of input weights can be chosen |
|
inp_to_rec - Create an integer weight matrix that serves as input weights to the |
|
one_dim_exc_res - Recurrent weight matrix where each neuron is connected to its n_neighbour nearest neighbours on a 1D grid. |
|
|
|
|
|
rndm_ei_net - Generate a random nicely-tuned real-valued reservoir matrix :param num_exc: Number of excitatory neurons in the network :param num_inh: Number of inhibitory neurons in the network :param ratio_inh_exc: Factor relating total inhibitory and excitatory weight (w_inh = ratio_inh_exc * w_exc) default: 1 :param rndm_weight_fct: Function used to draw initial random weights. |
|
rndm_sparse_ei_net - Return a (sparse) matrix defining reservoir weights |
|
|
|
unit_lambda_net - Generate a network from Norm(0, sqrt(N)) |
|
wilson_cowan_net - FUNCTION Define a Wilson-Cowan network of oscillators |
|
wipe_non_switiching_eigs - Eliminate eigenvectors that do not lead to a partition switching |