Welcome to ngc-learn’s documentation!
ngc-learn is a Python library for building, simulating, and analyzing biomimetic computational models, arbitrary predictive processing/coding models, and spiking neural networks. This toolkit is built on top of JAX and is distributed under the 3-Clause BSD license.
- ngclearn
- ngclearn package
- Subpackages
- ngclearn.commands package
- ngclearn.components package
- ngclearn.utils package
- Subpackages
- Submodules
- ngclearn.utils.data_loader module
- ngclearn.utils.io_utils module
- ngclearn.utils.metric_utils module
- ngclearn.utils.model_utils module
binarize()
clamp_max()
clamp_min()
create_function()
d_heaviside()
d_identity()
d_lrelu()
d_relu()
d_relu6()
d_sigmoid()
d_softplus()
d_tanh()
d_threshold()
drop_out()
heaviside()
identity()
initialize_params()
inverse_logistic()
inverse_tanh()
lrelu()
measure_ACC()
measure_BCE()
measure_CatNLL()
measure_KLD()
measure_MSE()
normalize_matrix()
one_hot()
pull_equations()
relu()
relu6()
sigmoid()
softmax()
softplus()
tanh()
threshold()
threshold_cauchy()
threshold_soft()
- ngclearn.utils.patch_utils module
- ngclearn.utils.surrogate_fx module
- Module contents
- Module contents
- Subpackages
- ngclearn package