norse.torch.module.lsnn

norse.torch.module.lsnn#

Long-short term memory module, building on the work by [G. Bellec, D. Salaj, A. Subramoney, R. Legenstein, and W. Maass](IGITUGraz/LSNN-official).

See norse.torch.functional.lsnn for more information.

Classes

LSNN([p, adjoint])

A Long short-term memory neuron module without recurrence adapted from https://arxiv.org/abs/1803.09574

LSNNCell([p, adjoint])

Euler integration cell for LIF Neuron with threshold adaptation without recurrence.

LSNNRecurrent(input_size, hidden_size[, p, ...])

A Long short-term memory neuron module wit recurrence adapted from https://arxiv.org/abs/1803.09574

LSNNRecurrentCell(input_size, hidden_size[, ...])

Module that computes a single euler-integration step of a LSNN neuron-model with recurrence.