inox.nn.recurrent#
Recurrent layers
Classes#
Descriptions#
- class inox.nn.recurrent.Cell(**kwargs)#
Abstract cell class.
A cell defines a recurrence function \(f\) of the form
\[(h_i, y_i) = f(h_{i-1}, x_i)\]and an initial hidden state \(h_0\).
Warning
The recurrence function \(f\) should have no side effects.
- __call__(h, x)#
- class inox.nn.recurrent.Recurrent(cell, reverse=False)#
Creates a recurrent layer.
- Parameters:
- class inox.nn.recurrent.BRCell(key, in_features, hid_features, bias=True, modulated=True)#
Creates a bistable recurrent cell (BRC).
References
A bio-inspired bistable recurrent cell allows for long-lasting memory (Vecoven et al., 2021)- Parameters:
- __call__(h, x)#
- class inox.nn.recurrent.MGUCell(key, in_features, hid_features, bias=True)#
Creates a minimal gated unit (MGU) cell.
References
Minimal Gated Unit for Recurrent Neural Networks (Zhou et al., 2016)- Parameters:
- __call__(h, x)#
- class inox.nn.recurrent.GRUCell(key, in_features, hid_features, bias=True)#
Creates a gated recurrent unit (GRU) cell.
References
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (Cho et al., 2014)- Parameters:
- __call__(h, x)#