Default activation function in Keras

Question

Does anyone know the default activation function used in the recurrent layers in Keras? https://keras.io/layers/recurrent/

It says the default activation function is linear. But what about the default recurrent activation function. Nothing is mentioned about that. Any help would be highly appreciated. Thanks in advance

Has my answer helped you? – Marcin Możejko Jan 12 '18 at 19:40 — Marcin Możejko, Jan 12 '18 at 19:40

Marcin Możejko · Accepted Answer · 2017-09-14T07:05:18.310

7

Keras Recurrent is an abstact class for recurrent layers. In Keras 2.0 all default activations are linear for all implemented RNNs (LSTM, GRU and SimpleRNN). In previous versions you had:

linear for SimpleRNN,
tanh for LSTM and GRU.

edited Sep 14 '17 at 07:05

answered Mar 18 '17 at 18:44

Marcin Możejko

39,542
10
109
120

1

Seems this answer is outdated. In Keras 2.2.4 default activation for LSTM is `tanh` – Xiaohong Deng Apr 16 '19 at 08:25

score 1 · Answer 2 · answered Jan 31 '20 at 09:03

1

https://github.com/keras-team/keras/blob/master/keras/layers/recurrent.py#L2081

It mentions tanh here for version 2.3.0 :-)

answered Jan 31 '20 at 09:03

Raghav

11
1

Default activation function in Keras

2 Answers2