I am trying to model some deep networks which I have already modelled with Keras (the usual way) and now I wish to see what would happen in the Bayesian context. Suppose the model I have is as the following: x_in = Input(shape=(X_train.shape[1:])) h = Dense(10, use_bias=False)(x_in) out = Activati…

PyMC3 with Keras

junpenglao March 13, 2018, 11:06pm 5

Not necessary - depending on how you do the inference.

Topic		Replies	Views
Help Converting Keras Model to PYMC3 syntax Questions	4	1147	February 20, 2019
Deep Neural Network Question Questions	4	1111	February 25, 2019
Predicting Bayesion NN does not work with variational api Questions	0	550	April 23, 2019
Theano (lasagna) neural network not improved (learn at all) Questions theano	3	679	August 23, 2020
Binary neural network training Questions	5	1238	June 8, 2018