bias update - Githubissues

DimitriF commented 8 years ago

A few changes:

the option use_bias in trainr trigger the use of a bias for network calculation
during the network crossing, I went step by step: weight multiplication, eventually bias addition, unit activation (last one is the sigmoid/logistic/stuff)
if use_bias == T, a new object in the output list is added: bias_synapse
in predictr, if bias_synapse in the list, the bias is added during network crossing

I didn't care about efficiency and calculate the bias anyway, I just take them into account or not during network crossing, I don't think there is a bottleneck here.

the RNG changed because of bias generation so I add a seed in the test_rnn.R and change the result (I needed it to check that the use_bias = F wasn't messing around compare to the last version)

coveralls commented 8 years ago

Coverage decreased (-1.2%) to 87.047% when pulling e7ffc91683c132e4baf562eb6e356f7c506d557e on DimitriF:master into fd06501dd3b830274797d3f0d910bbab4c39df86 on bquast:sigmoid.

bquast commented 8 years ago

perfect, again i'm going to have read this in more detail later, but the fact that it passes the test should say enough.

at some point in the future I will add some more tests just to be sure

bquast / rnn

bias update #5