Reproducibility issue

Open tlikhomanenko opened this issue 10 years ago • 2 comments

All of neural nets (pybrain, neurolab, theanets) have problems with reproducibility:

pybrain https://github.com/pybrain/pybrain/issues/170
neurolab https://github.com/zueve/neurolab/issues/26
theanets https://github.com/lmjohns3/downhill/issues/3

Meanwhile there are some dirty hacks with changing global seed, which is awful. (And they don't work for pyBrain, so things there are totally irreproducible)

Jun 30 '15 16:06 tlikhomanenko

there is one more problem, which is common for all NNs - they aren't supporting weights, but in theanets this will be probably resolved.

Jul 02 '15 14:07 arogozhnikov

In theanets reproducibility issue is fixed in 0.7.3 by adding rng during Downhill.Dataset creating https://github.com/lmjohns3/theanets/blob/v0.7/theanets/graph.py#L327 and this fix https://github.com/lmjohns3/theanets/commit/94662f50800b5815c2ff97ab38b5488732eb9045.

This is shown in https://github.com/lmjohns3/theanets/issues/102.

Jul 18 '16 20:07 tlikhomanenko