Clear Filters
Clear Filters

Trainscg works in R2014b but not in R2015b and R2016a

1 view (last 30 days)
I have been working on the MNIST digit recognition problem and was using "Trainscg" to train my networks. I can get around 90% and maybe 400 epochs in R2014b. When I came back from vacation my Matlab was updated to 2016a and the exact same code now gets 20% accuracy and meets the gradient target in 9 epochs. I unistalled the updates, but want to know WHY this happened so I can fix the problem. Thanks!

Answers (1)

Luigi Faustini
Luigi Faustini on 26 Jan 2018
Did they ever help you? I ran in to a similar issue where (Matlab2017) I was training a net with trainlm and getting excellent results, then I switched over to trainscg (because I had to -- I waned to use a GPU to speed things up) and the results were very poor, errors went from .003 (typical) to .9 I tried tweaking all of the parameters, with no improvements. It seems like either trainscg is just a crappy algorithm -- or it is broken.
  1 Comment
circuit_designer5172
circuit_designer5172 on 26 Jan 2018
I never heard back. Your experience is similar to mine. I moved off of Matlab to python/theano/TF for my ML work.

Sign in to comment.

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!