News for hackers. Stuff that matters.
Re:TensorFlow Implementation of Deep Convolutional Generativ... by argonaut on Wednesday March 23, 2016 @03:17AM (#11342661)
I understand that it's difficult for people not experienced with machine learning to tell what problems are actually suited for what models, but using deep learning / Tensorflow for this is like using Hadoop to sort a 10 megabyte file of numbers. Or writing a new Ruby on Rails app and deploying to AWS in order to create a survey for a class project.

Plain ol' statistics, plotting, and some hand rolled features (this is bascially "data science") is probably the best fit for this problem, especially since it doesn't seem to me like this would be a massive dataset.

Re:TensorFlow Implementation of Deep Convolutional Generativ... by ska on Wednesday March 23, 2016 @10:04AM (#11344505)
This is the big problem when an technique breaks through to name recognition in mass media. The last big one was SVM/kernel methods but it wasn't this bad. Now we have lots of people running around wanting to hit things with the "Deep Learning" hammer, with no real idea where it is appropriate (or worse, offering to do it for your company without much better understanding)
Re:TensorFlow Implementation of Deep Convolutional Generativ... by anewhnaccount on Wednesday March 23, 2016 @03:58AM (#11342775)
Arguably those things might still be a useful way for one to make their first forays into Hadoop or Ruby on Rails.