0

I was implementing some sample Neural networks and in most tutorials saw this statement.

Neural networks tend to work better on GPUs than on CPU. The scikit-learn framework isn’t built for GPU optimization.

So does this statement (work better) refers solely regarding the train phase of a neural network or it includes the prediction part also. Would greatly appreciate some explanation on this.

DavidG
  • 24,279
  • 14
  • 89
  • 82
Nirojan Selvanathan
  • 10,066
  • 5
  • 61
  • 82
  • 2
    This only talks about performance/speed and includes prediction, although the difference is usually smaller and as always it's dependent on a lot of parameters (single-pred vs. batch-pred; NN size and co). – sascha Aug 31 '17 at 01:07

1 Answers1

1

That statement refers to the training phase. The only issue here is that you can explore the search space of feasible models in a more efficient way using a GPU so you will probably find better models in less time. However, this is only related to computational costs and not to model predictive performance.

kelwinfc
  • 3,101
  • 2
  • 14
  • 10