Neural Networks and TensorFlow - Deep Learning Series [Part 24]

in #deep-learning6 years ago

Once you have a trained model for your deep learning experiment, what do you do to improve its performance?

As I discuss in the video, there are a couple of tactics that one could implement. And I'll briefly mention some of them:

  • you could train the model for longer
  • you could do the training on better hardware
  • you could increase the size of the model
  • you could implement data augmentation procedures
  • you could focus a lot on preprocessing and optimization
  • etc.

For a breakdown on each of these, in more detail, please see the video lesson below.



To stay in touch with me, follow @cristi


Cristi Vlad Self-Experimenter and Author

Sort:  

Replay me and vote my blog please

Very nice.