Pre-trained - deep learning

machine_learning
deep_learning

#1

How can one improve a Pre-trained neural networks i.e AleNet to fit your domain/ to fit another domain/ transfer learning


#2

Hi @erigits,

The concept of transfer learning came into being when some researchers found that a deep neural network, after training on a particular recognition task (eg. Object Recognition ), can be applied on another domain (eg. Bird Subcategorization) giving state-of-the-art results. This idea has powerful implications, as a model can be pre-trained and then applied on the required problem.

You can use a pre-trained model in two ways:

  • As a feature extractor; Train model on a bigger data (possibly on a similar domain), use on on the required problem as on “off-the-shelf” model.
  • As a fined-tuned-network; Train model on a bigger data, then freeze the upper-layers (set the learning rate of the earlier layers to minimum) and retrain on the required problem.

PS: To read in depth about transfer learning, here’s a resource


#3

Thank @jalFaizy