AI News, advanced topics in artificial intelligence
- On Saturday, July 13, 2019
- By Read More
Advanced Topics in Deep Convolutional Neural Networks
However, we know that companies such as Google and Microsoft have dedicated teams of data scientists that have spent years developing exceptional networks for the purpose of image classification — why not just use these networks as a starting point for your own image classification projects?
Obviously, just purely transferring the model will not be helpful, you must still train the network on your new data, but it is common to freeze the weights of the former layers as these are more generalized features that will likely be unchanged during training.
Transfer learning works best for problems that are fairly general and there are networks freely available online (such as image analysis) and when the user has a relatively small dataset available such that it is insufficient to train a neural network — this is a fairly common problem.