Today I Learned This Part 2: Pretrained Neural Networks What are they?

Deeplearning is the buzz word right now. I was working on the course for deep learning by Jeremy Howard and one thing I noticed were pretrained deep Neural Networks. In the first lesson he used the pretrained NN to predict on the Dogs vs Cats competition on Kaggle to achieve very good results.

What are pretrained Neural Networks?

So let me tell you about the background a little bit. There is a challenge that happens every year in the visual recognition community - The Imagenet Challenge. The task there is to classify the images in 1000 categories using Image training data. People train big convolutional deep learning models for this challenge.

Now what does training a neural model actually mean? It just means that they learn the weights for a NN. What if we can get the weights they learn? We can use those weights to load them into our own NN model and predict on the test dataset. Right?

But actually we can go further than that. We can add an extra layer on top of the NN they have prepared…