A Beginner's Guide to Understanding Convolutional Neural Networks

Re:A Beginner's Guide to Understanding Convolutional Neural ... by dbecker on Thursday July 21, 2016 @08:48AM (#12136451)

I've seen many examples where networks are trained on thousands or tens of thousands.

The most common example is digit recognition with the MNIST dataset. This is a common problem given to beginners, and even many beginners to CNN's achieve human-level accuracy. That dataset is in the tens of thousands.

there should be a push towards adapting CNNs to calculate/predict how the object might look under different conditions

Data augmentation like rotations, horizontal flipping and random cropping are a widespread practice.

[ Parent | on HN ]

Re:A Beginner's Guide to Understanding Convolutional Neural ... by cynicaldevil on Thursday July 21, 2016 @08:53AM (#12136481)

I see. Could you link some articles about these techniques?

[ Parent | on HN ]

Re:A Beginner's Guide to Understanding Convolutional Neural ... by dbecker on Thursday July 21, 2016 @11:16PM (#12141511)

I don't have great links for this, but for something less technical, you might look at the blog posts from Kaggle competition winners. Here are a couple examples

http://benanne.github.io/2015/03/17/plankton.html http://blog.kaggle.com/2016/04/13/diagnosing-heart-diseases-...

or check out what's available in a deep learning library like keras http://keras.io/preprocessing/image/

Sorry I don't have better academic references.

[ Parent | on HN ]