Re:Intel Introduces Neuromorphic Test Chip
by 0xbear on Monday September 25, 2017 @09:49PM
(#15335570)
>> MNIST is a dataset, VGG is a software model
Strictly speaking, true. But one discovers early enough that you can screw up a number of things when training a model on something as simple as MNIST and the model will still work, because there's so much redundancy, the correct layers will just train their way around the ones that don't really work.
VGG trained for general purpose image classification with a decent sized input is a much better indicator of whether or not some ML hardware improvement is useful.
Re:Intel Introduces Neuromorphic Test Chip
by p1esk on Monday September 25, 2017 @10:01PM
(#15335614)
You're contradicting yourself. If you're afraid that redundancy will hide hardware problems, then VGG is a bad choice, because it's pretty much the most redundant NN model ever :)
Strictly speaking, true. But one discovers early enough that you can screw up a number of things when training a model on something as simple as MNIST and the model will still work, because there's so much redundancy, the correct layers will just train their way around the ones that don't really work.
VGG trained for general purpose image classification with a decent sized input is a much better indicator of whether or not some ML hardware improvement is useful.