News for hackers. Stuff that matters.
Re:MNIST Handwritten Digit Classifier – beginner neural netw... by IshKebab on Sunday July 31, 2016 @05:14PM (#12198900)
I kind of with people would stop using MNIST for NN tutorials. There are a billion of them already. Do something different.
Re:MNIST Handwritten Digit Classifier – beginner neural netw... by orthoganol on Monday August 01, 2016 @05:29AM (#12201095)
Neural nets even have their own "universality theorem", meaning any function at all, any sort of process out there in the world, anything, could in theory be approximated by a neural net. Yet everyone just does MNIST :)
Re:MNIST Handwritten Digit Classifier – beginner neural netw... by detaro on Sunday July 31, 2016 @05:35PM (#12198998)
Suggestions for other interesting starter projects? Doing something with NN is on the learning list...
Re:MNIST Handwritten Digit Classifier – beginner neural netw... by IshKebab on Monday August 01, 2016 @05:12AM (#12201040)
The difficulty is always getting a dataset.

I've started trying to get a network to recognise different vowels ("aaahhhhhh", "eeeeee", "ooooooo", etc.). Relatively easy to generate data - you just need your voice and a microphone. Downside is all the NN systems are much more set up for images than sound.

Or what about neural net fingerprint recognition. There must be databases of fingerprints somewhere. Or irises.

Recognise a type of wood from images of its grain?

Or activity recognition from accelerometer data. I think Pebble recently open sourced their recogniser and it was surprisingly not a neural network. I'm sure a neural network could do better. Might be hard to get a decent amount of data here but this could be a good incentive to do exercise!