[csense]

I've found that, in practice, traditional neural networks tend to be prone to overfitting and are finicky about their parameters (in particular the topology and number of nodes you choose).

I use the word "traditional" to describe the NN architecture discussed in the article. Recent NN research has been promising [1], but this article strictly discusses traditional NN's. I don't really have much experience with the newer NN algorithms, so I'm not sure to what extent they suffer from the same problems as traditional NN's.

[1] http://en.wikipedia.org/wiki/Neural_network#Recent_improveme...

[billderose]

Hinton's DropOut [1] and Wan's DropConnect [2] have ameliorated some of the overfitting issues present in traditional NN's. In fact, DropConnect in conjunction with deep learning are responsible for new records being set on classical datasets such as MNIST.

[1] http://arxiv.org/pdf/1207.0580.pdf [2] http://cs.nyu.edu/~wanli/dropc/

[agibsonccc]

Dropout is actually a knob on any neural network. These are used in image recognition as well as text and other areas.

The fuzzing creates a very similar effect to convolutional nets where it can learn different poses of an image.

[im3w1l]

It's pretty funny, I saw DropConnect described in a stackoverflow answer that predated the paper you reference. It was an incorrect answer on how to do dropout. I shall try to find it tomorrow.

[niels_olson]

Is it safe to say that in ML, use of NNs is more about writing code that designs NNs, evaluates the results, and modifies the designs to optimize some desired meta-values, like accuracy, efficiency, etc?