Settings

Theme

Theoretical Motivations for Deep Learning

rinuboney.github.io

93 points by rndn 10 years ago · 12 comments

Reader

chriskanan 10 years ago

There is a recent 5 page theoretical paper on this topic that I thought was pretty interesting, and it tackles both deep nets and recurrent nets: http://arxiv.org/abs/1509.08101

Here is the abstract:

This note provides a family of classification problems, indexed by a positive integer k, where all shallow networks with fewer than exponentially (in k) many nodes exhibit error at least 1/6, whereas a deep network with 2 nodes in each of 2k layers achieves zero error, as does a recurrent network with 3 distinct nodes iterated k times. The proof is elementary, and the networks are standard feedforward networks with ReLU (Rectified Linear Unit) nonlinearities.

arcanus 10 years ago

1) I am curious about learning more about the statement: "Deep learning is a branch of machine learning algorithms based on learning multiple levels of representation. The multiple levels of representation corresponds to multiple levels of abstraction. "

What evidence exists that the 'multiple levels of representation', which I understand to generally be multiple hidden layers of a neural network, actually correspond to 'levels of abstraction'?

2) I'm further confused by, "Deep learning is a kind of representation learning in which there are multiple levels of features. These features are automatically discovered and they are composed together in the various levels to produce the output. Each level represents abstract features that are discovered from the features represented in the previous level. "

This implies to me that this is "unsupervised learning". Are deep learning nets all unsupervised? Most traditional neural nets are supervised.

dnautics 10 years ago

I wonder if "lots of data" is wrong. If I show you say twenty similar-looking Chinese characters in one person's handwriting, and the same twenty in another person's handwriting, you'll probably do a good job (though maybe not an easy time) classifying them with very little data.

  • webmasterraj 10 years ago

    Because I've seen lots of other handwriting, even if in another language. I have very strong priors.

    The problem is that a computer comes in without knowing anything about tangential phenomenon. So it needs lots of data to catch up to me and my years of forming associative connections about other handwriting I've seen.

    If I showed you alien (ie not human) handwritten samples, you'd probably stuggle too.

  • p1esk 10 years ago

    "you'll probably do a good job classifying them with very little data."

    It's because we use much better algorithms in our brains (compared to the ones we currently have in DL). Having "lots of data" allows us to get good results even while using inferior algorithms.

  • Houshalter 10 years ago

    A baby who's never seen an image before wouldn't be able to do that. It wouldn't even know what writing is.

ilurk 10 years ago

What tools did you use to make those nice pictures?

(didn't read it yet though, will do when I have time)

memming 10 years ago

Nice. Very well organized.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection