[Ml-stat-talks] Fwd: Monday, 11AM: Geoff Hinton on neural networks

John C. Valentino jcvalent at princeton.edu
Sun May 15 23:04:51 EDT 2011

I am going to try to leave a meeting early to be there - but only because of
all of these Bach references ... my expectations have been maximized.

On Sun, May 15, 2011 at 9:47 PM, David Blei <blei at cs.princeton.edu> wrote:

> hi ml-stat-talks
> david's comparison to bach is fitting.  do not miss geoff hinton's talk
> tomorrow.  note the unusual time, 11am.  the talk is in CS 105 (also known
> as the "small auditorium").
> best
> dave
> ---------- Forwarded message ----------
> From: David Mimno <mimno at cs.princeton.edu>
> Date: Thu, May 12, 2011 at 2:57 PM
> Subject: [Ml-stat-talks] Monday, 11AM: Geoff Hinton on neural networks
> To: ml-stat-talks <ml-stat-talks at lists.cs.princeton.edu>
> For those not familiar with his work: "Geoffrey Hinton talks about neural
> networks" is roughly equivalent to "J.S. Bach talks about fugues".
> This is not to be missed. Drag your friends.
> Geoff's schedule is filling up, but if you would like to meet with him
> before the talk or in the afternoon, please let me know.
> Monday, May 16, 11AM (note the change), CS105
> =============================
> How to force unsupervised neural networks to discover
> the right representation of images
> Geoffrey Hinton
> University of Toronto
> One appealing way to design an object recognition system is to define
> objects recursively in terms of their parts and the required spatial
> relationships between the parts and the whole. These relationships can
> be represented by the coordinate transformation between an intrinsic
> frame of reference embedded in the part and an intrinsic frame
> embedded in the whole. This transformation is unaffected by the
> viewpoint so this form of knowledge about the shape of an object is
> viewpoint invariant. A natural way for a neural network to implement
> this knowledge is by using a matrix of weights to represent each
> part-whole relationship and a vector of neural activities to represent
> the pose of each part or whole relative to the viewer. The pose of the
> whole can then be predicted from the poses of the parts and, if the
> predictions agree, the whole is present. This leads to neural networks
> that can recognize objects over a wide range of viewpoints using
> neural activities that are ``equivariant'' rather than invariant: as
> the viewpoint varies the neural activities all vary even though the
> knowledge is viewpoint-invariant. The ``capsules'' that implement the
> lowest-level parts in the shape hierarchy need to extract explicit
> pose parameters from pixel intensities and these pose parameters need
> to have the right form to allow coordinate transformations to be
> implemented by matrix multiplies. These capsules are quite easy to
> learn from pairs of transformed images if the neural net has direct,
> non-visual access to the transformations, as it would if it controlled
> them.  (Joint work with Sida Wang and Alex Krizhevsky)
> _______________________________________________
> Ml-stat-talks mailing list
> Ml-stat-talks at lists.cs.princeton.edu
> https://lists.cs.princeton.edu/mailman/listinfo/ml-stat-talks
> _______________________________________________
> Ml-stat-talks mailing list
> Ml-stat-talks at lists.cs.princeton.edu
> https://lists.cs.princeton.edu/mailman/listinfo/ml-stat-talks
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20110515/f3058de8/attachment.htm>

More information about the Ml-stat-talks mailing list