hi cs faculty and graduate students, geoff hinton from U of T is speaking tomorrow at 11am in the small auditorium. geoff is one of the founders of modern machine learning and artificial intelligence. (and, he's an incredibly witty and engaging speaker.) see the full announcement below. best dave ---------- Forwarded message ---------- From: David Mimno < mimno@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@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)