Fetching the paper…

Reading the bibliography…

2015

Geodesics of learned representations

Hénaff, Olivier J., Simoncelli, Eero P.

Original
PDF
Post on X

Understand

We develop a new method for visualizing and refining the invariances of learned representations.

Specifically, we test for a general form of invariance, linearization, in which the action of a transformation is confined to a low-dimensional subspace.
Given two reference images (typically, differing by some transformation), we synthesize a sequence of images lying on a path between them that is of minimal length in the space of the representation (a "representational geodesic").
If the transformation relating the two reference images is linearized by the representation, this sequence should follow the gradual evolution of this transformation.

Geodesics of learned representations · Around

Built on

A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Portilla, Javier and Simoncelli, Eero P · 2000
Earlier work this paper cites.
Pattern classification
Duda, R., Hart, P., and Stork, D · 2001
Earlier work this paper cites.
Untangling invariant object recognition
DiCarlo, James J and Cox, David D · 2007
Earlier work this paper cites.
Learning invariant features through topographic filter maps
Kavukcuoglu, Koray, Ranzato, Marc’Aurelio, Fergus, Rob, and LeCun, Yann · 2009
Earlier work this paper cites.

Similar

Group Invariant Scattering
Mallat, Stéphane · 2011
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoff · 2012
Cited alongside, same era.
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
Saxe, Andrew M, McClelland, James L, and Ganguli, Surya · 2013
Cited alongside, same era.
Intriguing properties of neural networks
Szegedy, Christian, Zaremba, Wojciech, Sutskever, Ilya, Bruna, Joan, Erhan, Dumitru, Goodfellow, Ian, and Fergus, Rob · 2013
Cited alongside, same era.

Then

Adam: A Method for Stochastic Optimization
Kingma, Diederik and Ba, Jimmy · 2014
Later among the works it cites.
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, Karen and Zisserman, Andrew · 2014
Later among the works it cites.
A convolutional subunit model for neuronal responses in macaque V1
Original
Vintch, B, Movshon, J A, and Simoncelli, Eero P · 2015
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…