Fetching the paper…

Reading the bibliography…

2014

Self-informed neural network structure learning

Warde-Farley, David, Rabinovich, Andrew, Anguelov, Dragomir

Original
PDF
Post on X

Understand

We study the problem of large scale, multi-label visual recognition with a large number of possible classes.

We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its computational footprint.
Using the predictions of the network itself as a descriptor for assessing visual similarity, we define a partitioning of the label space into groups of visually similar entities.
We then augment the network with auxilliary hidden layer pathways with connectivity only to these groups of label units.

Self-informed neural network structure learning · Around

Built on

Adaptive mixtures of local experts
Jacobs, Robert A, Jordan, Michael I, Nowlan, Steven J, and Hinton, Geoffrey E · 1991
Earlier work this paper cites.
Spectral graph theory , volume 92
Chung, Fan RK · 1997
Earlier work this paper cites.
On spectral clustering: Analysis and an algorithm
Ng, Andrew Y, Jordan, Michael I, Weiss, Yair, et al · 2002
Earlier work this paper cites.
Model compression
Buciluǎ, Cristian, Caruana, Rich, and Niculescu-Mizil, Alexandru · 2006
Earlier work this paper cites.

Similar

Freebase: a collaboratively created graph database for structuring human knowledge
Bollacker, Kurt, Evans, Colin, Paritosh, Praveen, Sturge, Tim, and Taylor, Jamie · 2008
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E · 2012
Cited alongside, same era.
Deep learning of representations: Looking forward
Bengio, Yoshua · 2013
Cited alongside, same era.

Then

Distilling the knowledge in a neural network
Hinton, Geoffrey E., Vinyals, Oriol, and Dean, Jeff · 2014
Closest in time.
Overfeat: Integrated recognition, localization and detection using convolutional networks
Sermanet, Pierre, Eigen, David, Zhang, Xiang, Mathieu, Michael, Fergus, Rob, and LeCun, Yann · 2014
Closest in time.
Going Deeper with Convolutions
Original
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A · 2014
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…