A crop of new papers submitted to ICLR 2015: arxiv.org/abs/1412.6651 Deep learning with Elastic Averaging SGD by Sixin Zhang, Anna Choromanska, Yann LeCun: a way to distribute the training of deep nets over multiple GPUs by linking the parameter vectors of the workers with elastics. arxiv.org/abs/1412.7022 Audio Source Separation with Discriminative Scattering Networks Pablo Sprechmann, Joan Bruna, Yann LeCun: audio source separation using convnets operating on coefficients of a scattering transform of the signal. arxiv.org/abs/1412.6056 Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun: training sparse auto-convolutional auto-encoders so that the pooled features change minimally between successive video frames. Beautiful filters come out of it. arxiv.org/abs/1412.6615 Explorations on high dimensional landscapes Levent Sagun, V. Ugur Guney, Yann LeCun: another take on the application of random matrix theory to the geometry of the loss surface in deep nets. We use a teacher network and a student network scenario to see if SGD manages to find a zero-energy global minimum that we know exists. Bottom line: SGD cant find it, but it doesnt matter because the (local) minima that it finds are equally good as far as test error is concerned.
Posted on: Tue, 23 Dec 2014 23:17:42 +0000
Trending Topics
Recently Viewed Topics
© 2015