Oldest Papers
DNA barcoding survey of Trichoderma diversity in soil and litter of the Colombian lowland Amazonian rainforest reveals Trichoderma strigosellum sp. nov. and other species
Carlos A. López-Quintero, Lea Atanasova, A. Esperanza Franco-Molano, Walter Gams, Monika Komon-Zelazowska, Bart Theelen, Wally H. Müller, Teun Boekhout, Irina Druzhinina
Antonie van Leeuwenhoek·2013·32 citations
No abstract available
No ratings yet
View paper →Beyond race: constructions of ‘Europeanness’ in late-colonial legal practice in the Dutch East Indies
Bart Luttikhuis
European Review of History: Revue europeenne d'histoire·2013·13 citations
No abstract available
No ratings yet
View paper →Potentiating empathic growth: Generating imagery while reading fiction increases empathy and prosocial behavior.
Dan R. Johnson, Grace K. Cushman, Lauren A. Borden, Madison S. McCune
Psychology of Aesthetics, Creativity, and the Arts·2013·68 citations
No abstract available
No ratings yet
View paper →Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?
N. Kruger, P. Janssen, S. Kalkan, M. Lappe, A. Leonardis, J. Piater, A. J. Rodriguez-Sanchez, L. Wiskott
IEEE Transactions on Pattern Analysis and Machine Intelligence·2013·303 citations
No abstract available
No ratings yet
View paper →Deep social mind - Wikipedia
Unknown Author
en.wikipedia.org·2013
No abstract available
No ratings yet
View paper →Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Yoshua Bengio, Nicholas Léonard, Aaron Courville
arXiv·2013
Stochastic neurons and hard non-linearities can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such stochastic or non-smooth neurons? I.e., can we "back-propagate" through these stochastic neurons? We examine this question, existing approaches, and compare four families of solutions, applicable in different settings. One of them is the minimum variance unbiased gradient estimator for stochatic binary neurons (a special case of the REINFORCE algorithm). A second approach, introduced here, decomposes the operation of a binary stochastic neuron into a stochastic binary part and a smooth differentiable part, which approximates the expected effect of the pure stochatic binary neuron to first order. A third approach involves the injection of additive or multiplicative noise in a computational graph that is otherwise differentiable. A fourth approach heuristically copies the gradient with respect to the stochastic output directly as an estimator of the gradient with respect to the sigmoid argument (we call this the straight-through estimator). To explore a context where these estimators are useful, we consider a small-scale version of {\em conditional computation}, where sparse stochastic units form a distributed representation of gaters that can turn off in combinatorially many ways large chunks of the computation performed in the rest of the neural network. In this case, it is important that the gating units produce an actual 0 most of the time. The resulting sparsity can be potentially be exploited to greatly reduce the computational cost of large deep networks for which conditional computation would be useful.
No ratings yet
View paper →