Sciweavers

Share
ICANN
2010
Springer
9 years 3 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
ICANN
2010
Springer
9 years 3 months ago
A Learned Saliency Predictor for Dynamic Natural Scenes
Abstract. We investigate the extent to which eye movements in natural dynamic scenes can be predicted with a simple model of bottom-up saliency, which learns on different visual re...
Eleonora Vig, Michael Dorr, Thomas Martinetz, Erha...
ICANN
2010
Springer
9 years 3 months ago
Assessing Statistical Reliability of LiNGAM via Multiscale Bootstrap
Structural equation models have been widely used to study causal relationships between continuous variables. Recently, a non-Gaussian method called LiNGAM was proposed to discover ...
Yusuke Komatsu, Shohei Shimizu, Hidetoshi Shimodai...
ICANN
2010
Springer
9 years 3 months ago
Model of the Hippocampal Learning of Spatio-temporal Sequences
We propose a model of the hippocampus aimed at learning the timed association between subsequent sensory events. The properties of the neural network allow it to learn and predict ...
Julien Hirel, Philippe Gaussier, Mathias Quoy
ICANN
2010
Springer
9 years 3 months ago
Classification Based on Multiple-Resolution Data View
Abstract. We examine efficacy of a classifier based on average of kernel density estimators; each estimator corresponds to a different data "resolution". Parameters of th...
Mateusz Kobos, Jacek Mandziuk
ICANN
2010
Springer
9 years 3 months ago
A Bilinear Model for Consistent Topographic Representations
Visual recognition faces the difficult problem of recognizing objects despite the multitude of their appearances. Ample neuroscientific evidence shows that the cortex uses a topogr...
Urs Bergmann, Christoph von der Malsburg
ICANN
2010
Springer
9 years 3 months ago
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...
Dominik Scherer, Andreas Müller, Sven Behnke
ICANN
2010
Springer
9 years 3 months ago
Policy Gradients for Cryptanalysis
So-called Physical Unclonable Functions are an emerging, new cryptographic and security primitive. They can potentially replace secret binary keys in vulnerable hardware systems an...
Frank Sehnke, Christian Osendorfer, Jan Sölte...
ICANN
2010
Springer
9 years 3 months ago
Accelerating Large-Scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
Training convolutional neural networks (CNNs) on large sets of high-resolution images is too computationally intense to be performed on commodity CPUs. Such architectures however ...
Dominik Scherer, Hannes Schulz, Sven Behnke
books