Search

Contains fulltext : 166770.pdf (Publisher’s version ) (Open Access) We developed task-optimized deep neural networks (DNNs) that achieved state-of-the-art performance in different evaluation scenarios for automatic music tagging. These DNNs were subsequently used to probe the neural representations of music. Representational similarity analysis revealed the existence of a representational gradient across the superior temporal gyrus (STG). Anterior STG was shown to be more sensitive to low-level stimulus features encoded in shallow DNN layers whereas posterior STG was shown to be more sensitive to high-level stimulus features encoded in deep DNN layers. 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 5 - 10, 2016, 05 december 2016

Contains fulltext : 72243.pdf (Author’s version preprint ) (Open Access) NIPS 2007 : twenty-first annual conference on Neural Information Processing Systems (NIPS), held in British Columbia, Canada from December 3rd through 6th, 2007, 03 december 2007

Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions. Several approaches to improve the reliability of the predictions by exploiting redundancy in the independence information have been proposed recently. Though promising, existing approaches can still be greatly improved in terms of accuracy and scalability. We present a novel method that reduces the combinatorial explosion of the search space by using a more coarse-grained representation of causal information, drastically reducing computation time. Additionally, we propose a method to score causal predictions based on their confidence. Crucially, our implementation also allows one to easily combine observational and interventional data and to incorporate various types of available background knowledge. We prove soundness and asymptotic consistency of our method and demonstrate that it can outperform the state-of-the-art on synthetic data, achieving a speedup of several orders of magnitude. We illustrate its practical feasibility by applying it on a challenging protein data set., Comment: In Proceedings of Advances in Neural Information Processing Systems 29 (NIPS 2016)

Contains fulltext : 83472.pdf (Author’s version preprint ) (Open Access)

Contains fulltext : 112694.pdf (Author’s version preprint ) (Open Access)

Item does not contain fulltext Advances in Neural Information Processing Systems, (NIPS) 2001

Contains fulltext : 112682.pdf (Author’s version preprint ) (Open Access) We present a method to bound the partition function of a Boltzmann machine neural network with any odd-order polynomial. This is a direct extension of the mean-field bound, which is first order. We show that the third-order bound is strictly better than mean field. Additionally, we derive a third-order bound for the likelihood of sigmoid belief networks. Numerical experiments indicate that an error reduction of a factor of two is easily reached in the region where expansion-based approximations are useful.