Bernhard, Rémi, Moellic, Pierre-Alain, Dutertre, Jean-Max

As the will to deploy neural networks models on embedded systems grows, and considering the related memory footprint and energy consumption issues, finding lighter solutions to store neural networks such as weight quantization and more efficient inference methods become major research topics. Parallel to that, adversarial machine learning has risen recently with an impressive and significant attention, unveiling some critical flaws of machine learning models, especially neural networks. In particular, perturbed inputs called adversarial examples have been shown to fool a model into making incorrect predictions. In this article, we investigate the adversarial robustness of quantized neural networks under different threat models for a classical supervised image classification task. We show that quantization does not offer any robust protection, results in severe form of gradient masking and advance some hypotheses to explain it. However, we experimentally observe poor transferability capacities which we explain by quantization value shift phenomenon and gradient misalignment and explore how these results can be exploited with an ensemble-based defense.

McCarter, Calvin, Kim, Seyoung

In this paper, we address the problem of learning the structure of Gaussian chain graph models in a high-dimensional space. Chain graph models are generalizations of undirected and directed graphical models that contain a mixed set of directed and undirected edges. While the problem of sparse structure learning has been studied extensively for Gaussian graphical models and more recently for conditional Gaussian graphical models (CGGMs), there has been little previous work on the structure recovery of Gaussian chain graph models. We consider linear regression models and a re-parameterization of the linear regression models using CGGMs as building blocks of chain graph models. We argue that when the goal is to recover model structures, there are many advantages of using CGGMs as chain component models over linear regression models, including convexity of the optimization problem, computational efficiency, recovery of structured sparsity, and ability to leverage the model structure for semi-supervised learning.

Essay on the Application of Analysis to the Probability of Majority Decisions https://en.wikipedia.org/wiki/Condorcet%27s_jury_theorem 4. Condorcet's Jury Theorm Principle: If we assume each voter probability of making a good decision is better than random (i.e., 0.50), then the probability of a good decision increases with each voter added. He showed the converse was also true. If we assume each voter probability of making a good decision is less than random (i.e., 0.50), then the probability of a good decision decreases with each voter added. Example Even if the probability is slightly more than random (e.g., 0.51), the principle holds true.

That post drew quite a number of email requests for more information about the Almon estimator, and how it fits into the overall scheme of things. In addition, Almon's approach to modelling distributed lags has been used very effectively more recently in the estimation of the so-called MIDAS model. The MIDAS model (developed by Eric Ghysels and his colleagues – e.g., see Ghysels et al., 2004) is designed to handle regression analysis using data with different observation frequencies. The acronym, "MIDAS", stands for "Mixed-Data Sampling". The MIDAS model can be implemented in R, for instance (e.g., see here), as well as in EViews.

Updated September 6, 2017 to reflect the latest iPad models. You might think you know which iPad you have. But when you need to know exactly which model you have, or better yet, which generation, it can get a little trickier. You don't have to be an Apple Store Genius to figure it out, though you do have to know where to look... and what to look for. In addition to the marketing names that we all know so well, all iPads have a model number.