Aalto University

About: Aalto University is a education organization based out in Espoo, Finland. It is known for research contribution in the topics: Computer science & Context (language use). The organization has 9969 authors who have published 32648 publications receiving 829626 citations. The organization is also known as: TKK & Aalto-korkeakoulu.

Deep Learning Made Easier by Linear Transformations in Perceptrons

Abstract: We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. This transformation aims at separating the problems of learning the linear and nonlinear parts of the whole input-output mapping, which has many benefits. We study the theoretical properties of the transformation by noting that they make the Fisher information matrix closer to a diagonal matrix, and thus standard gradient closer to the natural gradient. We experimentally confirm the usefulness of the transformations by noting that they make basic stochastic gradient learning competitive with state-of-the-art learning algorithms in speed, and that they seem also to help find solutions that generalize better. The experiments include both classification of small images and learning a lowdimensional representation for images by using a deep unsupervised auto-encoder network. The transformations were beneficial in all cases, with and without regularization and with networks from two to five hidden layers.

Quantifying Controversy in Social Media

Abstract: Which topics spark the most heated debates on social media? Identifying those topics is not only interesting from a societal point of view, but also allows the filtering and aggregation of social media content for disseminating news stories. In this paper, we perform a systematic methodological study of controversy detection by using the content and the network structure of social media. Unlike previous work, rather than study controversy in a single hand-picked topic and use domain specific knowledge, we take a general approach to study topics in any domain. Our approach to quantifying controversy is based on a graph-based three-stage pipeline, which involves (i) building a conversation graph about a topic; (ii) partitioning the conversation graph to identify potential sides of the controversy; and (iii) measuring the amount of controversy from characteristics of the graph. We perform an extensive comparison of controversy measures, different graph-building approaches, and data sources. We use both controversial and non-controversial topics on Twitter, as well as other external datasets. We find that our new random-walk-based measure outperforms existing ones in capturing the intuitive notion of controversy, and show that content features are vastly less helpful in this task.

Planck early results - XI. Calibration of the local galaxy cluster Sunyaev-Zeldovich scaling relations

Abstract: We present precise Sunyaev-Zeldovich (SZ) effect measurements in the direction of 62 nearby galaxy clusters (z < 0.5) detected at high signal-tonoise in the first Planck all-sky data set. The sample spans approximately a decade in total mass, 2 × 10 14 M� < M500 < 2 × 10 15 M� ,w hereM500 is the mass corresponding to a total density contrast of 500. Combining these high quality Planck measurements with deep XMM-Newton X-ray data, we investigate the relations between D 2 Y500, the integrated Compton parameter due to the SZ effect, and the X-ray-derived gas mass Mg,500, temperature TX, luminosity LX,500, SZ signal analogue YX,500 = Mg,500 ×TX, and total mass M500. After correction for the effect of selection bias on the scaling relations, we find results that are in excellent agreement with both X-ray predictions and recently-published ground-based data derived from smaller samples. The present data yield an exceptionally robust, high-quality local reference, and illustrate Planck’s unique capabilities for all-sky statistical studies of galaxy clusters.

Private Information Retrieval From MDS Coded Data in Distributed Storage Systems

Abstract: The problem of providing privacy, in the private information retrieval (PIR) sense, to users requesting data from a distributed storage system (DSS), is considered. The DSS is coded by an $(n,k,d)$ maximum distance separable code to store the data reliably on unreliable storage nodes. Some of these nodes can be spies which report to a third party, such as an oppressive regime, which data is being requested by the user. An information theoretic PIR scheme ensures that a user can satisfy its request while revealing no information on which data is being requested to the nodes. A user can trivially achieve PIR by downloading all the data in the DSS. However, this is not a feasible solution due to its high communication cost. We construct PIR schemes with low download communication cost. When there is $b=1$ spy node in the DSS, in other words, no collusion between the nodes, we construct PIR schemes with download cost $\frac {1}{1-R}$ per unit of requested data ( $R=k/n$ is the code rate), achieving the information theoretic limit for linear schemes. The proposed schemes are universal since they depend on the code rate, but not on the generator matrix of the code. Also, if $b\leq n-\delta k$ nodes collude, with $\delta =\lfloor {\frac {n-b}{k}}\rfloor $ , we construct linear PIR schemes with download cost $\frac {b+\delta k}{\delta }$ .