Book chapter
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. We demonstrate that perforation can accelerate modern convolutional networks such as AlexNet and VGG-16 by a factor of 2x - 4x. Additionally, we show that perforation is complementary to the recently proposed acceleration method of Zhang et al.
In book
This paper is an overview of the current issues and tendencies in Computational linguistics. The overview is based on the materials of the conference on computational linguistics COLING’2012. The modern approaches to the traditional NLP domains such as pos-tagging, syntactic parsing, machine translation are discussed. The highlights of automated information extraction, such as fact extraction, opinion mining are also in focus. The main tendency of modern technologies in Computational linguistics is to accumulate the higher level of linguistic analysis (discourse analysis, cognitive modeling) in the models and to combine machine learning technologies with the algorithmic methods on the basis of deep expert linguistic knowledge.
The paper makes a brief introduction into multiple classifier systems and describes a particular algorithm which improves classification accuracy by making a recommendation of an algorithm to an object. This recommendation is done under a hypothesis that a classifier is likely to predict the label of the object correctly if it has correctly classified its neighbors. The process of assigning a classifier to each object involves here the apparatus of Formal Concept Analysis. We explain the principle of the algorithm on a toy example and describe experiments with real-world datasets.
The paper deals with the problems of creating and tuning a system of automated anaphora resolution for Russian. Such a system is introduced, combining rule-based and machine learning approaches. It shows F-measure from 0.51 to 0.59. Freeling serves as an underlying morphological layer and an account of its quality is given, with its influence on anaphora resolution workflow. The anaphora resolution system itself is available to download and use, coming with online demo.
The volume contains the abstracts of the 12th International Conference "Intelligent Data Processing: Theory and Applications". The conference is organized by the Russian Academy of Sciences, the Federal Research Center "Informatics and Control" of the Russian Academy of Sciences and the Scientific and Coordination Center "Digital Methods of Data Mining". The conference has being held biennially since 1989. It is one of the most recognizable scientific forums on data mining, machine learning, pattern recognition, image analysis, signal processing, and discrete analysis. The Organizing Committee of IDP-2018 is grateful to Forecsys Co. and CFRS Co. for providing assistance in the conference preparation and execution. The conference is funded by RFBR, grant 18-07-20075. The conference website http://mmro.ru/en/.
In an effort to make reading more accessible, an automated readability formula can help students to retrieve appropriate material for their language level. This study attempts to discover and analyze a set of possible features that can be used for single-sentence readability prediction in Russian. We test the influence of syntactic features on predictability of structural complexity. The readability of sentences from SynTagRus corpus was marked up manually and used for evaluation.
We present a universal method for algorithmic trading in Stock Market which performs asymptotically at least as well as any stationary trading strategy that computes the investment at each step using continuous function of the side information. In the process of the game, a trader makes decisions using predictions computed by a randomized well-calibrated algorithm. We use Dawid's notion of calibration with more general checking rules and some modication of Kakade and Foster's randomized rounding algorithm for computing the well-calibrated forecasts. The method of randomized calibration is combined with Vovk's method of defensive forecasting in RKHS. Unlike in statistical theory, no stochastic assumptions are made about the stock prices.