Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Aerial Drop of Robots and Sensors for Optimal Area Coverage

Nov 28, 2017
Kostas Alexis

The problem of rapid optimal coverage through the distribution a team of robots or static sensors via means of aerial drop is the topic of this work. Considering a nonholonomic (fixed-wing) aerial robot that corresponds to the carrier of a set of small holonomic (rotorcraft) aerial robots as well as static modules that are all equipped with a camera sensor, we address the problem of selecting optimal aerial drop times and configurations while the motion capabilities of the small aerial robots are also exploited to further survey their area of responsibility until they hit the ground. The overall solution framework consists of lightweight path-planning algorithms that can run on virtually any processing unit that might be available on-board. Evaluation studies in simulation as well as a set of elementary experiments that prove the validity of important assumptions illustrate the potential of the approach.

* 6 pages, 9 figures, technical report 

  Access Paper or Ask Questions

Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks

Sep 28, 2017
Mingbo Ma, Kai Zhao, Liang Huang, Bing Xiang, Bowen Zhou

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and slot filling, or in topic classification and named-entity recognition. In order to utilize the potential benefits from their correlations, we propose a jointly trained model for learning the two tasks simultaneously via Long Short-Term Memory (LSTM) networks. This model predicts the sentence-level category and the word-level label sequence from the stepwise output hidden representations of LSTM. We also introduce a novel mechanism of "sparse attention" to weigh words differently based on their semantic relevance to sentence-level classification. The proposed method outperforms baseline models on ATIS and TREC datasets.

* interspeech 2017 

  Access Paper or Ask Questions

Understanding Infographics through Textual and Visual Tag Prediction

Sep 26, 2017
Zoya Bylinskii, Sami Alsheikh, Spandan Madan, Adria Recasens, Kimberli Zhong, Hanspeter Pfister, Fredo Durand, Aude Oliva

We introduce the problem of visual hashtag discovery for infographics: extracting visual elements from an infographic that are diagnostic of its topic. Given an infographic as input, our computational approach automatically outputs textual and visual elements predicted to be representative of the infographic content. Concretely, from a curated dataset of 29K large infographic images sampled across 26 categories and 391 tags, we present an automated two step approach. First, we extract the text from an infographic and use it to predict text tags indicative of the infographic content. And second, we use these predicted text tags as a supervisory signal to localize the most diagnostic visual elements from within the infographic i.e. visual hashtags. We report performances on a categorization and multi-label tag prediction problem and compare our proposed visual hashtags to human annotations.

  Access Paper or Ask Questions

The Convergence of Machine Learning and Communications

Aug 28, 2017
Wojciech Samek, Slawomir Stanczak, Thomas Wiegand

The areas of machine learning and communication technology are converging. Today's communications systems generate a huge amount of traffic data, which can help to significantly enhance the design and management of networks and communication components when combined with advanced machine learning methods. Furthermore, recently developed end-to-end training procedures offer new ways to jointly optimize the components of a communication system. Also in many emerging application fields of communication technology, e.g., smart cities or internet of things, machine learning methods are of central importance. This paper gives an overview over the use of machine learning in different areas of communications and discusses two exemplar applications in wireless networking. Furthermore, it identifies promising future research topics and discusses their potential impact.

* 8 pages, 4 figures 

  Access Paper or Ask Questions

Exploring text datasets by visualizing relevant words

Jul 17, 2017
Franziska Horn, Leila Arras, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek

When working with a new dataset, it is important to first explore and familiarize oneself with it, before applying any advanced machine learning algorithms. However, to the best of our knowledge, no tools exist that quickly and reliably give insight into the contents of a selection of documents with respect to what distinguishes them from other documents belonging to different categories. In this paper we propose to extract `relevant words' from a collection of texts, which summarize the contents of documents belonging to a certain class (or discovered cluster in the case of unlabeled datasets), and visualize them in word clouds to allow for a survey of salient features at a glance. We compare three methods for extracting relevant words and demonstrate the usefulness of the resulting word clouds by providing an overview of the classes contained in a dataset of scientific publications as well as by discovering trending topics from recent New York Times article snippets.

  Access Paper or Ask Questions

Restricted Boltzmann Machine for Classification with Hierarchical Correlated Prior

Apr 20, 2015
Gang Chen, Sargur H. Srihari

Restricted Boltzmann machines (RBM) and its variants have become hot research topics recently, and widely applied to many classification problems, such as character recognition and document categorization. Often, classification RBM ignores the interclass relationship or prior knowledge of sharing information among classes. In this paper, we are interested in RBM with the hierarchical prior over classes. We assume parameters for nearby nodes are correlated in the hierarchical tree, and further the parameters at each node of the tree be orthogonal to those at its ancestors. We propose a hierarchical correlated RBM for classification problem, which generalizes the classification RBM with sharing information among different classes. In order to reduce the redundancy between node parameters in the hierarchy, we also introduce orthogonal restrictions to our objective function. We test our method on challenge datasets, and show promising results compared to competitive baselines.

* 13 pages, 5 figures 

  Access Paper or Ask Questions

Real-time Dynamic MRI Reconstruction using Stacked Denoising Autoencoder

Mar 22, 2015
Angshul Majumdar

In this work we address the problem of real-time dynamic MRI reconstruction. There are a handful of studies on this topic; these techniques are either based on compressed sensing or employ Kalman Filtering. These techniques cannot achieve the reconstruction speed necessary for real-time reconstruction. In this work, we propose a new approach to MRI reconstruction. We learn a non-linear mapping from the unstructured aliased images to the corresponding clean images using a stacked denoising autoencoder (SDAE). The training for SDAE is slow, but the reconstruction is very fast - only requiring a few matrix vector multiplications. In this work, we have shown that using SDAE one can reconstruct the MRI frame faster than the data acquisition rate, thereby achieving real-time reconstruction. The quality of reconstruction is of the same order as a previous compressed sensing based online reconstruction technique.

  Access Paper or Ask Questions

Bayesian Optimization with Unknown Constraints

Mar 22, 2014
Michael A. Gelbart, Jasper Snoek, Ryan P. Adams

Recent work on Bayesian optimization has shown its effectiveness in global optimization of difficult black-box objective functions. Many real-world optimization problems of interest also have constraints which are unknown a priori. In this paper, we study Bayesian optimization for constrained problems in the general case that noise may be present in the constraint functions, and the objective and constraints may be evaluated independently. We provide motivating practical examples, and present a general framework to solve such problems. We demonstrate the effectiveness of our approach on optimizing the performance of online latent Dirichlet allocation subject to topic sparsity constraints, tuning a neural network given test-time memory constraints, and optimizing Hamiltonian Monte Carlo to achieve maximal effectiveness in a fixed time, subject to passing standard convergence diagnostics.

* 14 pages, 3 figures 

  Access Paper or Ask Questions

Is getting the right answer just about choosing the right words? The role of syntactically-informed features in short answer scoring

Mar 05, 2014
Derrick Higgins, Chris Brew, Michael Heilman, Ramon Ziai, Lei Chen, Aoife Cahill, Michael Flor, Nitin Madnani, Joel Tetreault, Daniel Blanchard, Diane Napolitano, Chong Min Lee, John Blackmore

Developments in the educational landscape have spurred greater interest in the problem of automatically scoring short answer questions. A recent shared task on this topic revealed a fundamental divide in the modeling approaches that have been applied to this problem, with the best-performing systems split between those that employ a knowledge engineering approach and those that almost solely leverage lexical information (as opposed to higher-level syntactic information) in assigning a score to a given response. This paper aims to introduce the NLP community to the largest corpus currently available for short-answer scoring, provide an overview of methods used in the shared task using this data, and explore the extent to which more syntactically-informed features can contribute to the short answer scoring task in a way that avoids the question-specific manual effort of the knowledge engineering approach.

  Access Paper or Ask Questions

Categorizing ancient documents

Aug 28, 2013
Nizar Zaghden, Remy Mullot, Mohamed Adel Alimi

The analysis of historical documents is still a topical issue given the importance of information that can be extracted and also the importance given by the institutions to preserve their heritage. The main idea in order to characterize the content of the images of ancient documents after attempting to clean the image is segmented blocks texts from the same image and tries to find similar blocks in either the same image or the entire image database. Most approaches of offline handwriting recognition proceed by segmenting words into smaller pieces (usually characters) which are recognized separately. Recognition of a word then requires the recognition of all characters (OCR) that compose it. Our work focuses mainly on the characterization of classes in images of old documents. We use Som toolbox for finding classes in documents. We applied also fractal dimensions and points of interest to categorize and match ancient documents.

* IJCSI International Journal of Computer Science Issues, Vol. 10, Issue 2, No 2, March 2013 ISSN (Print): 1694-0814 | ISSN (Online): 1694-0784 
* 10 pages 

  Access Paper or Ask Questions