July 28, 2019

3470 words 17 mins read

Paper Group ANR 326

An affective computational model for machine consciousness. A visual search engine for Bangladeshi laws. Solving Equations of Random Convex Functions via Anchored Regression. Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders. What Words Do We Use to Lie?: Word Choice in Deceptive …

An affective computational model for machine consciousness


Title	An affective computational model for machine consciousness
Authors	Rohitash Chandra
Abstract	In the past, several models of consciousness have become popular and have led to the development of models for machine consciousness with varying degrees of success and challenges for simulation and implementations. Moreover, affective computing attributes that involve emotions, behavior and personality have not been the focus of models of consciousness as they lacked motivation for deployment in software applications and robots. The affective attributes are important factors for the future of machine consciousness with the rise of technologies that can assist humans. Personality and affection hence can give an additional flavor for the computational model of consciousness in humanoid robotics. Recent advances in areas of machine learning with a focus on deep learning can further help in developing aspects of machine consciousness in areas that can better replicate human sensory perceptions such as speech recognition and vision. With such advancements, one encounters further challenges in developing models that can synchronize different aspects of affective computing. In this paper, we review some existing models of consciousnesses and present an affective computational model that would enable the human touch and feel for robotic systems.
Tasks	Speech Recognition
Published	2017-01-02
URL	http://arxiv.org/abs/1701.00349v1
PDF	http://arxiv.org/pdf/1701.00349v1.pdf
PWC	https://paperswithcode.com/paper/an-affective-computational-model-for-machine
Repo
Framework

A visual search engine for Bangladeshi laws


Title	A visual search engine for Bangladeshi laws
Authors	Manash Kumar Mandal, Pinku Deb Nath, Arpeeta Shams Mizan, Nazmus Saquib
Abstract	Browsing and finding relevant information for Bangladeshi laws is a challenge faced by all law students and researchers in Bangladesh, and by citizens who want to learn about any legal procedure. Some law archives in Bangladesh are digitized, but lack proper tools to organize the data meaningfully. We present a text visualization tool that utilizes machine learning techniques to make the searching of laws quicker and easier. Using Doc2Vec to layout law article nodes, link mining techniques to visualize relevant citation networks, and named entity recognition to quickly find relevant sections in long law articles, our tool provides a faster and better search experience to the users. Qualitative feedback from law researchers, students, and government officials show promise for visually intuitive search tools in the context of governmental, legal, and constitutional data in developing countries, where digitized data does not necessarily pave the way towards an easy access to information.
Tasks	Named Entity Recognition
Published	2017-11-14
URL	http://arxiv.org/abs/1711.05233v1
PDF	http://arxiv.org/pdf/1711.05233v1.pdf
PWC	https://paperswithcode.com/paper/a-visual-search-engine-for-bangladeshi-laws
Repo
Framework

Solving Equations of Random Convex Functions via Anchored Regression


Title	Solving Equations of Random Convex Functions via Anchored Regression
Authors	Sohail Bahmani, Justin Romberg
Abstract	We consider the question of estimating a solution to a system of equations that involve convex nonlinearities, a problem that is common in machine learning and signal processing. Because of these nonlinearities, conventional estimators based on empirical risk minimization generally involve solving a non-convex optimization program. We propose anchored regression, a new approach based on convex programming that amounts to maximizing a linear functional (perhaps augmented by a regularizer) over a convex set. The proposed convex program is formulated in the natural space of the problem, and avoids the introduction of auxiliary variables, making it computationally favorable. Working in the native space also provides great flexibility as structural priors (e.g., sparsity) can be seamlessly incorporated. For our analysis, we model the equations as being drawn from a fixed set according to a probability law. Our main results provide guarantees on the accuracy of the estimator in terms of the number of equations we are solving, the amount of noise present, a measure of statistical complexity of the random equations, and the geometry of the regularizer at the true solution. We also provide recipes for constructing the anchor vector (that determines the linear functional to maximize) directly from the observed data.
Tasks
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05327v3
PDF	http://arxiv.org/pdf/1702.05327v3.pdf
PWC	https://paperswithcode.com/paper/solving-equations-of-random-convex-functions
Repo
Framework

Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders


Title	Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders
Authors	Nastaran Mohammadian Rad, Seyed Mostafa Kia, Calogero Zarbo, Twan van Laarhoven, Giuseppe Jurman, Paola Venuti, Elena Marchiori, Cesare Furlanello
Abstract	Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multi-axis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.
Tasks	Transfer Learning
Published	2017-09-14
URL	http://arxiv.org/abs/1709.05956v1
PDF	http://arxiv.org/pdf/1709.05956v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-automatic-stereotypical
Repo
Framework

What Words Do We Use to Lie?: Word Choice in Deceptive Messages


Title	What Words Do We Use to Lie?: Word Choice in Deceptive Messages
Authors	Jason Dou, Michelle Liu, Haaris Muneer, Adam Schlussel
Abstract	Text messaging is the most widely used form of computer- mediated communication (CMC). Previous findings have shown that linguistic factors can reliably indicate messages as deceptive. For example, users take longer and use more words to craft deceptive messages than they do truthful messages. Existing research has also examined how factors, such as student status and gender, affect rates of deception and word choice in deceptive messages. However, this research has been limited by small sample sizes and has returned contradicting findings. This paper aims to address these issues by using a dataset of text messages collected from a large and varied set of participants using an Android messaging application. The results of this paper show significant differences in word choice and frequency of deceptive messages between male and female participants, as well as between students and non-students.
Tasks
Published	2017-10-01
URL	http://arxiv.org/abs/1710.00273v1
PDF	http://arxiv.org/pdf/1710.00273v1.pdf
PWC	https://paperswithcode.com/paper/what-words-do-we-use-to-lie-word-choice-in
Repo
Framework

Automated News Suggestions for Populating Wikipedia Entity Pages


Title	Automated News Suggestions for Populating Wikipedia Entity Pages
Authors	Besnik Fetahu, Katja Markert, Avishek Anand
Abstract	Wikipedia entity pages are a valuable source of information for direct consumption and for knowledge-base construction, update and maintenance. Facts in these entity pages are typically supported by references. Recent studies show that as much as 20% of the references are from online news sources. However, many entity pages are incomplete even if relevant information is already available in existing news articles. Even for the already present references, there is often a delay between the news article publication time and the reference time. In this work, we therefore look at Wikipedia through the lens of news and propose a novel news-article suggestion task to improve news coverage in Wikipedia, and reduce the lag of newsworthy references. Our work finds direct application, as a precursor, to Wikipedia page generation and knowledge-base acceleration tasks that rely on relevant and high quality input sources. We propose a two-stage supervised approach for suggesting news articles to entity pages for a given state of Wikipedia. First, we suggest news articles to Wikipedia entities (article-entity placement) relying on a rich set of features which take into account the \emph{salience} and \emph{relative authority} of entities, and the \emph{novelty} of news articles to entity pages. Second, we determine the exact section in the entity page for the input article (article-section placement) guided by class-based section templates. We perform an extensive evaluation of our approach based on ground-truth data that is extracted from external references in Wikipedia. We achieve a high precision value of up to 93% in the \emph{article-entity} suggestion stage and upto 84% for the \emph{article-section placement}. Finally, we compare our approach against competitive baselines and show significant improvements.
Tasks
Published	2017-03-30
URL	http://arxiv.org/abs/1703.10344v1
PDF	http://arxiv.org/pdf/1703.10344v1.pdf
PWC	https://paperswithcode.com/paper/automated-news-suggestions-for-populating
Repo
Framework

Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks


Title	Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
Authors	Tianshui Chen, Liang Lin, Wangmeng Zuo, Xiaonan Luo, Lei Zhang
Abstract	Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A practical strategy to this goal usually relies on a two-stage process: operating on the trained DNNs (e.g., approximating the convolutional filters with tensor decomposition) and fine-tuning the amended network, leading to difficulty in balancing the trade-off between acceleration and maintaining recognition performance. In this work, aiming at a general and comprehensive way for neural network acceleration, we develop a Wavelet-like Auto-Encoder (WAE) that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training. The two decomposed channels, in particular, are encoded to carry the low-frequency information (e.g., image profiles) and high-frequency (e.g., image details or noises), respectively, and enable reconstructing the original input image through the decoding process. Then, we feed the low-frequency channel into a standard classification network such as VGG or ResNet and employ a very lightweight network to fuse with the high-frequency channel to obtain the classification result. Compared to existing DNN acceleration solutions, our framework has the following advantages: i) it is tolerant to any existing convolutional neural networks for classification without amending their structures; ii) the WAE provides an interpretable way to preserve the main components of the input image for classification.
Tasks
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07493v1
PDF	http://arxiv.org/pdf/1712.07493v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-wavelet-like-auto-encoder-to
Repo
Framework

A batching and scheduling optimisation for a cutting work-center: Acta-Mobilier case study


Title	A batching and scheduling optimisation for a cutting work-center: Acta-Mobilier case study
Authors	Emmanuel Zimmermann, Hind Haouzi, Philippe Thomas, André Thomas, Melanie Noyel
Abstract	The purpose of this study is to investigate an approach to group lots in batches and to schedule these batches on Acta-Mobilier cutting work-center while taking into account numerous constraints and objectives. The specific batching method was proposed to handle the Acta-Mobilier problem and a mathematical formalisation and genetic algorithm were proposed to deal with the scheduling problem. The proposed algorithm has been embedded in software to optimise production costs and emphasis the visual management on the production line. The application is currently being used in Acta-Mobilier plant and shows significant results
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.03981v1
PDF	http://arxiv.org/pdf/1710.03981v1.pdf
PWC	https://paperswithcode.com/paper/a-batching-and-scheduling-optimisation-for-a
Repo
Framework

Deep Learning in Customer Churn Prediction: Unsupervised Feature Learning on Abstract Company Independent Feature Vectors


Title	Deep Learning in Customer Churn Prediction: Unsupervised Feature Learning on Abstract Company Independent Feature Vectors
Authors	Philip Spanoudes, Thomson Nguyen
Abstract	As companies increase their efforts in retaining customers, being able to predict accurately ahead of time, whether a customer will churn in the foreseeable future is an extremely powerful tool for any marketing team. The paper describes in depth the application of Deep Learning in the problem of churn prediction. Using abstract feature vectors, that can generated on any subscription based company’s user event logs, the paper proves that through the use of the intrinsic property of Deep Neural Networks (learning secondary features in an unsupervised manner), the complete pipeline can be applied to any subscription based company with extremely good churn predictive performance. Furthermore the research documented in the paper was performed for Framed Data (a company that sells churn prediction as a service for other companies) in conjunction with the Data Science Institute at Lancaster University, UK. This paper is the intellectual property of Framed Data.
Tasks
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03869v1
PDF	http://arxiv.org/pdf/1703.03869v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-customer-churn-prediction
Repo
Framework

A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning


Title	A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning
Authors	Einar Cesar Santos
Abstract	Resource allocation is still a difficult issue to deal with in wireless networks. The unstable channel condition and traffic demand for Quality of Service (QoS) raise some barriers that interfere with the process. It is significant that an optimal policy takes into account some resources available to each traffic class while considering the spectral efficiency and other related channel issues. Reinforcement learning is a dynamic and effective method to support the accomplishment of resource allocation properly maintaining QoS levels for applications. The technique can track the system state as feedback to enhance the performance of a given task. Herein, it is proposed a simple reinforcement learning mechanism introduced in LTE-A networks and aimed to choose and limit the number of resources allocated for each traffic class, regarding the QoS Class Identifier (QCI), at each Transmission Time Interval (TTI) along the scheduling procedure. The proposed mechanism implements a Markov Decision Process (MDP) solved by the Q-Learning algorithm to find an optimal action-state decision policy. The results obtained from simulation exhibit good performance, especially for the real-time Video application.
Tasks	Q-Learning
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09312v1
PDF	http://arxiv.org/pdf/1709.09312v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-reinforcement-learning-mechanism-for
Repo
Framework

Learning Filterbanks from Raw Speech for Phone Recognition


Title	Learning Filterbanks from Raw Speech for Phone Recognition
Authors	Neil Zeghidour, Nicolas Usunier, Iasonas Kokkinos, Thomas Schatz, Gabriel Synnaeve, Emmanuel Dupoux
Abstract	We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition. These time-domain filterbanks (TD-filterbanks) are initialized as an approximation of mel-filterbanks, and then fine-tuned jointly with the remaining convolutional architecture. We perform phone recognition experiments on TIMIT and show that for several architectures, models trained on TD-filterbanks consistently outperform their counterparts trained on comparable mel-filterbanks. We get our best performance by learning all front-end steps, from pre-emphasis up to averaging. Finally, we observe that the filters at convergence have an asymmetric impulse response, and that some of them remain almost analytic.
Tasks
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01161v2
PDF	http://arxiv.org/pdf/1711.01161v2.pdf
PWC	https://paperswithcode.com/paper/learning-filterbanks-from-raw-speech-for
Repo
Framework

The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation


Title	The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation
Authors	Georgi Karadjov, Tsvetomila Mihaylova, Yasen Kiprov, Georgi Georgiev, Ivan Koychev, Preslav Nakov
Abstract	Users posting online expect to remain anonymous unless they have logged in, which is often needed for them to be able to discuss freely on various topics. Preserving the anonymity of a text’s writer can be also important in some other contexts, e.g., in the case of witness protection or anonymity programs. However, each person has his/her own style of writing, which can be analyzed using stylometry, and as a result, the true identity of the author of a piece of text can be revealed even if s/he has tried to hide it. Thus, it could be helpful to design automatic tools that can help a person obfuscate his/her identity when writing text. In particular, here we propose an approach that changes the text, so that it is pushed towards average values for some general stylometric characteristics, thus making the use of these characteristics less discriminative. The approach consists of three main steps: first, we calculate the values for some popular stylometric metrics that can indicate authorship; then we apply various transformations to the text, so that these metrics are adjusted towards the average level, while preserving the semantics and the soundness of the text; and finally, we add random noise. This approach turned out to be very efficient, and yielded the best performance on the Author Obfuscation task at the PAN-2016 competition.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03736v2
PDF	http://arxiv.org/pdf/1707.03736v2.pdf
PWC	https://paperswithcode.com/paper/the-case-for-being-average-a-mediocrity
Repo
Framework

INTEL-TUT Dataset for Camera Invariant Color Constancy Research


Title	INTEL-TUT Dataset for Camera Invariant Color Constancy Research
Authors	Caglar Aytekin, Jarno Nikkanen, Moncef Gabbouj
Abstract	In this paper, we provide a novel dataset designed for camera invariant color constancy research. Camera invariance corresponds to the robustness of an algorithm’s performance when run on images of the same scene taken by different cameras. Accordingly, images in the database correspond to several lab and field scenes each of which are captured by three different cameras with minimal registration errors. The lab scenes are also captured under five different illuminations. The spectral responses of cameras and the spectral power distributions of the lab light sources are also provided, as they may prove beneficial for training future algorithms to achieve color constancy. For a fair evaluation of future methods, we provide guidelines for supervised methods with indicated training, validation and testing partitions. Accordingly, we evaluate a recently proposed convolutional neural network based color constancy algorithm as a baseline for future research. As a side contribution, this dataset also includes images taken by a mobile camera with color shading corrected and uncorrected results. This allows research on the effect of color shading as well.
Tasks	Color Constancy
Published	2017-03-21
URL	http://arxiv.org/abs/1703.09778v2
PDF	http://arxiv.org/pdf/1703.09778v2.pdf
PWC	https://paperswithcode.com/paper/intel-tut-dataset-for-camera-invariant-color
Repo
Framework

Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis


Title	Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis
Authors	Adrian Galdran, Aitor Alvarez-Gila, Maria Ines Meyer, Cristina L. Saratxaga, Teresa Araújo, Estibaliz Garrote, Guilherme Aresta, Pedro Costa, A. M. Mendonça, Aurélio Campilho
Abstract	Dermoscopic skin images are often obtained with different imaging devices, under varying acquisition conditions. In this work, instead of attempting to perform intensity and color normalization, we propose to leverage computational color constancy techniques to build an artificial data augmentation technique suitable for this kind of images. Specifically, we apply the \emph{shades of gray} color constancy technique to color-normalize the entire training set of images, while retaining the estimated illuminants. We then draw one sample from the distribution of training set illuminants and apply it on the normalized image. We employ this technique for training two deep convolutional neural networks for the tasks of skin lesion segmentation and skin lesion classification, in the context of the ISIC 2017 challenge and without using any external dermatologic image set. Our results on the validation set are promising, and will be supplemented with extended results on the hidden test set when available.
Tasks	Color Constancy, Data Augmentation, Lesion Segmentation, Skin Lesion Classification
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03702v1
PDF	http://arxiv.org/pdf/1703.03702v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-color-augmentation-techniques-for
Repo
Framework

Functions that Emerge through End-to-End Reinforcement Learning - The Direction for Artificial General Intelligence -


Title	Functions that Emerge through End-to-End Reinforcement Learning - The Direction for Artificial General Intelligence -
Authors	Katsunari Shibata
Abstract	Recently, triggered by the impressive results in TV-games or game of Go by Google DeepMind, end-to-end reinforcement learning (RL) is collecting attentions. Although little is known, the author’s group has propounded this framework for around 20 years and already has shown various functions that emerge in a neural network (NN) through RL. In this paper, they are introduced again at this timing. “Function Modularization” approach is deeply penetrated subconsciously. The inputs and outputs for a learning system can be raw sensor signals and motor commands. “State space” or “action space” generally used in RL show the existence of functional modules. That has limited reinforcement learning to learning only for the action-planning module. In order to extend reinforcement learning to learning of the entire function on a huge degree of freedom of a massively parallel learning system and to explain or develop human-like intelligence, the author has believed that end-to-end RL from sensors to motors using a recurrent NN (RNN) becomes an essential key. Especially in the higher functions, this approach is very effective by being free from the need to decide their inputs and outputs. The functions that emerge, we have confirmed, through RL using a NN cover a broad range from real robot learning with raw camera pixel inputs to acquisition of dynamic functions in a RNN. Those are (1)image recognition, (2)color constancy (optical illusion), (3)sensor motion (active recognition), (4)hand-eye coordination and hand reaching movement, (5)explanation of brain activities, (6)communication, (7)knowledge transfer, (8)memory, (9)selective attention, (10)prediction, (11)exploration. The end-to-end RL enables the emergence of very flexible comprehensive functions that consider many things in parallel although it is difficult to give the boundary of each function clearly.
Tasks	Color Constancy, Game of Go, Transfer Learning
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02239v2
PDF	http://arxiv.org/pdf/1703.02239v2.pdf
PWC	https://paperswithcode.com/paper/functions-that-emerge-through-end-to-end
Repo
Framework