Paper Group ANR 203
QR code denoising using parallel Hopfield networks. WisenetMD: Motion Detection Using Dynamic Background Region Analysis. Online Diverse Learning to Rank from Partial-Click Feedback. Band Assignment in Dual Band Systems: A Learning-based Approach. A Novel Approach to Sparse Inverse Covariance Estimation Using Transform Domain Updates and Exponentia …
QR code denoising using parallel Hopfield networks
Title | QR code denoising using parallel Hopfield networks |
Authors | Ishan Bhatnagar, Shubhang Bhatnagar |
Abstract | We propose a novel algorithm for using Hopfield networks to denoise QR codes. Hopfield networks have mostly been used as a noise tolerant memory or to solve difficult combinatorial problems. One of the major drawbacks in their use in noise tolerant associative memory is their low capacity of storage, scaling only linearly with the number of nodes in the network. A larger capacity therefore requires a larger number of nodes, thereby reducing the speed of convergence of the network in addition to increasing hardware costs for acquiring more precise data to be fed to a larger number of nodes. Our paper proposes a new algorithm to allow the use of several Hopfield networks in parallel thereby increasing the cumulative storage capacity of the system many times as compared to a single Hopfield network. Our algorithm would also be much faster than a larger single Hopfield network with the same total capacity. This enables their use in applications like denoising QR codes, which we have demonstrated in our paper. We then test our network on a large set of QR code images with different types of noise and demonstrate that such a system of Hopfield networks can be used to denoise and recognize QR codes in real time. |
Tasks | Denoising |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.01065v2 |
http://arxiv.org/pdf/1812.01065v2.pdf | |
PWC | https://paperswithcode.com/paper/qr-code-denoising-using-parallel-hopfield |
Repo | |
Framework | |
WisenetMD: Motion Detection Using Dynamic Background Region Analysis
Title | WisenetMD: Motion Detection Using Dynamic Background Region Analysis |
Authors | Sang-Ha Lee, Soon-Chul Kwon, Jin-Wook Shim, Jeong-Eun Lim, Jisang Yoo |
Abstract | Motion detection algorithms that can be applied to surveillance cameras such as CCTV (Closed Circuit Television) have been studied extensively. Motion detection algorithm is mostly based on background subtraction. One main issue in this technique is that false positives of dynamic backgrounds such as wind shaking trees and flowing rivers might occur. In this paper, we proposed a method to search for dynamic background region by analyzing the video and removing false positives by re-checking false positives. The proposed method was evaluated based on CDnet 2012/2014 dataset obtained at “changedetection.net” site. We also compared its processing speed with other algorithms. |
Tasks | Motion Detection |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09277v1 |
http://arxiv.org/pdf/1805.09277v1.pdf | |
PWC | https://paperswithcode.com/paper/wisenetmd-motion-detection-using-dynamic |
Repo | |
Framework | |
Online Diverse Learning to Rank from Partial-Click Feedback
Title | Online Diverse Learning to Rank from Partial-Click Feedback |
Authors | Prakhar Gupta, Gaurush Hiranandani, Harvineet Singh, Branislav Kveton, Zheng Wen, Iftikhar Ahamath Burhanuddin |
Abstract | Learning to rank is an important problem in machine learning and recommender systems. In a recommender system, a user is typically recommended a list of items. Since the user is unlikely to examine the entire recommended list, partial feedback arises naturally. At the same time, diverse recommendations are important because it is challenging to model all tastes of the user in practice. In this paper, we propose the first algorithm for online learning to rank diverse items from partial-click feedback. We assume that the user examines the list of recommended items until the user is attracted by an item, which is clicked, and does not examine the rest of the items. This model of user behavior is known as the cascade model. We propose an online learning algorithm, cascadelsb, for solving our problem. The algorithm actively explores the tastes of the user with the objective of learning to recommend the optimal diverse list. We analyze the algorithm and prove a gap-free upper bound on its n-step regret. We evaluate cascadelsb on both synthetic and real-world datasets, compare it to various baselines, and show that it learns even when our modeling assumptions do not hold exactly. |
Tasks | Learning-To-Rank, Recommendation Systems |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00911v2 |
http://arxiv.org/pdf/1811.00911v2.pdf | |
PWC | https://paperswithcode.com/paper/online-diverse-learning-to-rank-from-partial |
Repo | |
Framework | |
Band Assignment in Dual Band Systems: A Learning-based Approach
Title | Band Assignment in Dual Band Systems: A Learning-based Approach |
Authors | Daoud Burghal, Rui Wang, Andreas F. Molisch |
Abstract | We consider the band assignment problem in dual band systems, where the base-station (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate data to the mobile station (MS). While the millimeter-wave band offers higher data rate when it is available, there is a significant probability of outage during which the communication should be carried on the centimeter-wave band. In this work, we use a machine learning framework to provide an efficient and practical solution to the band assignment problem. In particular, the BS trains a Neural Network (NN) to predict the right band assignment decision using observed channel information. We study the performance of the NN in two environments: (i) A stochastic channel model with correlated bands, and (ii) microcellular outdoor channels obtained by simulations with a commercial ray-tracer. For the former case, for sake of comparison we also develop a threshold based band assignment that relies on the optimal mean square error estimator of the best band. In addition, we study the performance of the NN-based solution with different NN structures and different observed parameters (position, field strength, etc.). We compare the achieved performance to linear and logistic regression based solutions as well as the threshold based solution. Under practical constraints, the learning based band assignment shows competitive or superior performance in both environments. |
Tasks | |
Published | 2018-10-02 |
URL | http://arxiv.org/abs/1810.01534v1 |
http://arxiv.org/pdf/1810.01534v1.pdf | |
PWC | https://paperswithcode.com/paper/band-assignment-in-dual-band-systems-a |
Repo | |
Framework | |
A Novel Approach to Sparse Inverse Covariance Estimation Using Transform Domain Updates and Exponentially Adaptive Thresholding
Title | A Novel Approach to Sparse Inverse Covariance Estimation Using Transform Domain Updates and Exponentially Adaptive Thresholding |
Authors | Ashkan Esmaeili, Farokh Marvasti |
Abstract | Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this paper, we introduce a novel SICE approach using adaptive thresholding. Our method is based on updates in a transformed domain of the desired matrix and exponentially decaying adaptive thresholding in the main domain (Inverse Covariance matrix domain). In addition to the proposed algorithm, the convergence analysis is also provided. In the Numerical Experiments Section, we show that the proposed method outperforms state-of-the-art methods in terms of accuracy. |
Tasks | |
Published | 2018-11-16 |
URL | http://arxiv.org/abs/1811.06773v2 |
http://arxiv.org/pdf/1811.06773v2.pdf | |
PWC | https://paperswithcode.com/paper/a-novel-approach-to-sparse-inverse-covariance |
Repo | |
Framework | |
Unsupervised cross-lingual matching of product classifications
Title | Unsupervised cross-lingual matching of product classifications |
Authors | Denis Gordeev, Alexey Rey, Dmitry Shagarov |
Abstract | Unsupervised cross-lingual embeddings mapping has provided a unique tool for completely unsupervised translation even for languages with different scripts. In this work we use this method for the task of unsupervised cross-lingual matching of product classifications. Our work also investigates limitations of unsupervised vector alignment and we also suggest two other techniques for aligning product classifications based on their descriptions: using hierarchical information and translations. |
Tasks | |
Published | 2018-09-19 |
URL | http://arxiv.org/abs/1809.07234v1 |
http://arxiv.org/pdf/1809.07234v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-cross-lingual-matching-of |
Repo | |
Framework | |
A Feedback Neural Network for Small Target Motion Detection in Cluttered Backgrounds
Title | A Feedback Neural Network for Small Target Motion Detection in Cluttered Backgrounds |
Authors | Hongxin Wang, Jigen Peng, Shigang Yue |
Abstract | Small target motion detection is critical for insects to search for and track mates or prey which always appear as small dim speckles in the visual field. A class of specific neurons, called small target motion detectors (STMDs), has been characterized by exquisite sensitivity for small target motion. Understanding and analyzing visual pathway of STMD neurons are beneficial to design artificial visual systems for small target motion detection. Feedback loops have been widely identified in visual neural circuits and play an important role in target detection. However, if there exists a feedback loop in the STMD visual pathway or if a feedback loop could significantly improve the detection performance of STMD neurons, is unclear. In this paper, we propose a feedback neural network for small target motion detection against naturally cluttered backgrounds. In order to form a feedback loop, model output is temporally delayed and relayed to previous neural layer as feedback signal. Extensive experiments showed that the significant improvement of the proposed feedback neural network over the existing STMD-based models for small target motion detection. |
Tasks | Motion Detection |
Published | 2018-05-01 |
URL | http://arxiv.org/abs/1805.00342v2 |
http://arxiv.org/pdf/1805.00342v2.pdf | |
PWC | https://paperswithcode.com/paper/a-feedback-neural-network-for-small-target |
Repo | |
Framework | |
Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet
Title | Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet |
Authors | Shahla RezezadehAzar, Ali Ahmadi, Saber Malekzadeh, Maryam Samami |
Abstract | In this paper, AzarNet, a deep neural network (DNN), is proposed to recognizing seven different Dastgahs of Iranian classical music in Maryam Iranian classical music (MICM) dataset. Over the last years, there has been remarkable interest in employing feature learning and DNNs which lead to decreasing the required engineering effort. DNNs have shown better performance in many classification tasks such as audio signal classification compares to shallow processing architectures. Despite image data, audio data need some preprocessing steps to extract spectra and temporal features. Some transformations like Short-Time Fourier Transform (STFT) have been used in the state of art researches to transform audio signals from time-domain to time-frequency domain to extract both temporal and spectra features. In this research, the STFT output results which are extracted features are given to AzarNet for learning and classification processes. It is worth noting that, the mentioned dataset contains music tracks composed with two instruments (violin and straw). The overall f1 score of AzarNet on test set, for average of all seven classes was 86.21% which is the best result ever reported in Dastgah classification according to our best knowledge. |
Tasks | Recognizing Seven Different Dastgahs Of Iranian Classical Music |
Published | 2018-12-17 |
URL | http://arxiv.org/abs/1812.07017v3 |
http://arxiv.org/pdf/1812.07017v3.pdf | |
PWC | https://paperswithcode.com/paper/instrument-independent-dastgah-recognition-of |
Repo | |
Framework | |
Online Learning to Rank with Features
Title | Online Learning to Rank with Features |
Authors | Shuai Li, Tor Lattimore, Csaba Szepesvári |
Abstract | We introduce a new model for online ranking in which the click probability factors into an examination and attractiveness function and the attractiveness function is a linear function of a feature vector and an unknown parameter. Only relatively mild assumptions are made on the examination function. A novel algorithm for this setup is analysed, showing that the dependence on the number of items is replaced by a dependence on the dimension, allowing the new algorithm to handle a large number of items. When reduced to the orthogonal case, the regret of the algorithm improves on the state-of-the-art. |
Tasks | Learning-To-Rank |
Published | 2018-10-05 |
URL | https://arxiv.org/abs/1810.02567v2 |
https://arxiv.org/pdf/1810.02567v2.pdf | |
PWC | https://paperswithcode.com/paper/online-learning-to-rank-with-features |
Repo | |
Framework | |
Automatic trajectory recognition in Active Target Time Projection Chambers data by means of hierarchical clustering
Title | Automatic trajectory recognition in Active Target Time Projection Chambers data by means of hierarchical clustering |
Authors | Christoph Dalitz, Yassid Ayyad, Jens Wilberg, Lukas Aymans, Daniel Bazin, Wolfgang Mittig |
Abstract | The automatic reconstruction of three-dimensional particle tracks from Active Target Time Projection Chambers data can be a challenging task, especially in the presence of noise. In this article, we propose a non-parametric algorithm that is based on the idea of clustering point triplets instead of the original points. We define an appropriate distance measure on point triplets and then apply a single-link hierarchical clustering on the triplets. Compared to parametric approaches like RANSAC or the Hough transform, the new algorithm has the advantage of potentially finding trajectories even of shapes that are not known beforehand. This feature is particularly important in low-energy nuclear physics experiments with Active Targets operating inside a magnetic field. The algorithm has been validated using data from experiments performed with the Active Target Time Projection Chamber developed at the National Superconducting Cyclotron Laboratory (NSCL).The results demonstrate the capability of the algorithm to identify and isolate particle tracks that describe non-analytical trajectories. For curved tracks, the vertex detection recall was 86% and the precision 94%. For straight tracks, the vertex detection recall was 96% and the precision 98%. In the case of a test set containing only straight linear tracks, the algorithm performed better than an iterative Hough transform. |
Tasks | |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.03513v3 |
http://arxiv.org/pdf/1807.03513v3.pdf | |
PWC | https://paperswithcode.com/paper/automatic-trajectory-recognition-in-active |
Repo | |
Framework | |
An integrated rolling horizon approach to increase operating theatre efficiency
Title | An integrated rolling horizon approach to increase operating theatre efficiency |
Authors | Belinda Spratt, Erhan Kozan |
Abstract | Demand for healthcare is increasing rapidly. To meet demand, we must improve the efficiency of our public health services. We present a mixed integer programming (MIP) formulation that simultaneously tackles the integrated Master Surgical Schedule (MSS) and Surgical Case Assignment (SCA) problems. We consider volatile surgical durations and non-elective arrivals whilst applying a rolling horizon approach to adjust the schedule after cancellations, equipment failure, or new arrivals on the waiting list. A case study of an Australian public hospital with a large surgical department is the basis for the model. The formulation includes significant detail and provides practitioners with a globally implementable model. We produce good feasible solutions in short amounts of computational time with a constructive heuristic and two hyper metaheuristics. Using a rolling horizon schedule increases patient throughput and can help reduce waiting lists. |
Tasks | |
Published | 2018-08-30 |
URL | http://arxiv.org/abs/1808.10139v3 |
http://arxiv.org/pdf/1808.10139v3.pdf | |
PWC | https://paperswithcode.com/paper/an-integrated-rolling-horizon-approach-to |
Repo | |
Framework | |
Splitting source code identifiers using Bidirectional LSTM Recurrent Neural Network
Title | Splitting source code identifiers using Bidirectional LSTM Recurrent Neural Network |
Authors | Vadim Markovtsev, Waren Long, Egor Bulychev, Romain Keramitas, Konstantin Slavnov, Gabor Markowski |
Abstract | Programmers make rich use of natural language in the source code they write through identifiers and comments. Source code identifiers are selected from a pool of tokens which are strongly related to the meaning, naming conventions, and context. These tokens are often combined to produce more precise and obvious designations. Such multi-part identifiers count for 97% of all naming tokens in the Public Git Archive - the largest dataset of Git repositories to date. We introduce a bidirectional LSTM recurrent neural network to detect subtokens in source code identifiers. We trained that network on 41.7 million distinct splittable identifiers collected from 182,014 open source projects in Public Git Archive, and show that it outperforms several other machine learning models. The proposed network can be used to improve the upstream models which are based on source code identifiers, as well as improving developer experience allowing writing code without switching the keyboard case. |
Tasks | |
Published | 2018-05-26 |
URL | http://arxiv.org/abs/1805.11651v2 |
http://arxiv.org/pdf/1805.11651v2.pdf | |
PWC | https://paperswithcode.com/paper/splitting-source-code-identifiers-using |
Repo | |
Framework | |
Evolution leads to a diversity of motion-detection neuronal circuits
Title | Evolution leads to a diversity of motion-detection neuronal circuits |
Authors | Ali Tehrani-Saleh, Thomas LaBar, Christoph Adami |
Abstract | A central goal of evolutionary biology is to explain the origins and distribution of diversity across life. Beyond species or genetic diversity, we also observe diversity in the circuits (genetic or otherwise) underlying complex functional traits. However, while the theory behind the origins and maintenance of genetic and species diversity has been studied for decades, theory concerning the origin of diverse functional circuits is still in its infancy. It is not known how many different circuit structures can implement any given function, which evolutionary factors lead to different circuits, and whether the evolution of a particular circuit was due to adaptive or non-adaptive processes. Here, we use digital experimental evolution to study the diversity of neural circuits that encode motion detection in digital (artificial) brains. We find that evolution leads to an enormous diversity of potential neural architectures encoding motion detection circuits, even for circuits encoding the exact same function. Evolved circuits vary in both redundancy and complexity (as previously found in genetic circuits) suggesting that similar evolutionary principles underlie circuit formation using any substrate. We also show that a simple (designed) motion detection circuit that is optimally-adapted gains in complexity when evolved further, and that selection for mutational robustness led this gain in complexity. |
Tasks | Motion Detection |
Published | 2018-04-07 |
URL | http://arxiv.org/abs/1804.02508v2 |
http://arxiv.org/pdf/1804.02508v2.pdf | |
PWC | https://paperswithcode.com/paper/evolution-leads-to-a-diversity-of-motion |
Repo | |
Framework | |
Structure-from-Motion using Dense CNN Features with Keypoint Relocalization
Title | Structure-from-Motion using Dense CNN Features with Keypoint Relocalization |
Authors | Aji Resindra Widya, Akihiko Torii, Masatoshi Okutomi |
Abstract | Structure from Motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the extracted CNN features which is not even pixel-level accuracy in the existing approach. Providing dense feature matches with precise keypoint positions is not trivial because of memory limitation and computational burden of dense features. To achieve accurate SfM reconstruction with highly repeatable dense features, we propose an SfM pipeline that uses dense CNN features with relocalization of keypoint position that can efficiently and accurately provide pixel-level feature correspondences. Then, we demonstrate on the Aachen Day-Night dataset that the proposed SfM using dense CNN features with the keypoint relocalization outperforms a state-of-the-art SfM (COLMAP using RootSIFT) by a large margin. |
Tasks | |
Published | 2018-05-10 |
URL | http://arxiv.org/abs/1805.03879v2 |
http://arxiv.org/pdf/1805.03879v2.pdf | |
PWC | https://paperswithcode.com/paper/structure-from-motion-using-dense-cnn |
Repo | |
Framework | |
A Model for Evaluating Algorithmic Systems Accountability
Title | A Model for Evaluating Algorithmic Systems Accountability |
Authors | Yiannis Kanellopoulos |
Abstract | Algorithmic systems make decisions that have a great impact in our lives. As our dependency on them is growing so does the need for transparency and holding them accountable. This paper presents a model for evaluating how transparent these systems are by focusing on their algorithmic part as well as the maturity of the organizations that utilize them. We applied this model on a classification algorithm created and utilized by a large financial institution. The results of our analysis indicated that the organization was only partially in control of their algorithm and they lacked the necessary benchmark to interpret the deducted results and assess the validity of its inferencing. |
Tasks | |
Published | 2018-07-12 |
URL | http://arxiv.org/abs/1807.06083v1 |
http://arxiv.org/pdf/1807.06083v1.pdf | |
PWC | https://paperswithcode.com/paper/a-model-for-evaluating-algorithmic-systems |
Repo | |
Framework | |