Paper Group ANR 178
Find an Optimal Path in Static System and Dynamical System within Polynomial Runtime. Geometry of 3D Environments and Sum of Squares Polynomials. Large scale near-duplicate image retrieval using Triples of Adjacent Ranked Features (TARF) with embedded geometric information. Machine Learning for Visual Navigation of Unmanned Ground Vehicles. Towards …
Find an Optimal Path in Static System and Dynamical System within Polynomial Runtime
| Title | Find an Optimal Path in Static System and Dynamical System within Polynomial Runtime |
| Authors | Yong Tan |
| Abstract | We study an ancient problem that in a static or dynamical system, sought an optimal path, which the context always means within an extremal condition. In fact, through those discussions about this theme, we established a universal essential calculated model to serve for these complex systems. Meanwhile we utilize the sample space to character the system. These contents in this paper would involve in several major areas including the geometry, probability, graph algorithms and some prior approaches, which stands the ultimately subtle linear algorithm to solve this class problem. Along with our progress, our discussion would demonstrate more general meaning and robust character, which provides clear ideas or notion to support our concrete applications, who work in a more popular complex system. |
| Tasks | |
| Published | 2016-02-07 |
| URL | http://arxiv.org/abs/1602.02377v1 |
| http://arxiv.org/pdf/1602.02377v1.pdf | |
| PWC | https://paperswithcode.com/paper/find-an-optimal-path-in-static-system-and |
| Repo | |
| Framework | |
Geometry of 3D Environments and Sum of Squares Polynomials
| Title | Geometry of 3D Environments and Sum of Squares Polynomials |
| Authors | Amir Ali Ahmadi, Georgina Hall, Ameesh Makadia, Vikas Sindhwani |
| Abstract | Motivated by applications in robotics and computer vision, we study problems related to spatial reasoning of a 3D environment using sublevel sets of polynomials. These include: tightly containing a cloud of points (e.g., representing an obstacle) with convex or nearly-convex basic semialgebraic sets, computation of Euclidean distances between two such sets, separation of two convex basic semalgebraic sets that overlap, and tight containment of the union of several basic semialgebraic sets with a single convex one. We use algebraic techniques from sum of squares optimization that reduce all these tasks to semidefinite programs of small size and present numerical experiments in realistic scenarios. |
| Tasks | |
| Published | 2016-11-22 |
| URL | http://arxiv.org/abs/1611.07369v3 |
| http://arxiv.org/pdf/1611.07369v3.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-of-3d-environments-and-sum-of |
| Repo | |
| Framework | |
Large scale near-duplicate image retrieval using Triples of Adjacent Ranked Features (TARF) with embedded geometric information
| Title | Large scale near-duplicate image retrieval using Triples of Adjacent Ranked Features (TARF) with embedded geometric information |
| Authors | Sergei Fedorov, Olga Kacher |
| Abstract | Most approaches to large-scale image retrieval are based on the construction of the inverted index of local image descriptors or visual words. A search in such an index usually results in a large number of candidates. This list of candidates is then re-ranked with the help of a geometric verification, using a RANSAC algorithm, for example. In this paper we propose a feature representation, which is built as a combination of three local descriptors. It allows one to significantly decrease the number of false matches and to shorten the list of candidates after the initial search in the inverted index. This combination of local descriptors is both reproducible and highly discriminative, and thus can be efficiently used for large-scale near-duplicate image retrieval. |
| Tasks | Image Retrieval |
| Published | 2016-03-19 |
| URL | http://arxiv.org/abs/1603.06093v1 |
| http://arxiv.org/pdf/1603.06093v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-near-duplicate-image-retrieval |
| Repo | |
| Framework | |
Machine Learning for Visual Navigation of Unmanned Ground Vehicles
| Title | Machine Learning for Visual Navigation of Unmanned Ground Vehicles |
| Authors | Artem A. Lenskiy, Jong-Soo Lee |
| Abstract | The use of visual information for the navigation of unmanned ground vehicles in a cross-country environment recently received great attention. However, until now, the use of textural information has been somewhat less effective than color or laser range information. This manuscript reviews the recent achievements in cross-country scene segmentation and addresses their shortcomings. It then describes a problem related to classification of high dimensional texture features. Finally, it compares three machine learning algorithms aimed at resolving this problem. The experimental results for each machine learning algorithm with the discussion of comparisons are given at the end of the manuscript. |
| Tasks | Scene Segmentation, Visual Navigation |
| Published | 2016-04-08 |
| URL | http://arxiv.org/abs/1604.02485v1 |
| http://arxiv.org/pdf/1604.02485v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-visual-navigation-of |
| Repo | |
| Framework | |
Towards Bayesian Deep Learning: A Survey
| Title | Towards Bayesian Deep Learning: A Survey |
| Authors | Hao Wang, Dit-Yan Yeung |
| Abstract | While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This survey provides a general introduction to Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this survey, we also discuss the relationship and differences between Bayesian deep learning and other related topics like Bayesian treatment of neural networks. |
| Tasks | Object Recognition, Recommendation Systems, Topic Models |
| Published | 2016-04-06 |
| URL | http://arxiv.org/abs/1604.01662v2 |
| http://arxiv.org/pdf/1604.01662v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-bayesian-deep-learning-a-survey |
| Repo | |
| Framework | |
A Deep Learning Based Fast Image Saliency Detection Algorithm
| Title | A Deep Learning Based Fast Image Saliency Detection Algorithm |
| Authors | Hengyue Pan, Hui Jiang |
| Abstract | In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify the input images based on the pixel-wise gradients to reduce a pre-defined cost function, which is defined to measure the class-specific objectness and clamp the class-irrelevant outputs to maintain image background. The pixel-wise gradients can be efficiently computed using the back-propagation algorithm. We further apply SLIC superpixels and LAB color based low level saliency features to smooth and refine the gradients. Our methods are quite computationally efficient, much faster than other deep learning based saliency methods. Experimental results on two benchmark tasks, namely Pascal VOC 2012 and MSRA10k, have shown that our proposed methods can generate high-quality salience maps, at least comparable with many slow and complicated deep learning methods. Comparing with the pure low-level methods, our approach excels in handling many difficult images, which contain complex background, highly-variable salient objects, multiple objects, and/or very small salient objects. |
| Tasks | Saliency Detection |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00577v1 |
| http://arxiv.org/pdf/1602.00577v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-based-fast-image-saliency |
| Repo | |
| Framework | |
The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization
| Title | The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization |
| Authors | Etai Littwin, Lior Wolf |
| Abstract | Deep Residual Networks present a premium in performance in comparison to conventional networks of the same depth and are trainable at extreme depths. It has recently been shown that Residual Networks behave like ensembles of relatively shallow networks. We show that these ensembles are dynamic: while initially the virtual ensemble is mostly at depths lower than half the network’s depth, as training progresses, it becomes deeper and deeper. The main mechanism that controls the dynamic ensemble behavior is the scaling introduced, e.g., by the Batch Normalization technique. We explain this behavior and demonstrate the driving force behind it. As a main tool in our analysis, we employ generalized spin glass models, which we also use in order to study the number of critical points in the optimization of Residual Networks. |
| Tasks | |
| Published | 2016-11-08 |
| URL | http://arxiv.org/abs/1611.02525v1 |
| http://arxiv.org/pdf/1611.02525v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-loss-surface-of-residual-networks |
| Repo | |
| Framework | |
Ensemble Maximum Entropy Classification and Linear Regression for Author Age Prediction
| Title | Ensemble Maximum Entropy Classification and Linear Regression for Author Age Prediction |
| Authors | Joey Hong, Chris Mattmann, Paul Ramirez |
| Abstract | The evolution of the internet has created an abundance of unstructured data on the web, a significant part of which is textual. The task of author profiling seeks to find the demographics of people solely from their linguistic and content-based features in text. The ability to describe traits of authors clearly has applications in fields such as security and forensics, as well as marketing. Instead of seeing age as just a classification problem, we also frame age as a regression one, but use an ensemble chain method that incorporates the power of both classification and regression to learn the authors exact age. |
| Tasks | |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.00852v1 |
| http://arxiv.org/pdf/1610.00852v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-maximum-entropy-classification-and |
| Repo | |
| Framework | |
Decentralized Topic Modelling with Latent Dirichlet Allocation
| Title | Decentralized Topic Modelling with Latent Dirichlet Allocation |
| Authors | Igor Colin, Christophe Dupuy |
| Abstract | Privacy preserving networks can be modelled as decentralized networks (e.g., sensors, connected objects, smartphones), where communication between nodes of the network is not controlled by an all-knowing, central node. For this type of networks, the main issue is to gather/learn global information on the network (e.g., by optimizing a global cost function) while keeping the (sensitive) information at each node. In this work, we focus on text information that agents do not want to share (e.g., text messages, emails, confidential reports). We use recent advances on decentralized optimization and topic models to infer topics from a graph with limited communication. We propose a method to adapt latent Dirichlet allocation (LDA) model to decentralized optimization and show on synthetic data that we still recover similar parameters and similar performance at each node than with stochastic methods accessing to the whole information in the graph. |
| Tasks | Topic Models |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01417v1 |
| http://arxiv.org/pdf/1610.01417v1.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-topic-modelling-with-latent |
| Repo | |
| Framework | |
Machine Learning for E-mail Spam Filtering: Review,Techniques and Trends
| Title | Machine Learning for E-mail Spam Filtering: Review,Techniques and Trends |
| Authors | Alexy Bhowmick, Shyamanta M. Hazarika |
| Abstract | We present a comprehensive review of the most effective content-based e-mail spam filtering techniques. We focus primarily on Machine Learning-based spam filters and their variants, and report on a broad review ranging from surveying the relevant ideas, efforts, effectiveness, and the current progress. The initial exposition of the background examines the basics of e-mail spam filtering, the evolving nature of spam, spammers playing cat-and-mouse with e-mail service providers (ESPs), and the Machine Learning front in fighting spam. We conclude by measuring the impact of Machine Learning-based filters and explore the promising offshoots of latest developments. |
| Tasks | |
| Published | 2016-06-03 |
| URL | http://arxiv.org/abs/1606.01042v1 |
| http://arxiv.org/pdf/1606.01042v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-e-mail-spam-filtering |
| Repo | |
| Framework | |
Training IBM Watson using Automatically Generated Question-Answer Pairs
| Title | Training IBM Watson using Automatically Generated Question-Answer Pairs |
| Authors | Jangho Lee, Gyuwan Kim, Jaeyoon Yoo, Changwoo Jung, Minseok Kim, Sungroh Yoon |
| Abstract | IBM Watson is a cognitive computing system capable of question answering in natural languages. It is believed that IBM Watson can understand large corpora and answer relevant questions more effectively than any other question-answering system currently available. To unleash the full power of Watson, however, we need to train its instance with a large number of well-prepared question-answer pairs. Obviously, manually generating such pairs in a large quantity is prohibitively time consuming and significantly limits the efficiency of Watson’s training. Recently, a large-scale dataset of over 30 million question-answer pairs was reported. Under the assumption that using such an automatically generated dataset could relieve the burden of manual question-answer generation, we tried to use this dataset to train an instance of Watson and checked the training efficiency and accuracy. According to our experiments, using this auto-generated dataset was effective for training Watson, complementing manually crafted question-answer pairs. To the best of the authors’ knowledge, this work is the first attempt to use a large-scale dataset of automatically generated question-answer pairs for training IBM Watson. We anticipate that the insights and lessons obtained from our experiments will be useful for researchers who want to expedite Watson training leveraged by automatically generated question-answer pairs. |
| Tasks | Question Answering |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.03932v1 |
| http://arxiv.org/pdf/1611.03932v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-ibm-watson-using-automatically |
| Repo | |
| Framework | |
Clinical Information Extraction via Convolutional Neural Network
| Title | Clinical Information Extraction via Convolutional Neural Network |
| Authors | Peng Li, Heng Huang |
| Abstract | We report an implementation of a clinical information extraction tool that leverages deep neural network to annotate event spans and their attributes from raw clinical notes and pathology reports. Our approach uses context words and their part-of-speech tags and shape information as features. Then we hire temporal (1D) convolutional neural network to learn hidden feature representations. Finally, we use Multilayer Perceptron (MLP) to predict event spans. The empirical evaluation demonstrates that our approach significantly outperforms baselines. |
| Tasks | |
| Published | 2016-03-30 |
| URL | http://arxiv.org/abs/1603.09381v1 |
| http://arxiv.org/pdf/1603.09381v1.pdf | |
| PWC | https://paperswithcode.com/paper/clinical-information-extraction-via |
| Repo | |
| Framework | |
From Images to 3D Shape Attributes
| Title | From Images to 3D Shape Attributes |
| Authors | David F. Fouhey, Abhinav Gupta, Andrew Zisserman |
| Abstract | Our goal in this paper is to investigate properties of 3D shape that can be determined from a single image. We define 3D shape attributes – generic properties of the shape that capture curvature, contact and occupied space. Our first objective is to infer these 3D shape attributes from a single image. A second objective is to infer a 3D shape embedding – a low dimensional vector representing the 3D shape. We study how the 3D shape attributes and embedding can be obtained from a single image by training a Convolutional Neural Network (CNN) for this task. We start with synthetic images so that the contribution of various cues and nuisance parameters can be controlled. We then turn to real images and introduce a large scale image dataset of sculptures containing 143K images covering 2197 works from 242 artists. For the CNN trained on the sculpture dataset we show the following: (i) which regions of the imaged sculpture are used by the CNN to infer the 3D shape attributes; (ii) that the shape embedding can be used to match previously unseen sculptures largely independent of viewpoint; and (iii) that the 3D attributes generalize to images of other (non-sculpture) object classes. |
| Tasks | |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06836v2 |
| http://arxiv.org/pdf/1612.06836v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-images-to-3d-shape-attributes |
| Repo | |
| Framework | |
Improving Correlation with Human Judgments by Integrating Semantic Similarity with Second–Order Vectors
| Title | Improving Correlation with Human Judgments by Integrating Semantic Similarity with Second–Order Vectors |
| Authors | Bridget T. McInnes, Ted Pedersen |
| Abstract | Vector space methods that measure semantic similarity and relatedness often rely on distributional information such as co–occurrence frequencies or statistical measures of association to weight the importance of particular co–occurrences. In this paper, we extend these methods by incorporating a measure of semantic similarity based on a human curated taxonomy into a second–order vector representation. This results in a measure of semantic relatedness that combines both the contextual information available in a corpus–based vector space representation with the semantic knowledge found in a biomedical ontology. Our results show that incorporating semantic similarity into a second order co–occurrence matrices improves correlation with human judgments for both similarity and relatedness, and that our method compares favorably to various different word embedding methods that have recently been evaluated on the same reference standards we have used. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-09-02 |
| URL | http://arxiv.org/abs/1609.00559v2 |
| http://arxiv.org/pdf/1609.00559v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-correlation-with-human-judgments-by |
| Repo | |
| Framework | |
An artificial neural network to find correlation patterns in an arbitrary number of variables
| Title | An artificial neural network to find correlation patterns in an arbitrary number of variables |
| Authors | Alessandro Fontana |
| Abstract | Methods to find correlation among variables are of interest to many disciplines, including statistics, machine learning, (big) data mining and neurosciences. Parameters that measure correlation between two variables are of limited utility when used with multiple variables. In this work, I propose a simple criterion to measure correlation among an arbitrary number of variables, based on a data set. The central idea is to i) design a function of the variables that can take different forms depending on a set of parameters, ii) calculate the difference between a statistics associated to the function computed on the data set and the same statistics computed on a randomised version of the data set, called “scrambled” data set, and iii) optimise the parameters to maximise this difference. Many such functions can be organised in layers, which can in turn be stacked one on top of the other, forming a neural network. The function parameters are searched with an enhanced genetic algortihm called POET and the resulting method is tested on a cancer gene data set. The method may have potential implications for some issues that affect the field of neural networks, such as overfitting, the need to process huge amounts of data for training and the presence of “adversarial examples”. |
| Tasks | |
| Published | 2016-06-21 |
| URL | http://arxiv.org/abs/1606.06564v2 |
| http://arxiv.org/pdf/1606.06564v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-artificial-neural-network-to-find |
| Repo | |
| Framework | |
