Paper Group ANR 168
Evaluating the effect of topic consideration in identifying communities of rating-based social networks. Predicting the Industry of Users on Social Media. Automatic Construction of a Recurrent Neural Network based Classifier for Vehicle Passage Detection. Image Segmentation Based on the Self-Balancing Mechanism in Virtual 3D Elastic Mesh. Dual Dens …
Evaluating the effect of topic consideration in identifying communities of rating-based social networks
| Title | Evaluating the effect of topic consideration in identifying communities of rating-based social networks |
| Authors | Ali Reihanian, Behrouz Minaei-Bidgoli, Muhammad Yousefnezhad |
| Abstract | Finding meaningful communities in social network has attracted the attentions of many researchers. The community structure of complex networks reveals both their organization and hidden relations among their constituents. Most of the researches in the field of community detection mainly focus on the topological structure of the network without performing any content analysis. Nowadays, real world social networks are containing a vast range of information including shared objects, comments, following information, etc. In recent years, a number of researches have proposed approaches which consider both the contents that are interchanged in the networks and the topological structures of the networks in order to find more meaningful communities. In this research, the effect of topic analysis in finding more meaningful communities in social networking sites in which the users express their feelings toward different objects (like movies) by the means of rating is demonstrated by performing extensive experiments. |
| Tasks | Community Detection |
| Published | 2016-04-26 |
| URL | http://arxiv.org/abs/1604.07878v1 |
| http://arxiv.org/pdf/1604.07878v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-the-effect-of-topic-consideration |
| Repo | |
| Framework | |
Predicting the Industry of Users on Social Media
| Title | Predicting the Industry of Users on Social Media |
| Authors | Konstantinos Pappas, Rada Mihalcea |
| Abstract | Automatic profiling of social media users is an important task for supporting a multitude of downstream applications. While a number of studies have used social media content to extract and study collective social attributes, there is a lack of substantial research that addresses the detection of a user’s industry. We frame this task as classification using both feature engineering and ensemble learning. Our industry-detection system uses both posted content and profile information to detect a user’s industry with 64.3% accuracy, significantly outperforming the majority baseline in a taxonomy of fourteen industry classes. Our qualitative analysis suggests that a person’s industry not only affects the words used and their perceived meanings, but also the number and type of emotions being expressed. |
| Tasks | Feature Engineering |
| Published | 2016-12-24 |
| URL | http://arxiv.org/abs/1612.08205v1 |
| http://arxiv.org/pdf/1612.08205v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-industry-of-users-on-social |
| Repo | |
| Framework | |
Automatic Construction of a Recurrent Neural Network based Classifier for Vehicle Passage Detection
| Title | Automatic Construction of a Recurrent Neural Network based Classifier for Vehicle Passage Detection |
| Authors | Evgeny Burnaev, Ivan Koptelov, German Novikov, Timur Khanipov |
| Abstract | Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data. |
| Tasks | Time Series |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.08209v1 |
| http://arxiv.org/pdf/1609.08209v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-construction-of-a-recurrent-neural |
| Repo | |
| Framework | |
Image Segmentation Based on the Self-Balancing Mechanism in Virtual 3D Elastic Mesh
| Title | Image Segmentation Based on the Self-Balancing Mechanism in Virtual 3D Elastic Mesh |
| Authors | Xiaodong Zhuang, N. E. Mastorakis, Jieru Chi, Hanping Wang |
| Abstract | In this paper, a novel model of 3D elastic mesh is presented for image segmentation. The model is inspired by stress and strain in physical elastic objects, while the repulsive force and elastic force in the model are defined slightly different from the physical force to suit the segmentation problem well. The self-balancing mechanism in the model guarantees the stability of the method in segmentation. The shape of the elastic mesh at balance state is used for region segmentation, in which the sign distribution of the points’z coordinate values is taken as the basis for segmentation. The effectiveness of the proposed method is proved by analysis and experimental results for both test images and real world images. |
| Tasks | Semantic Segmentation |
| Published | 2016-10-10 |
| URL | http://arxiv.org/abs/1610.02760v1 |
| http://arxiv.org/pdf/1610.02760v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-segmentation-based-on-the-self |
| Repo | |
| Framework | |
Dual Density Operators and Natural Language Meaning
| Title | Dual Density Operators and Natural Language Meaning |
| Authors | Daniela Ashoush, Bob Coecke |
| Abstract | Density operators allow for representing ambiguity about a vector representation, both in quantum theory and in distributional natural language meaning. Formally equivalently, they allow for discarding part of the description of a composite system, where we consider the discarded part to be the context. We introduce dual density operators, which allow for two independent notions of context. We demonstrate the use of dual density operators within a grammatical-compositional distributional framework for natural language meaning. We show that dual density operators can be used to simultaneously represent: (i) ambiguity about word meanings (e.g. queen as a person vs. queen as a band), and (ii) lexical entailment (e.g. tiger -> mammal). We provide a proof-of-concept example. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1608.01401v1 |
| http://arxiv.org/pdf/1608.01401v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-density-operators-and-natural-language |
| Repo | |
| Framework | |
Path Integral Guided Policy Search
| Title | Path Integral Guided Policy Search |
| Authors | Yevgen Chebotar, Mrinal Kalakrishnan, Ali Yahya, Adrian Li, Stefan Schaal, Sergey Levine |
| Abstract | We present a policy search method for learning complex feedback control policies that map from high-dimensional sensory inputs to motor torques, for manipulation tasks with discontinuous contact dynamics. We build on a prior technique called guided policy search (GPS), which iteratively optimizes a set of local policies for specific instances of a task, and uses these to train a complex, high-dimensional global policy that generalizes across task instances. We extend GPS in the following ways: (1) we propose the use of a model-free local optimizer based on path integral stochastic optimal control (PI2), which enables us to learn local policies for tasks with highly discontinuous contact dynamics; and (2) we enable GPS to train on a new set of task instances in every iteration by using on-policy sampling: this increases the diversity of the instances that the policy is trained on, and is crucial for achieving good generalization. We show that these contributions enable us to learn deep neural network policies that can directly perform torque control from visual input. We validate the method on a challenging door opening task and a pick-and-place task, and we demonstrate that our approach substantially outperforms the prior LQR-based local policy optimizer on these tasks. Furthermore, we show that on-policy sampling significantly increases the generalization ability of these policies. |
| Tasks | |
| Published | 2016-10-03 |
| URL | http://arxiv.org/abs/1610.00529v2 |
| http://arxiv.org/pdf/1610.00529v2.pdf | |
| PWC | https://paperswithcode.com/paper/path-integral-guided-policy-search |
| Repo | |
| Framework | |
DeepCancer: Detecting Cancer through Gene Expressions via Deep Generative Learning
| Title | DeepCancer: Detecting Cancer through Gene Expressions via Deep Generative Learning |
| Authors | Rajendra Rana Bhat, Vivek Viswanath, Xiaolin Li |
| Abstract | Transcriptional profiling on microarrays to obtain gene expressions has been used to facilitate cancer diagnosis. We propose a deep generative machine learning architecture (called DeepCancer) that learn features from unlabeled microarray data. These models have been used in conjunction with conventional classifiers that perform classification of the tissue samples as either being cancerous or non-cancerous. The proposed model has been tested on two different clinical datasets. The evaluation demonstrates that DeepCancer model achieves a very high precision score, while significantly controlling the false positive and false negative scores. |
| Tasks | |
| Published | 2016-12-09 |
| URL | http://arxiv.org/abs/1612.03211v2 |
| http://arxiv.org/pdf/1612.03211v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepcancer-detecting-cancer-through-gene |
| Repo | |
| Framework | |
Sentiment Analysis on Bangla and Romanized Bangla Text (BRBT) using Deep Recurrent models
| Title | Sentiment Analysis on Bangla and Romanized Bangla Text (BRBT) using Deep Recurrent models |
| Authors | A. Hassan, M. R. Amin, N. Mohammed, A. K. A. Azad |
| Abstract | Sentiment Analysis (SA) is an action research area in the digital age. With rapid and constant growth of online social media sites and services, and the increasing amount of textual data such as - statuses, comments, reviews etc. available in them, application of automatic SA is on the rise. However, most of the research works on SA in natural language processing (NLP) are based on English language. Despite being the sixth most widely spoken language in the world, Bangla still does not have a large and standard dataset. Because of this, recent research works in Bangla have failed to produce results that can be both comparable to works done by others and reusable as stepping stones for future researchers to progress in this field. Therefore, we first tried to provide a textual dataset - that includes not just Bangla, but Romanized Bangla texts as well, is substantial, post-processed and multiple validated, ready to be used in SA experiments. We tested this dataset in Deep Recurrent model, specifically, Long Short Term Memory (LSTM), using two types of loss functions - binary crossentropy and categorical crossentropy, and also did some experimental pre-training by using data from one validation to pre-train the other and vice versa. Lastly, we documented the results along with some analysis on them, which were promising. |
| Tasks | Sentiment Analysis |
| Published | 2016-10-02 |
| URL | http://arxiv.org/abs/1610.00369v2 |
| http://arxiv.org/pdf/1610.00369v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-on-bangla-and-romanized |
| Repo | |
| Framework | |
Robust Multi-body Feature Tracker: A Segmentation-free Approach
| Title | Robust Multi-body Feature Tracker: A Segmentation-free Approach |
| Authors | Pan Ji, Hongdong Li, Mathieu Salzmann, Yiran Zhong |
| Abstract | Feature tracking is a fundamental problem in computer vision, with applications in many computer vision tasks, such as visual SLAM and action recognition. This paper introduces a novel multi-body feature tracker that exploits a multi-body rigidity assumption to improve tracking robustness under a general perspective camera model. A conventional approach to addressing this problem would consist of alternating between solving two subtasks: motion segmentation and feature tracking under rigidity constraints for each segment. This approach, however, requires knowing the number of motions, as well as assigning points to motion groups, which is typically sensitive to the motion estimates. By contrast, here, we introduce a segmentation-free solution to multi-body feature tracking that bypasses the motion assignment step and reduces to solving a series of subproblems with closed-form solutions. Our experiments demonstrate the benefits of our approach in terms of tracking accuracy and robustness to noise. |
| Tasks | Motion Segmentation, Temporal Action Localization |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00110v2 |
| http://arxiv.org/pdf/1603.00110v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-multi-body-feature-tracker-a |
| Repo | |
| Framework | |
Representation Learning Models for Entity Search
| Title | Representation Learning Models for Entity Search |
| Authors | Shijia E, Yang Xiang, Mohan Zhang |
| Abstract | We focus on the problem of learning distributed representations for entity search queries, named entities, and their short descriptions. With our representation learning models, the entity search query, named entity and description can be represented as low-dimensional vectors. Our goal is to develop a simple but effective model that can make the distributed representations of query related entities similar to the query in the vector space. Hence, we propose three kinds of learning strategies, and the difference between them mainly lies in how to deal with the relationship between an entity and its description. We analyze the strengths and weaknesses of each learning strategy and validate our methods on public datasets which contain four kinds of named entities, i.e., movies, TV shows, restaurants and celebrities. The experimental results indicate that our proposed methods can adapt to different types of entity search queries, and outperform the current state-of-the-art methods based on keyword matching and vanilla word2vec models. Besides, the proposed methods can be trained fast and be easily extended to other similar tasks. |
| Tasks | Representation Learning |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09091v3 |
| http://arxiv.org/pdf/1610.09091v3.pdf | |
| PWC | https://paperswithcode.com/paper/representation-learning-models-for-entity |
| Repo | |
| Framework | |
Robustly representing uncertainty in deep neural networks through sampling
| Title | Robustly representing uncertainty in deep neural networks through sampling |
| Authors | Patrick McClure, Nikolaus Kriegeskorte |
| Abstract | As deep neural networks (DNNs) are applied to increasingly challenging problems, they will need to be able to represent their own uncertainty. Modeling uncertainty is one of the key features of Bayesian methods. Using Bernoulli dropout with sampling at prediction time has recently been proposed as an efficient and well performing variational inference method for DNNs. However, sampling from other multiplicative noise based variational distributions has not been investigated in depth. We evaluated Bayesian DNNs trained with Bernoulli or Gaussian multiplicative masking of either the units (dropout) or the weights (dropconnect). We tested the calibration of the probabilistic predictions of Bayesian convolutional neural networks (CNNs) on MNIST and CIFAR-10. Sampling at prediction time increased the calibration of the DNNs’ probabalistic predictions. Sampling weights, whether Gaussian or Bernoulli, led to more robust representation of uncertainty compared to sampling of units. However, using either Gaussian or Bernoulli dropout led to increased test set classification accuracy. Based on these findings we used both Bernoulli dropout and Gaussian dropconnect concurrently, which we show approximates the use of a spike-and-slab variational distribution without increasing the number of learned parameters. We found that spike-and-slab sampling had higher test set performance than Gaussian dropconnect and more robustly represented its uncertainty compared to Bernoulli dropout. |
| Tasks | Calibration |
| Published | 2016-11-05 |
| URL | http://arxiv.org/abs/1611.01639v7 |
| http://arxiv.org/pdf/1611.01639v7.pdf | |
| PWC | https://paperswithcode.com/paper/robustly-representing-uncertainty-in-deep |
| Repo | |
| Framework | |
Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks
| Title | Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks |
| Authors | James Garland, David Gregg |
| Abstract | Convolutional Neural Networks (CNNs) are one of the most successful deep machine learning technologies for processing image, voice and video data. CNNs require large amounts of processing capacity and memory, which can exceed the resources of low power mobile and embedded systems. Several designs for hardware accelerators have been proposed for CNNs which typically contain large numbers of Multiply Accumulate (MAC) units. One approach to reducing data sizes and memory traffic in CNN accelerators is “weight sharing”, where the full range of values in a trained CNN are put in bins and the bin index is stored instead of the original weight value. In this paper we propose a novel MAC circuit that exploits binning in weight-sharing CNNs. Rather than computing the MAC directly we instead count the frequency of each weight and place it in a bin. We then compute the accumulated value in a subsequent multiply phase. This allows hardware multipliers in the MAC circuit to be replaced with adders and selection logic. Experiments show that for the same clock speed our approach results in fewer gates, smaller logic, and reduced power. |
| Tasks | |
| Published | 2016-08-30 |
| URL | http://arxiv.org/abs/1609.05132v4 |
| http://arxiv.org/pdf/1609.05132v4.pdf | |
| PWC | https://paperswithcode.com/paper/low-complexity-multiply-accumulate-unit-for |
| Repo | |
| Framework | |
Analysis of Kelner and Levin graph sparsification algorithm for a streaming setting
| Title | Analysis of Kelner and Levin graph sparsification algorithm for a streaming setting |
| Authors | Daniele Calandriello, Alessandro Lazaric, Michal Valko |
| Abstract | We derive a new proof to show that the incremental resparsification algorithm proposed by Kelner and Levin (2013) produces a spectral sparsifier in high probability. We rigorously take into account the dependencies across subsequent resparsifications using martingale inequalities, fixing a flaw in the original analysis. |
| Tasks | |
| Published | 2016-09-13 |
| URL | http://arxiv.org/abs/1609.03769v1 |
| http://arxiv.org/pdf/1609.03769v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-kelner-and-levin-graph |
| Repo | |
| Framework | |
Dendritic Spine Shape Analysis: A Clustering Perspective
| Title | Dendritic Spine Shape Analysis: A Clustering Perspective |
| Authors | Muhammad Usman Ghani, Ertunc Erdil, Sumeyra Demir Kanik, Ali Ozgur Argunsah, Anna Felicity Hobbiss, Inbal Israely, Devrim Unay, Tolga Tasdizen, Mujdat Cetin |
| Abstract | Functional properties of neurons are strongly coupled with their morphology. Changes in neuronal activity alter morphological characteristics of dendritic spines. First step towards understanding the structure-function relationship is to group spines into main spine classes reported in the literature. Shape analysis of dendritic spines can help neuroscientists understand the underlying relationships. Due to unavailability of reliable automated tools, this analysis is currently performed manually which is a time-intensive and subjective task. Several studies on spine shape classification have been reported in the literature, however, there is an on-going debate on whether distinct spine shape classes exist or whether spines should be modeled through a continuum of shape variations. Another challenge is the subjectivity and bias that is introduced due to the supervised nature of classification approaches. In this paper, we aim to address these issues by presenting a clustering perspective. In this context, clustering may serve both confirmation of known patterns and discovery of new ones. We perform cluster analysis on two-photon microscopic images of spines using morphological, shape, and appearance based features and gain insights into the spine shape analysis problem. We use histogram of oriented gradients (HOG), disjunctive normal shape models (DNSM), morphological features, and intensity profile based features for cluster analysis. We use x-means to perform cluster analysis that selects the number of clusters automatically using the Bayesian information criterion (BIC). For all features, this analysis produces 4 clusters and we observe the formation of at least one cluster consisting of spines which are difficult to be assigned to a known class. This observation supports the argument of intermediate shape types. |
| Tasks | |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05523v1 |
| http://arxiv.org/pdf/1607.05523v1.pdf | |
| PWC | https://paperswithcode.com/paper/dendritic-spine-shape-analysis-a-clustering |
| Repo | |
| Framework | |
A Flexible Primal-Dual Toolbox
| Title | A Flexible Primal-Dual Toolbox |
| Authors | Hendrik Dirks |
| Abstract | \textbf{FlexBox} is a flexible MATLAB toolbox for finite dimensional convex variational problems in image processing and beyond. Such problems often consist of non-differentiable parts and involve linear operators. The toolbox uses a primal-dual scheme to avoid (computationally) inefficient operator inversion and to get reliable error estimates. From the user-side, \textbf{FlexBox} expects the primal formulation of the problem, automatically decouples operators and dualizes the problem. For large-scale problems, \textbf{FlexBox} also comes with a \cpp-module, which can be used stand-alone or together with MATLAB via MEX-interfaces. Besides various pre-implemented data-fidelities and regularization-terms, \textbf{FlexBox} is able to handle arbitrary operators while being easily extendable, due to its object-oriented design. The toolbox is available at \href{http://www.flexbox.im}{http://www.flexbox.im} |
| Tasks | |
| Published | 2016-03-18 |
| URL | http://arxiv.org/abs/1603.05835v2 |
| http://arxiv.org/pdf/1603.05835v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-flexible-primal-dual-toolbox |
| Repo | |
| Framework | |
