Paper Group ANR 924
Did William Shakespeare and Thomas Kyd Write Edward III?. Design and implementation of smart cooking based on amazon echo. Automatic Metric Validation for Grammatical Error Correction. Manifold Structured Prediction. Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference. gl2vec: Learning Feature Repr …
Did William Shakespeare and Thomas Kyd Write Edward III?
| Title | Did William Shakespeare and Thomas Kyd Write Edward III? |
| Authors | David Kernot, Terry Bossomaier, Roger Bradbury |
| Abstract | William Shakespeare is believed to be a significant author in the anonymous play, The Reign of King Edward III, published in 1596. However, recently, Thomas Kyd, has been suggested as the primary author. Using a neurolinguistics approach to authorship identification we use a four-feature technique, RPAS, to convert the 19 scenes in Edward III into a multi-dimensional vector. Three complementary analytical techniques are applied to cluster the data and reduce single technique bias before an alternate method, seriation, is used to measure the distances between clusters and test the strength of the connections. We find the multivariate techniques robust and are able to allocate up to 14 scenes to Thomas Kyd, and further question if scenes long believed to be Shakespeare’s are not his. |
| Tasks | |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.04017v1 |
| http://arxiv.org/pdf/1801.04017v1.pdf | |
| PWC | https://paperswithcode.com/paper/did-william-shakespeare-and-thomas-kyd-write |
| Repo | |
| Framework | |
Design and implementation of smart cooking based on amazon echo
| Title | Design and implementation of smart cooking based on amazon echo |
| Authors | Lin Xiaoguang, Yang Yong, Zhang Ju |
| Abstract | Smart cooking based on Amazon Echo uses the internet of things and cloud computing to assist in cooking food. People may speak to Amazon Echo during the cooking in order to get the information and situation of the cooking. Amazon Echo recognizes what people say, then transfers the information to the cloud services, and speaks to people the results that cloud services make by querying the embedded cooking knowledge and achieving the information of intelligent kitchen devices online. An intelligent food thermometer and its mobile application are well-designed and implemented to monitor the temperature of cooking food. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01375v1 |
| http://arxiv.org/pdf/1812.01375v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-and-implementation-of-smart-cooking |
| Repo | |
| Framework | |
Automatic Metric Validation for Grammatical Error Correction
| Title | Automatic Metric Validation for Grammatical Error Correction |
| Authors | Leshem Choshen, Omri Abend |
| Abstract | Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties with existing practices. Experiments with \maege\ shed a new light on metric quality, showing for example that the standard $M^2$ metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analysis of metric behavior, showing that correcting some types of errors is consistently penalized by existing metrics. |
| Tasks | Grammatical Error Correction |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1804.11225v2 |
| http://arxiv.org/pdf/1804.11225v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-metric-validation-for-grammatical |
| Repo | |
| Framework | |
Manifold Structured Prediction
| Title | Manifold Structured Prediction |
| Authors | Alessandro Rudi, Carlo Ciliberto, Gian Maria Marconi, Lorenzo Rosasco |
| Abstract | Structured prediction provides a general framework to deal with supervised problems where the outputs have semantically rich structure. While classical approaches consider finite, albeit potentially huge, output spaces, in this paper we discuss how structured prediction can be extended to a continuous scenario. Specifically, we study a structured prediction approach to manifold valued regression. We characterize a class of problems for which the considered approach is statistically consistent and study how geometric optimization can be used to compute the corresponding estimator. Promising experimental results on both simulated and real data complete our study. |
| Tasks | Structured Prediction |
| Published | 2018-06-26 |
| URL | http://arxiv.org/abs/1806.09908v1 |
| http://arxiv.org/pdf/1806.09908v1.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-structured-prediction |
| Repo | |
| Framework | |
Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference
| Title | Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference |
| Authors | Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis |
| Abstract | Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e.g., meteorological and traffic information. In this work, we focus on street-level air quality inference by utilizing data collected by mobile stations. We formulate air quality inference in this setting as a graph-based matrix completion problem and propose a novel variational model based on graph convolutional autoencoders. Our model captures effectively the spatio-temporal correlation of the measurements and does not depend on the availability of additional information apart from the street-network topology. Experiments on a real air quality dataset, collected with mobile stations, shows that the proposed model outperforms state-of-the-art approaches. |
| Tasks | Air Quality Inference, Matrix Completion |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01662v1 |
| http://arxiv.org/pdf/1811.01662v1.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-completion-with-variational-graph |
| Repo | |
| Framework | |
gl2vec: Learning Feature Representation Using Graphlets for Directed Networks
| Title | gl2vec: Learning Feature Representation Using Graphlets for Directed Networks |
| Authors | Kun Tu, Jian Li, Don Towsley, Dave Braines, Liam Turner |
| Abstract | Learning network representations has a variety of applications, such as network classification. Most existing work in this area focuses on static undirected networks and does not account for presence of directed edges or temporal changes. Furthermore, most work focuses on node representations that do poorly on tasks like network classification. In this paper, we propose a novel network embedding methodology, {\emph{gl2vec}}, for network classification in both static and temporal directed networks. \emph{gl2vec} constructs vectors for feature representation using static or temporal network graphlet distributions and a null model for comparing them against random graphs. We demonstrate the efficacy and usability of \emph{gl2vec} over existing state-of-the-art methods on network classification tasks such as network type classification and subgraph identification in several real-world static and temporal directed networks. We argue that \emph{gl2vec} provides additional network features that are not captured by state-of-the-art methods, which can significantly improve their classification accuracy by up to $10%$ in real-world applications such as detecting departments for subgraphs in an email network or identifying mobile users given their app switching behaviors represented as static or temporal directed networks. |
| Tasks | Learning Network Representations, Network Embedding |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05473v2 |
| http://arxiv.org/pdf/1812.05473v2.pdf | |
| PWC | https://paperswithcode.com/paper/gl2vec-learning-feature-representation-using |
| Repo | |
| Framework | |
Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning
| Title | Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning |
| Authors | Maurice Yang, Mahmoud Faraj, Assem Hussein, Vincent Gaudet |
| Abstract | The recent trend toward increasingly deep convolutional neural networks (CNNs) leads to a higher demand of computational power and memory storage. Consequently, the deployment of CNNs in hardware has become more challenging. In this paper, we propose an Intra-Kernel Regular (IKR) pruning scheme to reduce the size and computational complexity of the CNNs by removing redundant weights at a fine-grained level. Unlike other pruning methods such as Fine-Grained pruning, IKR pruning maintains regular kernel structures that are exploitable in a hardware accelerator. Experimental results demonstrate up to 10x parameter reduction and 7x computational reduction at a cost of less than 1% degradation in accuracy versus the un-pruned case. |
| Tasks | |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05909v1 |
| http://arxiv.org/pdf/1803.05909v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-hardware-realization-of |
| Repo | |
| Framework | |
Localisation via Deep Imagination: learn the features not the map
| Title | Localisation via Deep Imagination: learn the features not the map |
| Authors | Jaime Spencer, Oscar Mendez, Richard Bowden, Simon Hadfield |
| Abstract | How many times does a human have to drive through the same area to become familiar with it? To begin with, we might first build a mental model of our surroundings. Upon revisiting this area, we can use this model to extrapolate to new unseen locations and imagine their appearance. Based on this, we propose an approach where an agent is capable of modelling new environments after a single visitation. To this end, we introduce “Deep Imagination”, a combination of classical Visual-based Monte Carlo Localisation and deep learning. By making use of a feature embedded 3D map, the system can “imagine” the view from any novel location. These “imagined” views are contrasted with the current observation in order to estimate the agent’s current location. In order to build the embedded map, we train a deep Siamese Fully Convolutional U-Net to perform dense feature extraction. By training these features to be generic, no additional training or fine tuning is required to adapt to new environments. Our results demonstrate the generality and transfer capability of our learnt dense features by training and evaluating on multiple datasets. Additionally, we include several visualizations of the feature representations and resulting 3D maps, as well as their application to localisation. |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07583v1 |
| http://arxiv.org/pdf/1811.07583v1.pdf | |
| PWC | https://paperswithcode.com/paper/localisation-via-deep-imagination-learn-the |
| Repo | |
| Framework | |
Improved Density-Based Spatio–Textual Clustering on Social Media
| Title | Improved Density-Based Spatio–Textual Clustering on Social Media |
| Authors | Minh D. Nguyen, Won-Yong Shin |
| Abstract | DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio–textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not include a POI name or its semantically coherent variations, respectively. By leveraging the proportion of POI-relevant and POI-irrelevant tweets, the proposed algorithm demonstrates much higher clustering performance than the DBSCAN case in terms of $\mathcal{F}_1$ score and its variants. While DBSTexC performs exactly as DBSCAN with the textually homogeneous inputs, it far outperforms DBSCAN with the textually heterogeneous inputs. Furthermore, to further improve the clustering quality by fully capturing the geographic distribution of tweets, we present fuzzy DBSTexC (F-DBSTexC), an extension of DBSTexC, which incorporates the notion of fuzzy clustering into the DBSTexC. We then demonstrate the robustness of F-DBSTexC via intensive experiments. The computational complexity of our algorithms is also analytically and numerically shown. |
| Tasks | |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05522v1 |
| http://arxiv.org/pdf/1806.05522v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-density-based-spatio-textual |
| Repo | |
| Framework | |
Geometrical analysis of polynomial lens distortion models
| Title | Geometrical analysis of polynomial lens distortion models |
| Authors | José I. Ronda, Antonio Valdés |
| Abstract | Polynomial functions are a usual choice to model the nonlinearity of lenses. Typically, these models are obtained through physical analysis of the lens system or on purely empirical grounds. The aim of this work is to facilitate an alternative approach to the selection or design of these models based on establishing a priori the desired geometrical properties of the distortion functions. With this purpose we obtain all the possible isotropic linear models and also those that are formed by functions with symmetry with respect to some axis. In this way, the classical models (decentering, thin prism distortion) are found to be particular instances of the family of models found by geometric considerations. These results allow to find generalizations of the most usually employed models while preserving the desired geometrical properties. Our results also provide a better understanding of the geometric properties of the models employed in the most usual computer vision software libraries. |
| Tasks | |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.03584v2 |
| http://arxiv.org/pdf/1804.03584v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometrical-analysis-of-polynomial-lens |
| Repo | |
| Framework | |
Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration
| Title | Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration |
| Authors | Tathagata Chakraborti, Subbarao Kambhampati |
| Abstract | Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up pathways for manipulating and exploiting the human in the hopes of achieving some greater good, especially when the intent or values of the AI and the human are not aligned or when they have an asymmetrical relationship with respect to knowledge or computation power. In fact, such behavior does not necessarily require any malicious intent but can rather be borne out of cooperative scenarios. It is also beyond simple misinterpretation of intents, as in the case of value alignment problems, and thus can be effectively engineered if desired. Such techniques already exist and pose several unresolved ethical and moral questions with regards to the design of autonomy. In this paper, we illustrate some of these issues in a teaming scenario and investigate how they are perceived by participants in a thought experiment. |
| Tasks | |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.09854v1 |
| http://arxiv.org/pdf/1801.09854v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-the-greater-good-on-mental |
| Repo | |
| Framework | |
On variation of gradients of deep neural networks
| Title | On variation of gradients of deep neural networks |
| Authors | Yongdai Kim, Dongha Kim |
| Abstract | We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks. We prove that the largest variation of a deep neural network with ReLU activation function arises when the layer with the fewest nodes changes its activation pattern. An important implication is that deep neural network is a useful tool to generate functions most of whose variations are concentrated on a smaller area of the input space near the boundaries corresponding to the layer with the fewest nodes. In turn, this property makes the function more invariant to input transformation. That is, our theoretical result gives a clue about how to design the architecture of a deep neural network to increase complexity and transformation invariancy simultaneously. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00308v1 |
| http://arxiv.org/pdf/1812.00308v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-variation-of-gradients-of-deep-neural |
| Repo | |
| Framework | |
Proximal algorithms for large-scale statistical modeling and sensor/actuator selection
| Title | Proximal algorithms for large-scale statistical modeling and sensor/actuator selection |
| Authors | Armin Zare, Hesameddin Mohammadi, Neil K. Dhingra, Tryphon T. Georgiou, Mihailo R. Jovanović |
| Abstract | Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs. We examine two such representative problems and show that they can be formulated in a similar manner. The first, in statistical modeling, seeks to reconcile observed statistics by suitably and minimally perturbing prior dynamics. The second seeks to optimally select a subset of available sensors and actuators for control purposes. To address modeling and control of large-scale systems we develop a unified algorithmic framework using proximal methods. Our customized algorithms exploit problem structure and allow handling statistical modeling, as well as sensor and actuator selection, for substantially larger scales than what is amenable to current general-purpose solvers. We establish linear convergence of the proximal gradient algorithm, draw contrast between the proposed proximal algorithms and alternating direction method of multipliers, and provide examples that illustrate the merits and effectiveness of our framework. |
| Tasks | |
| Published | 2018-07-04 |
| URL | https://arxiv.org/abs/1807.01739v4 |
| https://arxiv.org/pdf/1807.01739v4.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-algorithms-for-large-scale |
| Repo | |
| Framework | |
A Fully Attention-Based Information Retriever
| Title | A Fully Attention-Based Information Retriever |
| Authors | Alvaro Henrique Chaim Correia, Jorge Luiz Moreira Silva, Thiago de Castro Martins, Fabio Gagliardi Cozman |
| Abstract | Recurrent neural networks are now the state-of-the-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have equipped feedforward networks with similar capabilities, hence enabling faster computations due to the increase in the number of operations that can be parallelized. We explore this new type of architecture in the domain of question-answering and propose a novel approach that we call Fully Attention Based Information Retriever (FABIR). We show that FABIR achieves competitive results in the Stanford Question Answering Dataset (SQuAD) while having fewer parameters and being faster at both learning and inference than rival methods. |
| Tasks | Question Answering |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09580v1 |
| http://arxiv.org/pdf/1810.09580v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fully-attention-based-information-retriever |
| Repo | |
| Framework | |
Face Mask Extraction in Video Sequence
| Title | Face Mask Extraction in Video Sequence |
| Authors | Yujiang Wang, Bingnan Luo, Jie Shen, Maja Pantic |
| Abstract | Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence. Comparing to landmark-based sparse face shape representation, our method can produce the segmentation masks of individual facial components, which can better reflect their detailed shape variations. By integrating Convolutional LSTM (ConvLSTM) algorithm with Fully Convolutional Networks (FCN), our new ConvLSTM-FCN model works on a per-sequence basis and takes advantage of the temporal correlation in video clips. In addition, we also propose a novel loss function, called Segmentation Loss, to directly optimise the Intersection over Union (IoU) performances. In practice, to further increase segmentation accuracy, one primary model and two additional models were trained to focus on the face, eyes, and mouth regions, respectively. Our experiment shows the proposed method has achieved a 16.99% relative improvement (from 54.50% to 63.76% mean IoU) over the baseline FCN model on the 300 Videos in the Wild (300VW) dataset. |
| Tasks | Semantic Segmentation |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09207v2 |
| http://arxiv.org/pdf/1807.09207v2.pdf | |
| PWC | https://paperswithcode.com/paper/face-mask-extraction-in-video-sequence |
| Repo | |
| Framework | |
