Paper Group ANR 107
Science Question Answering using Instructional Materials. Exploration for Multi-task Reinforcement Learning with Deep Generative Models. ICE: Information Credibility Evaluation on Social Media via Representation Learning. Development of an Ideal Observer that Incorporates Nuisance Parameters and Processes List-Mode Data. Sparse Estimation of Multiv …
Science Question Answering using Instructional Materials
| Title | Science Question Answering using Instructional Materials |
| Authors | Mrinmaya Sachan, Avinava Dubey, Eric P. Xing |
| Abstract | We provide a solution for elementary science test using instructional materials. We posit that there is a hidden structure that explains the correctness of an answer given the question and instructional materials and present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs and instructional materials), and uses what it learns to answer novel elementary science questions. Our evaluation shows that our framework outperforms several strong baselines. |
| Tasks | Question Answering |
| Published | 2016-02-13 |
| URL | http://arxiv.org/abs/1602.04375v2 |
| http://arxiv.org/pdf/1602.04375v2.pdf | |
| PWC | https://paperswithcode.com/paper/science-question-answering-using |
| Repo | |
| Framework | |
Exploration for Multi-task Reinforcement Learning with Deep Generative Models
| Title | Exploration for Multi-task Reinforcement Learning with Deep Generative Models |
| Authors | Sai Praveen Bangaru, JS Suhas, Balaraman Ravindran |
| Abstract | Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We evaluate our method on a new set of environments and provide intuitive interpretation of our results. |
| Tasks | |
| Published | 2016-11-29 |
| URL | http://arxiv.org/abs/1611.09894v1 |
| http://arxiv.org/pdf/1611.09894v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploration-for-multi-task-reinforcement |
| Repo | |
| Framework | |
ICE: Information Credibility Evaluation on Social Media via Representation Learning
| Title | ICE: Information Credibility Evaluation on Social Media via Representation Learning |
| Authors | Qiang Liu, Shu Wu, Feng Yu, Liang Wang, Tieniu Tan |
| Abstract | With the rapid growth of social media, rumors are also spreading widely on social media and bring harm to people’s daily life. Nowadays, information credibility evaluation has drawn attention from academic and industrial communities. Current methods mainly focus on feature engineering and achieve some success. However, feature engineering based methods require a lot of labor and cannot fully reveal the underlying relations among data. In our viewpoint, the key elements of user behaviors for evaluating credibility are concluded as “who”, “what”, “when”, and “how”. These existing methods cannot model the correlation among different key elements during the spreading of microblogs. In this paper, we propose a novel representation learning method, Information Credibility Evaluation (ICE), to learn representations of information credibility on social media. In ICE, latent representations are learnt for modeling user credibility, behavior types, temporal properties, and comment attitudes. The aggregation of these factors in the microblog spreading process yields the representation of a user’s behavior, and the aggregation of these dynamic representations generates the credibility representation of an event spreading on social media. Moreover, a pairwise learning method is applied to maximize the credibility difference between rumors and non-rumors. To evaluate the performance of ICE, we conduct experiments on a Sina Weibo data set, and the experimental results show that our ICE model outperforms the state-of-the-art methods. |
| Tasks | Feature Engineering, Representation Learning |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09226v4 |
| http://arxiv.org/pdf/1609.09226v4.pdf | |
| PWC | https://paperswithcode.com/paper/ice-information-credibility-evaluation-on |
| Repo | |
| Framework | |
Development of an Ideal Observer that Incorporates Nuisance Parameters and Processes List-Mode Data
| Title | Development of an Ideal Observer that Incorporates Nuisance Parameters and Processes List-Mode Data |
| Authors | Christopher J. MacGahan, Matthew A. Kupinski, Nathan R. Hilton, Erik M. Brubaker, William C. Johnson |
| Abstract | Observer models were developed to process data in list-mode format in order to perform binary discrimination tasks for use in an arms-control-treaty context. Data used in this study was generated using GEANT4 Monte Carlo simulations for photons using custom models of plutonium inspection objects and a radiation imaging system. Observer model performance was evaluated and presented using the area under the receiver operating characteristic curve. The ideal observer was studied under both signal-known-exactly conditions and in the presence of unknowns such as object orientation and absolute count-rate variability; when these additional sources of randomness were present, their incorporation into the observer yielded superior performance. |
| Tasks | |
| Published | 2016-02-02 |
| URL | http://arxiv.org/abs/1602.01449v1 |
| http://arxiv.org/pdf/1602.01449v1.pdf | |
| PWC | https://paperswithcode.com/paper/development-of-an-ideal-observer-that |
| Repo | |
| Framework | |
Sparse Estimation of Multivariate Poisson Log-Normal Models from Count Data
| Title | Sparse Estimation of Multivariate Poisson Log-Normal Models from Count Data |
| Authors | Hao Wu, Xinwei Deng, Naren Ramakrishnan |
| Abstract | Modeling data with multivariate count responses is a challenging problem due to the discrete nature of the responses. Existing methods for univariate count responses cannot be easily extended to the multivariate case since the dependency among multiple responses needs to be properly accommodated. In this paper, we propose a multivariate Poisson log-normal regression model for multivariate data with count responses. By simultaneously estimating the regression coefficients and inverse covariance matrix over the latent variables with an efficient Monte Carlo EM algorithm, the proposed regression model takes advantages of association among multiple count responses to improve the model prediction performance. Simulation studies and applications to real world data are conducted to systematically evaluate the performance of the proposed method in comparison with conventional methods. |
| Tasks | |
| Published | 2016-02-22 |
| URL | http://arxiv.org/abs/1602.07337v3 |
| http://arxiv.org/pdf/1602.07337v3.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-estimation-of-multivariate-poisson-log |
| Repo | |
| Framework | |
Personalized Prognostic Models for Oncology: A Machine Learning Approach
| Title | Personalized Prognostic Models for Oncology: A Machine Learning Approach |
| Authors | David Dooling, Angela Kim, Barbara McAneny, Jennifer Webster |
| Abstract | We have applied a little-known data transformation to subsets of the Surveillance, Epidemiology, and End Results (SEER) publically available data of the National Cancer Institute (NCI) to make it suitable input to standard machine learning classifiers. This transformation properly treats the right-censored data in the SEER data and the resulting Random Forest and Multi-Layer Perceptron models predict full survival curves. Treating the 6, 12, and 60 months points of the resulting survival curves as 3 binary classifiers, the 18 resulting classifiers have AUC values ranging from .765 to .885. Further evidence that the models have generalized well from the training data is provided by the extremely high levels of agreement between the random forest and neural network models predictions on the 6, 12, and 60 month binary classifiers. |
| Tasks | Epidemiology |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.07369v1 |
| http://arxiv.org/pdf/1606.07369v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-prognostic-models-for-oncology-a |
| Repo | |
| Framework | |
Mixed context networks for semantic segmentation
| Title | Mixed context networks for semantic segmentation |
| Authors | Haiming Sun, Di Xie, Shiliang Pu |
| Abstract | Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different layers plays an important role in these dense prediction models, as these features contains information of different levels. A number of models have been proposed to show how to use these features. However, what is the best architecture to make use of features of different layers is still a question. In this paper, we propose a module, called mixed context network, and show that our presented system outperforms most existing semantic segmentation systems by making use of this module. |
| Tasks | Semantic Segmentation |
| Published | 2016-10-19 |
| URL | http://arxiv.org/abs/1610.05854v1 |
| http://arxiv.org/pdf/1610.05854v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixed-context-networks-for-semantic |
| Repo | |
| Framework | |
Person Re-identification in the Wild
| Title | Person Re-identification in the Wild |
| Authors | Liang Zheng, Hengheng Zhang, Shaoyan Sun, Manmohan Chandraker, Yi Yang, Qi Tian |
| Abstract | We present a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification. We make three distinct contributions. First, a new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized cameras. It contains 932 identities and 11,816 frames in which pedestrians are annotated with their bounding box positions and identities. Extensive benchmarking results are presented on this dataset. Second, we show that pedestrian detection aids re-identification through two simple yet effective improvements: a discriminatively trained ID-discriminative Embedding (IDE) in the person subspace using convolutional neural network (CNN) features and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Third, we derive insights in evaluating detector performance for the particular scenario of accurate person re-identification. |
| Tasks | Pedestrian Detection, Person Recognition, Person Re-Identification |
| Published | 2016-04-09 |
| URL | http://arxiv.org/abs/1604.02531v2 |
| http://arxiv.org/pdf/1604.02531v2.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-in-the-wild |
| Repo | |
| Framework | |
Detecting Sarcasm in Multimodal Social Platforms
| Title | Detecting Sarcasm in Multimodal Social Platforms |
| Authors | Rossano Schifanella, Paloma de Juan, Joel Tetreault, Liangliang Cao |
| Abstract | Sarcasm is a peculiar form of sentiment expression, where the surface sentiment differs from the implied sentiment. The detection of sarcasm in social media platforms has been applied in the past mainly to textual utterances where lexical indicators (such as interjections and intensifiers), linguistic markers, and contextual information (such as user profiles, or past conversations) were used to detect the sarcastic tone. However, modern social media platforms allow to create multimodal messages where audiovisual content is integrated with the text, making the analysis of a mode in isolation partial. In our work, we first study the relationship between the textual and visual aspects in multimodal posts from three major social media platforms, i.e., Instagram, Tumblr and Twitter, and we run a crowdsourcing task to quantify the extent to which images are perceived as necessary by human annotators. Moreover, we propose two different computational frameworks to detect sarcasm that integrate the textual and visual modalities. The first approach exploits visual semantics trained on an external dataset, and concatenates the semantics features with state-of-the-art textual features. The second method adapts a visual neural network initialized with parameters trained on ImageNet to multimodal sarcastic posts. Results show the positive effect of combining modalities for the detection of sarcasm across platforms and methods. |
| Tasks | |
| Published | 2016-08-08 |
| URL | http://arxiv.org/abs/1608.02289v1 |
| http://arxiv.org/pdf/1608.02289v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-sarcasm-in-multimodal-social |
| Repo | |
| Framework | |
Fast Calculation of the Knowledge Gradient for Optimization of Deterministic Engineering Simulations
| Title | Fast Calculation of the Knowledge Gradient for Optimization of Deterministic Engineering Simulations |
| Authors | Joachim van der Herten, Ivo Couckuyt, Dirk Deschrijver, Tom Dhaene |
| Abstract | A novel efficient method for computing the Knowledge-Gradient policy for Continuous Parameters (KGCP) for deterministic optimization is derived. The differences with Expected Improvement (EI), a popular choice for Bayesian optimization of deterministic engineering simulations, are explored. Both policies and the Upper Confidence Bound (UCB) policy are compared on a number of benchmark functions including a problem from structural dynamics. It is empirically shown that KGCP has similar performance as the EI policy for many problems, but has better convergence properties for complex (multi-modal) optimization problems as it emphasizes more on exploration when the model is confident about the shape of optimal regions. In addition, the relationship between Maximum Likelihood Estimation (MLE) and slice sampling for estimation of the hyperparameters of the underlying models, and the complexity of the problem at hand, is studied. |
| Tasks | |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04550v1 |
| http://arxiv.org/pdf/1608.04550v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-calculation-of-the-knowledge-gradient |
| Repo | |
| Framework | |
Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling
| Title | Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling |
| Authors | Christopher De Sa, Kunle Olukotun, Christopher Ré |
| Abstract | Gibbs sampling is a Markov chain Monte Carlo technique commonly used for estimating marginal distributions. To speed up Gibbs sampling, there has recently been interest in parallelizing it by executing asynchronously. While empirical results suggest that many models can be efficiently sampled asynchronously, traditional Markov chain analysis does not apply to the asynchronous case, and thus asynchronous Gibbs sampling is poorly understood. In this paper, we derive a better understanding of the two main challenges of asynchronous Gibbs: bias and mixing time. We show experimentally that our theoretical results match practical outcomes. |
| Tasks | |
| Published | 2016-02-24 |
| URL | http://arxiv.org/abs/1602.07415v3 |
| http://arxiv.org/pdf/1602.07415v3.pdf | |
| PWC | https://paperswithcode.com/paper/ensuring-rapid-mixing-and-low-bias-for |
| Repo | |
| Framework | |
Augmenting Supervised Emotion Recognition with Rule-Based Decision Model
| Title | Augmenting Supervised Emotion Recognition with Rule-Based Decision Model |
| Authors | Amol Patwardhan, Gerald Knapp |
| Abstract | The aim of this research is development of rule based decision model for emotion recognition. This research also proposes using the rules for augmenting inter-corporal recognition accuracy in multimodal systems that use supervised learning techniques. The classifiers for such learning based recognition systems are susceptible to over fitting and only perform well on intra-corporal data. To overcome the limitation this research proposes using rule based model as an additional modality. The rules were developed using raw feature data from visual channel, based on human annotator agreement and existing studies that have attributed movement and postures to emotions. The outcome of the rule evaluations was combined during the decision phase of emotion recognition system. The results indicate rule based emotion recognition augment recognition accuracy of learning based systems and also provide better recognition rate across inter corpus emotion test data. |
| Tasks | Emotion Recognition |
| Published | 2016-07-09 |
| URL | http://arxiv.org/abs/1607.02660v1 |
| http://arxiv.org/pdf/1607.02660v1.pdf | |
| PWC | https://paperswithcode.com/paper/augmenting-supervised-emotion-recognition |
| Repo | |
| Framework | |
Comparison and Adaptation of Automatic Evaluation Metrics for Quality Assessment of Re-Speaking
| Title | Comparison and Adaptation of Automatic Evaluation Metrics for Quality Assessment of Re-Speaking |
| Authors | Krzysztof Wołk, Danijel Koržinek |
| Abstract | Re-speaking is a mechanism for obtaining high quality subtitles for use in live broadcast and other public events. Because it relies on humans performing the actual re-speaking, the task of estimating the quality of the results is non-trivial. Most organisations rely on humans to perform the actual quality assessment, but purely automatic methods have been developed for other similar problems, like Machine Translation. This paper will try to compare several of these methods: BLEU, EBLEU, NIST, METEOR, METEOR-PL, TER and RIBES. These will then be matched to the human-derived NER metric, commonly used in re-speaking. |
| Tasks | Machine Translation |
| Published | 2016-01-12 |
| URL | http://arxiv.org/abs/1601.02789v1 |
| http://arxiv.org/pdf/1601.02789v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-and-adaptation-of-automatic |
| Repo | |
| Framework | |
A method for locally approximating regularized iterative tomographic reconstruction methods
| Title | A method for locally approximating regularized iterative tomographic reconstruction methods |
| Authors | D. M. Pelt, K. J. Batenburg |
| Abstract | In many applications of tomography, the acquired projections are either limited in number or contain a significant amount of noise. In these cases, standard reconstruction methods tend to produce artifacts that can make further analysis difficult. Advanced regularized iterative methods, such as total variation minimization, are often able to achieve a higher reconstruction quality by exploiting prior knowledge about the scanned object. In practice, however, these methods often have prohibitively long computation times or large memory requirements. Furthermore, since they are based on minimizing a global objective function, regularized iterative methods need to reconstruct the entire scanned object, even when one is only interested in a (small) region of the reconstructed image. In this paper, we present a method to approximate regularized iterative reconstruction methods inside a (small) region of the scanned object. The method only performs computations inside the region of interest, ensuring low computational requirements. Reconstruction results for different phantom images and types of regularization are given, showing that reconstructions of the proposed local method are almost identical to those of the global regularized iterative methods that are approximated, even for relatively small regions of interest. Furthermore, we show that larger regions can be reconstructed efficiently by reconstructing several small regions in parallel and combining them into a single reconstruction afterwards. |
| Tasks | |
| Published | 2016-04-08 |
| URL | http://arxiv.org/abs/1604.02292v1 |
| http://arxiv.org/pdf/1604.02292v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-method-for-locally-approximating |
| Repo | |
| Framework | |
Machine Learning with Memristors via Thermodynamic RAM
| Title | Machine Learning with Memristors via Thermodynamic RAM |
| Authors | Timothy W. Molter, M. Alexander Nugent |
| Abstract | Thermodynamic RAM (kT-RAM) is a neuromemristive co-processor design based on the theory of AHaH Computing and implemented via CMOS and memristors. The co-processor is a 2-D array of differential memristor pairs (synapses) that can be selectively coupled together (neurons) via the digital bit addressing of the underlying CMOS RAM circuitry. The chip is designed to plug into existing digital computers and be interacted with via a simple instruction set. Anti-Hebbian and Hebbian (AHaH) computing forms the theoretical framework from which a nature-inspired type of computing architecture is built where, unlike von Neumann architectures, memory and processor are physically combined for synaptic operations. Through exploitation of AHaH attractor states, memristor-based circuits converge to attractor basins that represents machine learning solutions such as unsupervised feature learning, supervised classification and anomaly detection. Because kT-RAM eliminates the need to shuttle bits back and forth between memory and processor and can operate at very low voltage levels, it can significantly surpass CPU, GPU, and FPGA performance for synaptic integration and learning operations. Here, we present a memristor technology developed for use in kT-RAM, in particular bi-directional incremental adaptation of conductance via short low-voltage 1.0 V, 1.0 microsecond pulses. |
| Tasks | Anomaly Detection |
| Published | 2016-08-14 |
| URL | http://arxiv.org/abs/1608.04105v1 |
| http://arxiv.org/pdf/1608.04105v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-with-memristors-via |
| Repo | |
| Framework | |
