Paper Group ANR 414
Differentiable Submodular Maximization. Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features. Risk and parameter convergence of logistic regression. Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue. Hand Gesture Detection and Conversion to Speech and Text. …
Differentiable Submodular Maximization
| Title | Differentiable Submodular Maximization |
| Authors | Sebastian Tschiatschek, Aytunc Sahin, Andreas Krause |
| Abstract | We consider learning of submodular functions from data. These functions are important in machine learning and have a wide range of applications, e.g. data summarization, feature selection and active learning. Despite their combinatorial nature, submodular functions can be maximized approximately with strong theoretical guarantees in polynomial time. Typically, learning the submodular function and optimization of that function are treated separately, i.e. the function is first learned using a proxy objective and subsequently maximized. In contrast, we show how to perform learning and optimization jointly. By interpreting the output of greedy maximization algorithms as distributions over sequences of items and smoothening these distributions, we obtain a differentiable objective. In this way, we can differentiate through the maximization algorithms and optimize the model to work well with the optimization algorithm. We theoretically characterize the error made by our approach, yielding insights into the tradeoff of smoothness and accuracy. We demonstrate the effectiveness of our approach for jointly learning and optimizing on synthetic maximum cut data, and on real world applications such as product recommendation and image collection summarization. |
| Tasks | Active Learning, Data Summarization, Feature Selection, Product Recommendation |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01785v2 |
| http://arxiv.org/pdf/1803.01785v2.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-submodular-maximization |
| Repo | |
| Framework | |
Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features
| Title | Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features |
| Authors | Vrindavan Harrison, Marilyn Walker |
| Abstract | Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder–Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous diverse questions on a given sentence. Our model achieves state of the art results of 19.98 Bleu_4 on a benchmark Question Generation dataset, outperforming all previously published results by a significant margin. A human evaluation also shows that these added features improve the quality of the generated questions. |
| Tasks | Coreference Resolution, Named Entity Recognition, Question Generation, Sentence Embedding |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02637v2 |
| http://arxiv.org/pdf/1809.02637v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-generation-of-diverse-questions-using |
| Repo | |
| Framework | |
Risk and parameter convergence of logistic regression
| Title | Risk and parameter convergence of logistic regression |
| Authors | Ziwei Ji, Matus Telgarsky |
| Abstract | Gradient descent, when applied to the task of logistic regression, outputs iterates which are biased to follow a unique ray defined by the data. The direction of this ray is the maximum margin predictor of a maximal linearly separable subset of the data; the gradient descent iterates converge to this ray in direction at the rate $\mathcal{O}(\ln\ln t / \ln t)$. The ray does not pass through the origin in general, and its offset is the bounded global optimum of the risk over the remaining data; gradient descent recovers this offset at a rate $\mathcal{O}((\ln t)^2 / \sqrt{t})$. |
| Tasks | |
| Published | 2018-03-20 |
| URL | https://arxiv.org/abs/1803.07300v3 |
| https://arxiv.org/pdf/1803.07300v3.pdf | |
| PWC | https://paperswithcode.com/paper/risk-and-parameter-convergence-of-logistic |
| Repo | |
| Framework | |
Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue
| Title | Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue |
| Authors | Dieuwke Hupkes, Sanne Bouwmeester, Raquel Fernández |
| Abstract | We investigate how encoder-decoder models trained on a synthetic dataset of task-oriented dialogues process disfluencies, such as hesitations and self-corrections. We find that, contrary to earlier results, disfluencies have very little impact on the task success of seq-to-seq models with attention. Using visualisation and diagnostic classifiers, we analyse the representations that are incrementally built by the model, and discover that models develop little to no awareness of the structure of disfluencies. However, adding disfluencies to the data appears to help the model create clearer representations overall, as evidenced by the attention patterns the different models exhibit. |
| Tasks | |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09178v1 |
| http://arxiv.org/pdf/1808.09178v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysing-the-potential-of-seq-to-seq-models |
| Repo | |
| Framework | |
Hand Gesture Detection and Conversion to Speech and Text
| Title | Hand Gesture Detection and Conversion to Speech and Text |
| Authors | K. Manikandan, Ayush Patidar, Pallav Walia, Aneek Barman Roy |
| Abstract | The hand gestures are one of the typical methods used in sign language. It is very difficult for the hearing-impaired people to communicate with the world. This project presents a solution that will not only automatically recognize the hand gestures but will also convert it into speech and text output so that impaired person can easily communicate with normal people. A camera attached to computer will capture images of hand and the contour feature extraction is used to recognize the hand gestures of the person. Based on the recognized gestures, the recorded soundtrack will be played. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.11997v1 |
| http://arxiv.org/pdf/1811.11997v1.pdf | |
| PWC | https://paperswithcode.com/paper/hand-gesture-detection-and-conversion-to |
| Repo | |
| Framework | |
Variational End-to-End Navigation and Localization
| Title | Variational End-to-End Navigation and Localization |
| Authors | Alexander Amini, Guy Rosman, Sertac Karaman, Daniela Rus |
| Abstract | Deep learning has revolutionized the ability to learn “end-to-end” autonomous vehicle control directly from raw sensory data. While there have been recent extensions to handle forms of navigation instruction, these works are unable to capture the full distribution of possible actions that could be taken and to reason about localization of the robot within the environment. In this paper, we extend end-to-end driving networks with the ability to perform point-to-point navigation as well as probabilistic localization using only noisy GPS data. We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control commands; and (2) a deterministic control command capable of navigating on the route specified within the map. Additionally, we formulate how our model can be used to localize the robot according to correspondences between the map and the observed visual road topology, inspired by the rough localization that human drivers can perform. We test our algorithms on real-world driving data that the vehicle has never driven through before, and integrate our point-to-point navigation algorithms onboard a full-scale autonomous vehicle for real-time performance. Our localization algorithm is also evaluated over a new set of roads and intersections to demonstrates rough pose localization even in situations without any GPS prior. |
| Tasks | |
| Published | 2018-11-25 |
| URL | https://arxiv.org/abs/1811.10119v2 |
| https://arxiv.org/pdf/1811.10119v2.pdf | |
| PWC | https://paperswithcode.com/paper/variational-end-to-end-navigation-and |
| Repo | |
| Framework | |
Why rankings of biomedical image analysis competitions should be interpreted with care
| Title | Why rankings of biomedical image analysis competitions should be interpreted with care |
| Authors | Lena Maier-Hein, Matthias Eisenmann, Annika Reinke, Sinan Onogur, Marko Stankovic, Patrick Scholz, Tal Arbel, Hrvoje Bogunovic, Andrew P. Bradley, Aaron Carass, Carolin Feldmann, Alejandro F. Frangi, Peter M. Full, Bram van Ginneken, Allan Hanbury, Katrin Honauer, Michal Kozubek, Bennett A. Landman, Keno März, Oskar Maier, Klaus Maier-Hein, Bjoern H. Menze, Henning Müller, Peter F. Neher, Wiro Niessen, Nasir Rajpoot, Gregory C. Sharp, Korsuk Sirinukunwattana, Stefanie Speidel, Christian Stock, Danail Stoyanov, Abdel Aziz Taha, Fons van der Sommen, Ching-Wei Wang, Marc-André Weber, Guoyan Zheng, Pierre Jannin, Annette Kopp-Schneider |
| Abstract | International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical analysis of common practices related to the organization of challenges has not yet been performed. In this paper, we present a comprehensive analysis of biomedical image analysis challenges conducted up to now. We demonstrate the importance of challenges and show that the lack of quality control has critical consequences. First, reproducibility and interpretation of the results is often hampered as only a fraction of relevant information is typically provided. Second, the rank of an algorithm is generally not robust to a number of variables such as the test data used for validation, the ranking scheme applied and the observers that make the reference annotations. To overcome these problems, we recommend best practice guidelines and define open research questions to be addressed in the future. |
| Tasks | |
| Published | 2018-06-06 |
| URL | https://arxiv.org/abs/1806.02051v2 |
| https://arxiv.org/pdf/1806.02051v2.pdf | |
| PWC | https://paperswithcode.com/paper/is-the-winner-really-the-best-a-critical |
| Repo | |
| Framework | |
Infinite-Task Learning with RKHSs
| Title | Infinite-Task Learning with RKHSs |
| Authors | Romain Brault, Alex Lambert, Zoltán Szabó, Maxime Sangnier, Florence d’Alché-Buc |
| Abstract | Machine learning has witnessed tremendous success in solving tasks depending on a single hyperparameter. When considering simultaneously a finite number of tasks, multi-task learning enables one to account for the similarities of the tasks via appropriate regularizers. A step further consists of learning a continuum of tasks for various loss functions. A promising approach, called \emph{Parametric Task Learning}, has paved the way in the continuum setting for affine models and piecewise-linear loss functions. In this work, we introduce a novel approach called \emph{Infinite Task Learning} whose goal is to learn a function whose output is a function over the hyperparameter space. We leverage tools from operator-valued kernels and the associated vector-valued RKHSs that provide an explicit control over the role of the hyperparameters, and also allows us to consider new type of constraints. We provide generalization guarantees to the suggested scheme and illustrate its efficiency in cost-sensitive classification, quantile regression and density level set estimation. |
| Tasks | Multi-Task Learning |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08809v3 |
| http://arxiv.org/pdf/1805.08809v3.pdf | |
| PWC | https://paperswithcode.com/paper/infinite-task-learning-with-rkhss |
| Repo | |
| Framework | |
A Temporal Difference Reinforcement Learning Theory of Emotion: unifying emotion, cognition and adaptive behavior
| Title | A Temporal Difference Reinforcement Learning Theory of Emotion: unifying emotion, cognition and adaptive behavior |
| Authors | Joost Broekens |
| Abstract | Emotions are intimately tied to motivation and the adaptation of behavior, and many animal species show evidence of emotions in their behavior. Therefore, emotions must be related to powerful mechanisms that aid survival, and, emotions must be evolutionary continuous phenomena. How and why did emotions evolve in nature, how do events get emotionally appraised, how do emotions relate to cognitive complexity, and, how do they impact behavior and learning? In this article I propose that all emotions are manifestations of reward processing, in particular Temporal Difference (TD) error assessment. Reinforcement Learning (RL) is a powerful computational model for the learning of goal oriented tasks by exploration and feedback. Evidence indicates that RL-like processes exist in many animal species. Key in the processing of feedback in RL is the notion of TD error, the assessment of how much better or worse a situation just became, compared to what was previously expected (or, the estimated gain or loss of utility - or well-being - resulting from new evidence). I propose a TDRL Theory of Emotion and discuss its ramifications for our understanding of emotions in humans, animals and machines, and present psychological, neurobiological and computational evidence in its support. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.08941v1 |
| http://arxiv.org/pdf/1807.08941v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-temporal-difference-reinforcement-learning |
| Repo | |
| Framework | |
Using Chaos in Grey Wolf Optimizer and Application to Prime Factorization
| Title | Using Chaos in Grey Wolf Optimizer and Application to Prime Factorization |
| Authors | Harshit Mehrotra, Dr. Saibal K. Pal |
| Abstract | The Grey Wolf Optimizer (GWO) is a swarm intelligence meta-heuristic algorithm inspired by the hunting behaviour and social hierarchy of grey wolves in nature. This paper analyses the use of chaos theory in this algorithm to improve its ability to escape local optima by replacing the key parameters by chaotic variables. The optimal choice of chaotic maps is then used to apply the Chaotic Grey Wolf Optimizer (CGWO) to the problem of factoring a large semi prime into its prime factors. Assuming the number of digits of the factors to be equal, this is a computationally difficult task upon which the RSA-cryptosystem relies. This work proposes the use of a new objective function to solve the problem and uses the CGWO to optimize it and compute the factors. It is shown that this function performs better than its predecessor for large semi primes and CGWO is an efficient algorithm to optimize it. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04419v1 |
| http://arxiv.org/pdf/1806.04419v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-chaos-in-grey-wolf-optimizer-and |
| Repo | |
| Framework | |
Bayesian Optimization for Dynamic Problems
| Title | Bayesian Optimization for Dynamic Problems |
| Authors | Favour M. Nyikosa, Michael A. Osborne, Stephen J. Roberts |
| Abstract | We propose practical extensions to Bayesian optimization for solving dynamic problems. We model dynamic objective functions using spatiotemporal Gaussian process priors which capture all the instances of the functions over time. Our extensions to Bayesian optimization use the information learnt from this model to guide the tracking of a temporally evolving minimum. By exploiting temporal correlations, the proposed method also determines when to make evaluations, how fast to make those evaluations, and it induces an appropriate budget of steps based on the available information. Lastly, we evaluate our technique on synthetic and real-world problems. |
| Tasks | |
| Published | 2018-03-09 |
| URL | http://arxiv.org/abs/1803.03432v1 |
| http://arxiv.org/pdf/1803.03432v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-for-dynamic-problems |
| Repo | |
| Framework | |
Variational Regularization of Inverse Problems for Manifold-Valued Data
| Title | Variational Regularization of Inverse Problems for Manifold-Valued Data |
| Authors | Martin Storath, Andreas Weinmann |
| Abstract | In this paper, we consider the variational regularization of manifold-valued data in the inverse problems setting. In particular, we consider TV and TGV regularization for manifold-valued data with indirect measurement operators. We provide results on the well-posedness and present algorithms for a numerical realization of these models in the manifold setup. Further, we provide experimental results for synthetic and real data to show the potential of the proposed schemes for applications. |
| Tasks | |
| Published | 2018-04-27 |
| URL | http://arxiv.org/abs/1804.10432v1 |
| http://arxiv.org/pdf/1804.10432v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-regularization-of-inverse |
| Repo | |
| Framework | |
Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning
| Title | Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning |
| Authors | Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu, Pascale Fung |
| Abstract | Lack of text data has been the major issue on code-switching language modeling. In this paper, we introduce multi-task learning based language model which shares syntax representation of languages to leverage linguistic information and tackle the low resource data issue. Our model jointly learns both language modeling and Part-of-Speech tagging on code-switched utterances. In this way, the model is able to identify the location of code-switching points and improves the prediction of next word. Our approach outperforms standard LSTM based language model, with an improvement of 9.7% and 7.4% in perplexity on SEAME Phase I and Phase II dataset respectively. |
| Tasks | Language Modelling, Multi-Task Learning, Part-Of-Speech Tagging |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.12070v2 |
| http://arxiv.org/pdf/1805.12070v2.pdf | |
| PWC | https://paperswithcode.com/paper/code-switching-language-modeling-using-syntax |
| Repo | |
| Framework | |
Tentacular Artificial Intelligence, and the Architecture Thereof, Introduced
| Title | Tentacular Artificial Intelligence, and the Architecture Thereof, Introduced |
| Authors | Selmer Bringsjord, Naveen Sundar Govindarajulu, Atriya Sen, Matthew Peveler, Biplav Srivastava, Kartik Talamadupula |
| Abstract | We briefly introduce herein a new form of distributed, multi-agent artificial intelligence, which we refer to as “tentacular.” Tentacular AI is distinguished by six attributes, which among other things entail a capacity for reasoning and planning based in highly expressive calculi (logics), and which enlists subsidiary agents across distances circumscribed only by the reach of one or more given networks. |
| Tasks | |
| Published | 2018-10-14 |
| URL | http://arxiv.org/abs/1810.07007v1 |
| http://arxiv.org/pdf/1810.07007v1.pdf | |
| PWC | https://paperswithcode.com/paper/tentacular-artificial-intelligence-and-the |
| Repo | |
| Framework | |
DOD-CNN: Doubly-injecting Object Information for Event Recognition
| Title | DOD-CNN: Doubly-injecting Object Information for Event Recognition |
| Authors | Hyungtae Lee, Sungmin Eum, Heesung Kwon |
| Abstract | Recognizing an event in an image can be enhanced by detecting relevant objects in two ways: 1) indirectly utilizing object detection information within the unified architecture or 2) directly making use of the object detection output results. We introduce a novel approach, referred to as Doubly-injected Object Detection CNN (DOD-CNN), exploiting the object information in both ways for the task of event recognition. The structure of this network is inspired by the Integrated Object Detection CNN (IOD-CNN) where object information is indirectly exploited by the event recognition module through the shared portion of the network. In the DOD-CNN architecture, the intermediate object detection outputs are directly injected into the event recognition network while keeping the indirect sharing structure inherited from the IOD-CNN, thus being `doubly-injected’. We also introduce a batch pooling layer which constructs one representative feature map from multiple object hypotheses. We have demonstrated the effectiveness of injecting the object detection information in two different ways in the task of malicious event recognition. | |
| Tasks | Object Detection |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.02910v2 |
| http://arxiv.org/pdf/1811.02910v2.pdf | |
| PWC | https://paperswithcode.com/paper/dod-cnn-doubly-injecting-object-information |
| Repo | |
| Framework | |
