Paper Group ANR 334
Learning to generate one-sentence biographies from Wikidata. Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring. A Dynamic Programming Solution to Bounded Dejittering Problems. Bayesian Inference of Spreading Processes on Networks. Structured Probabilistic Pruning for Convolutional Neural Network Acceleration. Adversar …
Learning to generate one-sentence biographies from Wikidata
| Title | Learning to generate one-sentence biographies from Wikidata |
| Authors | Andrew Chisholm, Will Radford, Ben Hachey |
| Abstract | We investigate the generation of one-sentence Wikipedia biographies from facts derived from Wikidata slot-value pairs. We train a recurrent neural network sequence-to-sequence model with attention to select facts and generate textual summaries. Our model incorporates a novel secondary objective that helps ensure it generates sentences that contain the input facts. The model achieves a BLEU score of 41, improving significantly upon the vanilla sequence-to-sequence model and scoring roughly twice that of a simple template baseline. Human preference evaluation suggests the model is nearly as good as the Wikipedia reference. Manual analysis explores content selection, suggesting the model can trade the ability to infer knowledge against the risk of hallucinating incorrect information. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06235v1 |
| http://arxiv.org/pdf/1702.06235v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-generate-one-sentence-biographies |
| Repo | |
| Framework | |
Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring
| Title | Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring |
| Authors | Erwan Lecarpentier, Sebastian Rapp, Marc Melo, Emmanuel Rachelson |
| Abstract | Autonomous unpowered flight is a challenge for control and guidance systems: all the energy the aircraft might use during flight has to be harvested directly from the atmosphere. We investigate the design of an algorithm that optimizes the closed-loop control of a glider’s bank and sideslip angles, while flying in the lower convective layer of the atmosphere in order to increase its mission endurance. Using a Reinforcement Learning approach, we demonstrate the possibility for real-time adaptation of the glider’s behaviour to the time-varying and noisy conditions associated with thermal soaring flight. Our approach is online, data-based and model-free, hence avoids the pitfalls of aerological and aircraft modelling and allow us to deal with uncertainties and non-stationarity. Additionally, we put a particular emphasis on keeping low computational requirements in order to make on-board execution feasible. This article presents the stochastic, time-dependent aerological model used for simulation, together with a standard aircraft model. Then we introduce an adaptation of a Q-learning algorithm and demonstrate its ability to control the aircraft and improve its endurance by exploiting updrafts in non-stationary scenarios. |
| Tasks | Q-Learning |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05668v1 |
| http://arxiv.org/pdf/1707.05668v1.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-evaluation-of-a-q-learning |
| Repo | |
| Framework | |
A Dynamic Programming Solution to Bounded Dejittering Problems
| Title | A Dynamic Programming Solution to Bounded Dejittering Problems |
| Authors | Lukas F. Lang |
| Abstract | We propose a dynamic programming solution to image dejittering problems with bounded displacements and obtain efficient algorithms for the removal of line jitter, line pixel jitter, and pixel jitter. |
| Tasks | |
| Published | 2017-03-27 |
| URL | http://arxiv.org/abs/1703.09161v1 |
| http://arxiv.org/pdf/1703.09161v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dynamic-programming-solution-to-bounded |
| Repo | |
| Framework | |
Bayesian Inference of Spreading Processes on Networks
| Title | Bayesian Inference of Spreading Processes on Networks |
| Authors | Ritabrata Dutta, Antonietta Mira, Jukka-Pekka Onnela |
| Abstract | Infectious diseases are studied to understand their spreading mechanisms, to evaluate control strategies and to predict the risk and course of future outbreaks. Because people only interact with a small number of individuals, and because the structure of these interactions matters for spreading processes, the pairwise relationships between individuals in a population can be usefully represented by a network. Although the underlying processes of transmission are different, the network approach can be used to study the spread of pathogens in a contact network or the spread of rumors in an online social network. We study simulated simple and complex epidemics on synthetic networks and on two empirical networks, a social / contact network in an Indian village and an online social network in the U.S. Our goal is to learn simultaneously about the spreading process parameters and the source node (first infected node) of the epidemic, given a fixed and known network structure, and observations about state of nodes at several points in time. Our inference scheme is based on approximate Bayesian computation (ABC), an inference technique for complex models with likelihood functions that are either expensive to evaluate or analytically intractable. ABC enables us to adopt a Bayesian approach to the problem despite the posterior distribution being very complex. Our method is agnostic about the topology of the network and the nature of the spreading process. It generally performs well and, somewhat counter-intuitively, the inference problem appears to be easier on more heterogeneous network topologies, which enhances its future applicability to real-world settings where few networks have homogeneous topologies. |
| Tasks | Bayesian Inference |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.08862v3 |
| http://arxiv.org/pdf/1709.08862v3.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-inference-of-spreading-processes-on |
| Repo | |
| Framework | |
Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
| Title | Structured Probabilistic Pruning for Convolutional Neural Network Acceleration |
| Authors | Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu |
| Abstract | In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Experiments show that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of top-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet classification. Moreover, SPP can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations. Our 2x speedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We further show the effectiveness of SPP on transfer learning tasks. |
| Tasks | Transfer Learning |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.06994v3 |
| http://arxiv.org/pdf/1709.06994v3.pdf | |
| PWC | https://paperswithcode.com/paper/structured-probabilistic-pruning-for |
| Repo | |
| Framework | |
Adversarial training and dilated convolutions for brain MRI segmentation
| Title | Adversarial training and dilated convolutions for brain MRI segmentation |
| Authors | Pim Moeskops, Mitko Veta, Maxime W. Lafarge, Koen A. J. Eppenhof, Josien P. W. Pluim |
| Abstract | Convolutional neural networks (CNNs) have been applied to various automatic image segmentation tasks in medical image analysis, including brain MRI segmentation. Generative adversarial networks have recently gained popularity because of their power in generating images that are difficult to distinguish from real images. In this study we use an adversarial training approach to improve CNN-based brain MRI segmentation. To this end, we include an additional loss function that motivates the network to generate segmentations that are difficult to distinguish from manual segmentations. During training, this loss function is optimised together with the conventional average per-voxel cross entropy loss. The results show improved segmentation performance using this adversarial training procedure for segmentation of two different sets of images and using two different network architectures, both visually and in terms of Dice coefficients. |
| Tasks | Semantic Segmentation |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03195v1 |
| http://arxiv.org/pdf/1707.03195v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-training-and-dilated-convolutions |
| Repo | |
| Framework | |
A Hybrid Evolutionary Algorithm Based on Solution Merging for the Longest Arc-Preserving Common Subsequence Problem
| Title | A Hybrid Evolutionary Algorithm Based on Solution Merging for the Longest Arc-Preserving Common Subsequence Problem |
| Authors | Christian Blum, Maria J. Blesa |
| Abstract | The longest arc-preserving common subsequence problem is an NP-hard combinatorial optimization problem from the field of computational biology. This problem finds applications, in particular, in the comparison of arc-annotated Ribonucleic acid (RNA) sequences. In this work we propose a simple, hybrid evolutionary algorithm to tackle this problem. The most important feature of this algorithm concerns a crossover operator based on solution merging. In solution merging, two or more solutions to the problem are merged, and an exact technique is used to find the best solution within this union. It is experimentally shown that the proposed algorithm outperforms a heuristic from the literature. |
| Tasks | Combinatorial Optimization |
| Published | 2017-02-01 |
| URL | http://arxiv.org/abs/1702.00318v1 |
| http://arxiv.org/pdf/1702.00318v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-evolutionary-algorithm-based-on |
| Repo | |
| Framework | |
A Literature Based Approach to Define the Scope of Biomedical Ontologies: A Case Study on a Rehabilitation Therapy Ontology
| Title | A Literature Based Approach to Define the Scope of Biomedical Ontologies: A Case Study on a Rehabilitation Therapy Ontology |
| Authors | Mohammad K. Halawani, Rob Forsyth, Phillip Lord |
| Abstract | In this article, we investigate our early attempts at building an ontology describing rehabilitation therapies following brain injury. These therapies are wide-ranging, involving interventions of many different kinds. As a result, these therapies are hard to describe. As well as restricting actual practice, this is also a major impediment to evidence-based medicine as it is hard to meaningfully compare two treatment plans. Ontology development requires significant effort from both ontologists and domain experts. Knowledge elicited from domain experts forms the scope of the ontology. The process of knowledge elicitation is expensive, consumes experts’ time and might have biases depending on the selection of the experts. Various methodologies and techniques exist for enabling this knowledge elicitation, including community groups and open development practices. A related problem is that of defining scope. By defining the scope, we can decide whether a concept (i.e. term) should be represented in the ontology. This is the opposite of knowledge elicitation, in the sense that it defines what should not be in the ontology. This can be addressed by pre-defining a set of competency questions. These approaches are, however, expensive and time-consuming. Here, we describe our work toward an alternative approach, bootstrapping the ontology from an initially small corpus of literature that will define the scope of the ontology, expanding this to a set covering the domain, then using information extraction to define an initial terminology to provide the basis and the competencies for the ontology. Here, we discuss four approaches to building a suitable corpus that is both sufficiently covering and precise. |
| Tasks | |
| Published | 2017-09-27 |
| URL | http://arxiv.org/abs/1709.09450v1 |
| http://arxiv.org/pdf/1709.09450v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-literature-based-approach-to-define-the |
| Repo | |
| Framework | |
Deep Kernelized Autoencoders
| Title | Deep Kernelized Autoencoders |
| Authors | Michael Kampffmeyer, Sigurd Løkse, Filippo Maria Bianchi, Robert Jenssen, Lorenzo Livi |
| Abstract | In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space. The proposed method is based on traditional autoencoders and is trained through a new unsupervised loss function. During training, we optimize both the reconstruction accuracy of input samples and the alignment between a kernel matrix given as prior and the inner products of the hidden representations computed by the autoencoder. Kernel alignment provides control over the hidden representation learned by the autoencoder. Experiments have been performed to evaluate both reconstruction and kernel alignment performance. Additionally, we applied our method to emulate kPCA on a denoising task obtaining promising results. |
| Tasks | Denoising |
| Published | 2017-02-08 |
| URL | http://arxiv.org/abs/1702.02526v1 |
| http://arxiv.org/pdf/1702.02526v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-kernelized-autoencoders |
| Repo | |
| Framework | |
Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in End-to-End Question Answering
| Title | Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in End-to-End Question Answering |
| Authors | Royal Sequiera, Gaurav Baruah, Zhucheng Tu, Salman Mohammed, Jinfeng Rao, Haotian Zhang, Jimmy Lin |
| Abstract | Most work on natural language question answering today focuses on answer selection: given a candidate list of sentences, determine which contains the answer. Although important, answer selection is only one stage in a standard end-to-end question answering pipeline. This paper explores the effectiveness of convolutional neural networks (CNNs) for answer selection in an end-to-end context using the standard TrecQA dataset. We observe that a simple idf-weighted word overlap algorithm forms a very strong baseline, and that despite substantial efforts by the community in applying deep learning to tackle answer selection, the gains are modest at best on this dataset. Furthermore, it is unclear if a CNN is more effective than the baseline in an end-to-end context based on standard retrieval metrics. To further explore this finding, we conducted a manual user evaluation, which confirms that answers from the CNN are detectably better than those from idf-weighted word overlap. This result suggests that users are sensitive to relatively small differences in answer selection quality. |
| Tasks | Answer Selection, Question Answering |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07804v1 |
| http://arxiv.org/pdf/1707.07804v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-effectiveness-of-convolutional |
| Repo | |
| Framework | |
CogSciK: Clustering for Cognitive Science Motivated Decision Making
| Title | CogSciK: Clustering for Cognitive Science Motivated Decision Making |
| Authors | Dr. W. A. Rivera, James C. Wu |
| Abstract | Computational models of decisionmaking must contend with the variance of context and any number of possible decisions that a defined strategic actor can make at a given time. Relying on cognitive science theory, the authors have created an algorithm that captures the orientation of the actor towards an object and arrays the possible decisions available to that actor based on their given intersubjective orientation. This algorithm, like a traditional K-means clustering algorithm, relies on a core-periphery structure that gives the likelihood of moves as those closest to the cluster’s centroid. The result is an algorithm that enables unsupervised classification of an array of decision points belonging to an actor’s present state and deeply rooted in cognitive science theory. |
| Tasks | Decision Making |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03237v1 |
| http://arxiv.org/pdf/1711.03237v1.pdf | |
| PWC | https://paperswithcode.com/paper/cogscik-clustering-for-cognitive-science |
| Repo | |
| Framework | |
Student-t Process Quadratures for Filtering of Non-Linear Systems with Heavy-Tailed Noise
| Title | Student-t Process Quadratures for Filtering of Non-Linear Systems with Heavy-Tailed Noise |
| Authors | Jakub Prüher, Filip Tronarp, Toni Karvonen, Simo Särkkä, Ondřej Straka |
| Abstract | The aim of this article is to design a moment transformation for Student- t distributed random variables, which is able to account for the error in the numerically computed mean. We employ Student-t process quadrature, an instance of Bayesian quadrature, which allows us to treat the integral itself as a random variable whose variance provides information about the incurred integration error. Advantage of the Student- t process quadrature over the traditional Gaussian process quadrature, is that the integral variance depends also on the function values, allowing for a more robust modelling of the integration error. The moment transform is applied in nonlinear sigma-point filtering and evaluated on two numerical examples, where it is shown to outperform the state-of-the-art moment transforms. |
| Tasks | |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.05189v2 |
| http://arxiv.org/pdf/1703.05189v2.pdf | |
| PWC | https://paperswithcode.com/paper/student-t-process-quadratures-for-filtering |
| Repo | |
| Framework | |
Cascaded Boundary Regression for Temporal Action Detection
| Title | Cascaded Boundary Regression for Temporal Action Detection |
| Authors | Jiyang Gao, Zhenheng Yang, Ram Nevatia |
| Abstract | Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions, they may not necessarily cover the entire action instance, which would lead to inferior performance. We adapt a two-stage temporal action detection pipeline with Cascaded Boundary Regression (CBR) model. Class-agnostic proposals and specific actions are detected respectively in the first and the second stage. CBR uses temporal coordinate regression to refine the temporal boundaries of the sliding windows. The salient aspect of the refinement process is that, inside each stage, the temporal boundaries are adjusted in a cascaded way by feeding the refined windows back to the system for further boundary refinement. We test CBR on THUMOS-14 and TVSeries, and achieve state-of-the-art performance on both datasets. The performance gain is especially remarkable under high IoU thresholds, e.g. map@tIoU=0.5 on THUMOS-14 is improved from 19.0% to 31.0%. |
| Tasks | Action Detection |
| Published | 2017-05-02 |
| URL | http://arxiv.org/abs/1705.01180v1 |
| http://arxiv.org/pdf/1705.01180v1.pdf | |
| PWC | https://paperswithcode.com/paper/cascaded-boundary-regression-for-temporal |
| Repo | |
| Framework | |
Patch Correspondences for Interpreting Pixel-level CNNs
| Title | Patch Correspondences for Interpreting Pixel-level CNNs |
| Authors | Victor Fragoso, Chunhui Liu, Aayush Bansal, Deva Ramanan |
| Abstract | We present compositional nearest neighbors (CompNN), a simple approach to visually interpreting distributed representations learned by a convolutional neural network (CNN) for pixel-level tasks (e.g., image synthesis and segmentation). It does so by reconstructing both a CNN’s input and output image by copy-pasting corresponding patches from the training set with similar feature embeddings. To do so efficiently, it makes of a patch-match-based algorithm that exploits the fact that the patch representations learned by a CNN for pixel level tasks vary smoothly. Finally, we show that CompNN can be used to establish semantic correspondences between two images and control properties of the output image by modifying the images contained in the training set. We present qualitative and quantitative experiments for semantic segmentation and image-to-image translation that demonstrate that CompNN is a good tool for interpreting the embeddings learned by pixel-level CNNs. |
| Tasks | Image Generation, Image-to-Image Translation, Semantic Segmentation |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.10683v4 |
| http://arxiv.org/pdf/1711.10683v4.pdf | |
| PWC | https://paperswithcode.com/paper/patch-correspondences-for-interpreting-pixel |
| Repo | |
| Framework | |
Emotion in Reinforcement Learning Agents and Robots: A Survey
| Title | Emotion in Reinforcement Learning Agents and Robots: A Survey |
| Authors | Thomas M. Moerland, Joost Broekens, Catholijn M. Jonker |
| Abstract | This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action selection. Therefore, computational emotion models are usually grounded in the agent’s decision making architecture, of which RL is an important subclass. Studying emotions in RL-based agents is useful for three research fields. For machine learning (ML) researchers, emotion models may improve learning efficiency. For the interactive ML and human-robot interaction (HRI) community, emotions can communicate state and enhance user investment. Lastly, it allows affective modelling (AM) researchers to investigate their emotion theories in a successful AI agent class. This survey provides background on emotion theory and RL. It systematically addresses 1) from what underlying dimensions (e.g., homeostasis, appraisal) emotions can be derived and how these can be modelled in RL-agents, 2) what types of emotions have been derived from these dimensions, and 3) how these emotions may either influence the learning efficiency of the agent or be useful as social signals. We also systematically compare evaluation criteria, and draw connections to important RL sub-domains like (intrinsic) motivation and model-based RL. In short, this survey provides both a practical overview for engineers wanting to implement emotions in their RL agents, and identifies challenges and directions for future emotion-RL research. |
| Tasks | Decision Making |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05172v1 |
| http://arxiv.org/pdf/1705.05172v1.pdf | |
| PWC | https://paperswithcode.com/paper/emotion-in-reinforcement-learning-agents-and |
| Repo | |
| Framework | |
