May 7, 2019

2728 words 13 mins read

Paper Group ANR 17

Importance Sampling with Unequal Support. Empath: Understanding Topic Signals in Large-Scale Text. Information Theoretic-Learning Auto-Encoder. Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context. Using Recurrent Neural Networks to Optimize Dynamical Decoupling for Quan …

Importance Sampling with Unequal Support


Title	Importance Sampling with Unequal Support
Authors	Philip S. Thomas, Emma Brunskill
Abstract	Importance sampling is often used in machine learning when training and testing data come from different distributions. In this paper we propose a new variant of importance sampling that can reduce the variance of importance sampling-based estimates by orders of magnitude when the supports of the training and testing distributions differ. After motivating and presenting our new importance sampling estimator, we provide a detailed theoretical analysis that characterizes both its bias and variance relative to the ordinary importance sampling estimator (in various settings, which include cases where ordinary importance sampling is biased, while our new estimator is not, and vice versa). We conclude with an example of how our new importance sampling estimator can be used to improve estimates of how well a new treatment policy for diabetes will work for an individual, using only data from when the individual used a previous treatment policy.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03451v1
PDF	http://arxiv.org/pdf/1611.03451v1.pdf
PWC	https://paperswithcode.com/paper/importance-sampling-with-unequal-support
Repo
Framework

Empath: Understanding Topic Signals in Large-Scale Text


Title	Empath: Understanding Topic Signals in Large-Scale Text
Authors	Ethan Fast, Binbin Chen, Michael Bernstein
Abstract	Human language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them. We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like “bleed” and “punch” to generate the category violence). Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction. Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the category with a crowd-powered filter. Empath also analyzes text across 200 built-in, pre-validated categories we have generated from common topics in our web dataset, like neglect, government, and social media. We show that Empath’s data-driven, human validated categories are highly correlated (r=0.906) with similar categories in LIWC.
Tasks
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06979v1
PDF	http://arxiv.org/pdf/1602.06979v1.pdf
PWC	https://paperswithcode.com/paper/empath-understanding-topic-signals-in-large
Repo
Framework

Information Theoretic-Learning Auto-Encoder


Title	Information Theoretic-Learning Auto-Encoder
Authors	Eder Santana, Matthew Emigh, Jose C Principe
Abstract	We propose Information Theoretic-Learning (ITL) divergence measures for variational regularization of neural networks. We also explore ITL-regularized autoencoders as an alternative to variational autoencoding bayes, adversarial autoencoders and generative adversarial networks for randomly generating sample data without explicitly defining a partition function. This paper also formalizes, generative moment matching networks under the ITL framework.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06653v1
PDF	http://arxiv.org/pdf/1603.06653v1.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-learning-auto-encoder
Repo
Framework

Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context


Title	Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context
Authors	Nikolas J. Hemion
Abstract	Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning. However current computational reinforcement learning agents mostly learn each individual skill entirely from scratch. How can we enable artificial agents, such as robots, to acquire some form of generic knowledge, which they could leverage for the learning of new skills? This paper argues that, like the brain, the cognitive system of artificial agents has to develop a world model to support adaptive behavior and learning. Inspiration is taken from two recent developments in the cognitive science literature: predictive processing theories of cognition, and the sensorimotor contingencies theory of perception. Based on these, a hypothesis is formulated about what the content of information might be that is encoded in an internal world model, and how an agent could autonomously acquire it. A computational model is described to formalize this hypothesis, and is evaluated in a series of simulation experiments.
Tasks
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00359v1
PDF	http://arxiv.org/pdf/1608.00359v1.pdf
PWC	https://paperswithcode.com/paper/discovering-latent-states-for-model-learning
Repo
Framework

Using Recurrent Neural Networks to Optimize Dynamical Decoupling for Quantum Memory


Title	Using Recurrent Neural Networks to Optimize Dynamical Decoupling for Quantum Memory
Authors	Moritz August, Xiaotong Ni
Abstract	We utilize machine learning models which are based on recurrent neural networks to optimize dynamical decoupling (DD) sequences. DD is a relatively simple technique for suppressing the errors in quantum memory for certain noise models. In numerical simulations, we show that with minimum use of prior knowledge and starting from random sequences, the models are able to improve over time and eventually output DD-sequences with performance better than that of the well known DD-families. Furthermore, our algorithm is easy to implement in experiments to find solutions tailored to the specific hardware, as it treats the figure of merit as a black box.
Tasks
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00279v2
PDF	http://arxiv.org/pdf/1604.00279v2.pdf
PWC	https://paperswithcode.com/paper/using-recurrent-neural-networks-to-optimize
Repo
Framework

Belief Merging by Source Reliability Assessment


Title	Belief Merging by Source Reliability Assessment
Authors	Paolo Liberatore
Abstract	Merging beliefs requires the plausibility of the sources of the information to be merged. They are typically assumed equally reliable in lack of hints indicating otherwise; yet, a recent line of research spun from the idea of deriving this information from the revision process itself. In particular, the history of previous revisions and previous merging examples provide information for performing subsequent mergings. Yet, no examples or previous revisions may be available. In spite of the apparent lack of information, something can still be inferred by a try-and-check approach: a relative reliability ordering is assumed, the merging process is performed based on it, and the result is compared with the original information. The outcome of this check may be incoherent with the initial assumption, like when a completely reliable source is rejected some of the information it provided. In such cases, the reliability ordering assumed in the first place can be excluded from consideration. The first theorem of this article proves that such a scenario is indeed possible. Other results are obtained under various definition of reliability and merging.
Tasks
Published	2016-05-07
URL	http://arxiv.org/abs/1605.02160v1
PDF	http://arxiv.org/pdf/1605.02160v1.pdf
PWC	https://paperswithcode.com/paper/belief-merging-by-source-reliability
Repo
Framework

Video Scene Parsing with Predictive Feature Learning


Title	Video Scene Parsing with Predictive Feature Learning
Authors	Xiaojie Jin, Xin Li, Huaxin Xiao, Xiaohui Shen, Zhe Lin, Jimei Yang, Yunpeng Chen, Jian Dong, Luoqi Liu, Zequn Jie, Jiashi Feng, Shuicheng Yan
Abstract	In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing framework. (1) \textbf{Predictive feature learning}} from nearly unlimited unlabeled video data. Different from existing methods learning features from single frame parsing, we learn spatiotemporal discriminative features by enforcing a parsing network to predict future frames and their parsing maps (if available) given only historical frames. In this way, the network can effectively learn to capture video dynamics and temporal context, which are critical clues for video scene parsing, without requiring extra manual annotations. (2) \textbf{Prediction steering parsing}} architecture that effectively adapts the learned spatiotemporal features to scene parsing tasks and provides strong guidance for any off-the-shelf parsing model to achieve better video scene parsing performance. Extensive experiments over two challenging datasets, Cityscapes and Camvid, have demonstrated the effectiveness of our methods by showing significant improvement over well-established baselines.
Tasks	Representation Learning, Scene Parsing
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00119v2
PDF	http://arxiv.org/pdf/1612.00119v2.pdf
PWC	https://paperswithcode.com/paper/video-scene-parsing-with-predictive-feature
Repo
Framework

Co-active Learning to Adapt Humanoid Movement for Manipulation


Title	Co-active Learning to Adapt Humanoid Movement for Manipulation
Authors	Ren Mao, John S. Baras, Yezhou Yang, Cornelia Fermuller
Abstract	In this paper we address the problem of robot movement adaptation under various environmental constraints interactively. Motion primitives are generally adopted to generate target motion from demonstrations. However, their generalization capability is weak while facing novel environments. Additionally, traditional motion generation methods do not consider the versatile constraints from various users, tasks, and environments. In this work, we propose a co-active learning framework for learning to adapt robot end-effector’s movement for manipulation tasks. It is designed to adapt the original imitation trajectories, which are learned from demonstrations, to novel situations with various constraints. The framework also considers user’s feedback towards the adapted trajectories, and it learns to adapt movement through human-in-the-loop interactions. The implemented system generalizes trained motion primitives to various situations with different constraints considering user preferences. Experiments on a humanoid platform validate the effectiveness of our approach.
Tasks	Active Learning
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03628v1
PDF	http://arxiv.org/pdf/1609.03628v1.pdf
PWC	https://paperswithcode.com/paper/co-active-learning-to-adapt-humanoid-movement
Repo
Framework

There’s No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction


Title	There’s No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction
Authors	Courtney Napoles, Keisuke Sakaguchi, Joel Tetreault
Abstract	Current methods for automatically evaluating grammatical error correction (GEC) systems rely on gold-standard references. However, these methods suffer from penalizing grammatical edits that are correct but not in the gold standard. We show that reference-less grammaticality metrics correlate very strongly with human judgments and are competitive with the leading reference-based evaluation metrics. By interpolating both methods, we achieve state-of-the-art correlation with human judgments. Finally, we show that GEC metrics are much more reliable when they are calculated at the sentence level instead of the corpus level. We have set up a CodaLab site for benchmarking GEC output using a common dataset and different evaluation metrics.
Tasks	Grammatical Error Correction
Published	2016-10-07
URL	http://arxiv.org/abs/1610.02124v1
PDF	http://arxiv.org/pdf/1610.02124v1.pdf
PWC	https://paperswithcode.com/paper/theres-no-comparison-reference-less
Repo
Framework

Co-adaptive learning over a countable space


Title	Co-adaptive learning over a countable space
Authors	Michael Rabadi
Abstract	Co-adaptation is a special form of on-line learning where an algorithm $\mathcal{A}$ must assist an unknown algorithm $\mathcal{B}$ to perform some task. This is a general framework and has applications in recommendation systems, search, education, and much more. Today, the most common use of co-adaptive algorithms is in brain-computer interfacing (BCI), where algorithms help patients gain and maintain control over prosthetic devices. While previous studies have shown strong empirical results Kowalski et al. (2013); Orsborn et al. (2014) or have been studied in specific examples Merel et al. (2013, 2015), there is no general analysis of the co-adaptive learning problem. Here we will study the co-adaptive learning problem in the online, closed-loop setting. We will prove that, with high probability, co-adaptive learning is guaranteed to outperform learning with a fixed decoder as long as a particular condition is met.
Tasks	Recommendation Systems
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09816v2
PDF	http://arxiv.org/pdf/1611.09816v2.pdf
PWC	https://paperswithcode.com/paper/co-adaptive-learning-over-a-countable-space
Repo
Framework

Feature Extraction and Automated Classification of Heartbeats by Machine Learning


Title	Feature Extraction and Automated Classification of Heartbeats by Machine Learning
Authors	Choudur Lakshminarayan, Tony Basil
Abstract	We present algorithms for the detection of a class of heart arrhythmias with the goal of eventual adoption by practicing cardiologists. In clinical practice, detection is based on a small number of meaningful features extracted from the heartbeat cycle. However, techniques proposed in the literature use high dimensional vectors consisting of morphological, and time based features for detection. Using electrocardiogram (ECG) signals, we found smaller subsets of features sufficient to detect arrhythmias with high accuracy. The features were found by an iterative step-wise feature selection method. We depart from common literature in the following aspects: 1. As opposed to a high dimensional feature vectors, we use a small set of features with meaningful clinical interpretation, 2. we eliminate the necessity of short-duration patient-specific ECG data to append to the global training data for classification 3. We apply semi-parametric classification procedures (in an ensemble framework) for arrhythmia detection, and 4. our approach is based on a reduced sampling rate of ~ 115 Hz as opposed to 360 Hz in standard literature.
Tasks	Arrhythmia Detection, Feature Selection
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03822v1
PDF	http://arxiv.org/pdf/1607.03822v1.pdf
PWC	https://paperswithcode.com/paper/feature-extraction-and-automated
Repo
Framework

Unsupervised Measure of Word Similarity: How to Outperform Co-occurrence and Vector Cosine in VSMs


Title	Unsupervised Measure of Word Similarity: How to Outperform Co-occurrence and Vector Cosine in VSMs
Authors	Enrico Santus, Tin-Shing Chiu, Qin Lu, Alessandro Lenci, Chu-Ren Huang
Abstract	In this paper, we claim that vector cosine, which is generally considered among the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by an unsupervised measure that calculates the extent of the intersection among the most mutually dependent contexts of the target words. To prove it, we describe and evaluate APSyn, a variant of the Average Precision that, without any optimization, outperforms the vector cosine and the co-occurrence on the standard ESL test set, with an improvement ranging between +9.00% and +17.98%, depending on the number of chosen top contexts.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09054v1
PDF	http://arxiv.org/pdf/1603.09054v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-measure-of-word-similarity-how
Repo
Framework

Success Probability of Exploration: a Concrete Analysis of Learning Efficiency


Title	Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
Authors	Liangpeng Zhang, Ke Tang, Xin Yao
Abstract	Exploration has been a crucial part of reinforcement learning, yet several important questions concerning exploration efficiency are still not answered satisfactorily by existing analytical frameworks. These questions include exploration parameter setting, situation analysis, and hardness of MDPs, all of which are unavoidable for practitioners. To bridge the gap between the theory and practice, we propose a new analytical framework called the success probability of exploration. We show that those important questions of exploration above can all be answered under our framework, and the answers provided by our framework meet the needs of practitioners better than the existing ones. More importantly, we introduce a concrete and practical approach to evaluating the success probabilities in certain MDPs without the need of actually running the learning algorithm. We then provide empirical results to verify our approach, and demonstrate how the success probability of exploration can be used to analyse and predict the behaviours and possible outcomes of exploration, which are the keys to the answer of the important questions of exploration.
Tasks
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00882v1
PDF	http://arxiv.org/pdf/1612.00882v1.pdf
PWC	https://paperswithcode.com/paper/success-probability-of-exploration-a-concrete
Repo
Framework

A fuzzy approach for segmentation of touching characters


Title	A fuzzy approach for segmentation of touching characters
Authors	Giuseppe Airò Farulla, Nadir Murru, Rosaria Rossini
Abstract	The problem of correctly segmenting touching characters is an hard task to solve and it is of major relevance in pattern recognition. In the recent years, many methods and algorithms have been proposed; still, a definitive solution is far from being found. In this paper, we propose a novel method based on fuzzy logic. The proposed method combines in a novel way three features for segmenting touching characters that have been already proposed in other studies but have been exploited only singularly so far. The proposed strategy is based on a 3–input/1–output fuzzy inference system with fuzzy rules specifically optimized for segmenting touching characters in the case of Latin printed and handwritten characters. The system performances are illustrated and supported by numerical examples showing that our approach can achieve a reasonable good overall accuracy in segmenting characters even on tricky conditions of touching characters. Moreover, numerical results suggest that the method can be applied to many different datasets of characters by means of a convenient tuning of the fuzzy sets and rules.
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.04862v1
PDF	http://arxiv.org/pdf/1612.04862v1.pdf
PWC	https://paperswithcode.com/paper/a-fuzzy-approach-for-segmentation-of-touching
Repo
Framework

Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL


Title	Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL
Authors	Yevgeni Berzak, Roi Reichart, Boris Katz
Abstract	This work examines the impact of cross-linguistic transfer on grammatical errors in English as Second Language (ESL) texts. Using a computational framework that formalizes the theory of Contrastive Analysis (CA), we demonstrate that language specific error distributions in ESL writing can be predicted from the typological properties of the native language and their relation to the typology of English. Our typology driven model enables to obtain accurate estimates of such distributions without access to any ESL data for the target languages. Furthermore, we present a strategy for adjusting our method to low-resource languages that lack typological documentation using a bootstrapping approach which approximates native language typology from ESL texts. Finally, we show that our framework is instrumental for linguistic inquiry seeking to identify first language factors that contribute to a wide range of difficulties in second language acquisition.
Tasks	Language Acquisition
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07609v1
PDF	http://arxiv.org/pdf/1603.07609v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-analysis-with-predictive-power-1
Repo
Framework