Paper Group ANR 707
Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions. A survey of advances in epistemic logic program solvers. Ontology-Based Query Expansion with Latently Related Named Entities for Semantic Text Search. On Learning Markov Chains. Event-triggered Natural Hazard Monitoring with Convolutional Neural Networks on t …
Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions
| Title | Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions |
| Authors | Fredrik D. Johansson |
| Abstract | We study heterogeneity in the effect of a mindset intervention on student-level performance through an observational dataset from the National Study of Learning Mindsets (NSLM). Our analysis uses machine learning (ML) to address the following associated problems: assessing treatment group overlap and covariate balance, imputing conditional average treatment effects, and interpreting imputed effects. By comparing several different model families we illustrate the flexibility of both off-the-shelf and purpose-built estimators. We find that the mindset intervention has a positive average effect of 0.26, 95%-CI [0.22, 0.30], and that heterogeneity in the range of [0.1, 0.4] is moderated by school-level achievement level, poverty concentration, urbanicity, and student prior expectations. |
| Tasks | |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.05975v1 |
| http://arxiv.org/pdf/1811.05975v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-analysis-of-heterogeneity-in |
| Repo | |
| Framework | |
A survey of advances in epistemic logic program solvers
| Title | A survey of advances in epistemic logic program solvers |
| Authors | Anthony P. Leclerc, Patrick Thor Kahl |
| Abstract | Recent research in extensions of Answer Set Programming has included a renewed interest in the language of Epistemic Specifications, which adds modal operators K (“known”) and M (“may be true”) to provide for more powerful introspective reasoning and enhanced capability, particularly when reasoning with incomplete information. An epistemic logic program is a set of rules in this language. Infused with the research has been the desire for an efficient solver to enable the practical use of such programs for problem solving. In this paper, we report on the current state of development of epistemic logic program solvers. |
| Tasks | |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.07141v1 |
| http://arxiv.org/pdf/1809.07141v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-advances-in-epistemic-logic |
| Repo | |
| Framework | |
Ontology-Based Query Expansion with Latently Related Named Entities for Semantic Text Search
| Title | Ontology-Based Query Expansion with Latently Related Named Entities for Semantic Text Search |
| Authors | Vuong M. Ngo, Tru H. Cao |
| Abstract | Traditional information retrieval systems represent documents and queries by keyword sets. However, the content of a document or a query is mainly defined by both keywords and named entities occurring in it. Named entities have ontological features, namely, their aliases, classes, and identifiers, which are hidden from their textual appearance. Besides, the meaning of a query may imply latent named entities that are related to the apparent ones in the query. We propose an ontology-based generalized vector space model to semantic text search. It exploits ontological features of named entities and their latently related ones to reveal the semantics of documents and queries. We also propose a framework to combine different ontologies to take their complementary advantages for semantic annotation and searching. Experiments on a benchmark dataset show better search quality of our model to other ones. |
| Tasks | Information Retrieval |
| Published | 2018-07-15 |
| URL | http://arxiv.org/abs/1807.05579v1 |
| http://arxiv.org/pdf/1807.05579v1.pdf | |
| PWC | https://paperswithcode.com/paper/ontology-based-query-expansion-with-latently |
| Repo | |
| Framework | |
On Learning Markov Chains
| Title | On Learning Markov Chains |
| Authors | Yi Hao, Alon Orlitsky, Venkatadheeraj Pichapati |
| Abstract | The problem of estimating an unknown discrete distribution from its samples is a fundamental tenet of statistical learning. Over the past decade, it attracted significant research effort and has been solved for a variety of divergence measures. Surprisingly, an equally important problem, estimating an unknown Markov chain from its samples, is still far from understood. We consider two problems related to the min-max risk (expected loss) of estimating an unknown $k$-state Markov chain from its $n$ sequential samples: predicting the conditional distribution of the next sample with respect to the KL-divergence, and estimating the transition matrix with respect to a natural loss induced by KL or a more general $f$-divergence measure. For the first measure, we determine the min-max prediction risk to within a linear factor in the alphabet size, showing it is $\Omega(k\log\log n\ / n)$ and $\mathcal{O}(k^2\log\log n\ / n)$. For the second, if the transition probabilities can be arbitrarily small, then only trivial uniform risk upper bounds can be derived. We therefore consider transition probabilities that are bounded away from zero, and resolve the problem for essentially all sufficiently smooth $f$-divergences, including KL-, $L_2$-, Chi-squared, Hellinger, and Alpha-divergences. |
| Tasks | |
| Published | 2018-10-28 |
| URL | http://arxiv.org/abs/1810.11754v1 |
| http://arxiv.org/pdf/1810.11754v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-learning-markov-chains |
| Repo | |
| Framework | |
Event-triggered Natural Hazard Monitoring with Convolutional Neural Networks on the Edge
| Title | Event-triggered Natural Hazard Monitoring with Convolutional Neural Networks on the Edge |
| Authors | Matthias Meyer, Timo Farei-Campagna, Akos Pasztor, Reto Da Forno, Tonio Gsell, Jérome Faillettaz, Andreas Vieli, Samuel Weber, Jan Beutel, Lothar Thiele |
| Abstract | In natural hazard warning systems fast decision making is vital to avoid catastrophes. Decision making at the edge of a wireless sensor network promises fast response times but is limited by the availability of energy, data transfer speed, processing and memory constraints. In this work we present a realization of a wireless sensor network for hazard monitoring based on an array of event-triggered single-channel micro-seismic sensors with advanced signal processing and characterization capabilities based on a novel co-detection technique. On the one hand we leverage an ultra-low power, threshold-triggering circuit paired with on-demand digital signal acquisition capable of extracting relevant information exactly and efficiently at times when it matters most and consequentially not wasting precious resources when nothing can be observed. On the other hand we utilize machine-learning-based classification implemented on low-power, off-the-shelf microcontrollers to avoid false positive warnings and to actively identify humans in hazard zones. The sensors’ response time and memory requirement is substantially improved by quantizing and pipelining the inference of a convolutional neural network. In this way, convolutional neural networks that would not run unmodified on a memory constrained device can be executed in real-time and at scale on low-power embedded devices. A field study with our system is running on the rockfall scarp of the Matterhorn H"ornligrat at 3500 m a.s.l. since 08/2018. |
| Tasks | Decision Making |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09409v2 |
| http://arxiv.org/pdf/1810.09409v2.pdf | |
| PWC | https://paperswithcode.com/paper/event-triggered-natural-hazard-monitoring |
| Repo | |
| Framework | |
Improved Techniques for Adversarial Discriminative Domain Adaptation
| Title | Improved Techniques for Adversarial Discriminative Domain Adaptation |
| Authors | Aaron Chadha, Yiannis Andreopoulos |
| Abstract | Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. We investigate whether we can improve performance of ADDA with a new framework and new loss formulations. Following the framework of semi-supervised GANs, we first extend the discriminator output over the source classes, in order to model the joint distribution over domain and task. We thus leverage on the distribution over the source encoder posteriors (which is fixed during adversarial training) and propose maximum mean discrepancy (MMD) and reconstruction-based loss functions for aligning the target encoder distribution to the source domain. We compare and provide a comprehensive analysis of how our framework and loss formulations extend over simple multi-class extensions of ADDA and other discriminative variants of semi-supervised GANs. In addition, we introduce various forms of regularization for stabilizing training, including treating the discriminator as a denoising autoencoder and regularizing the target encoder with source examples to reduce overfitting under a contraction mapping (i.e., when the target per-class distributions are contracting during alignment with the source). Finally, we validate our framework on standard domain adaptation datasets, such as SVHN and MNIST. We also examine how our framework benefits recognition problems based on modalities that lack training data, by introducing and evaluating on a neuromorphic vision sensing (NVS) sign language recognition dataset, where the source and target domains constitute emulated and real neuromorphic spike events respectively. Our results on all datasets show that our proposal competes or outperforms the state-of-the-art in unsupervised domain adaptation. |
| Tasks | Denoising, Domain Adaptation, Image Classification, Sign Language Recognition, Unsupervised Domain Adaptation |
| Published | 2018-09-10 |
| URL | https://arxiv.org/abs/1809.03625v3 |
| https://arxiv.org/pdf/1809.03625v3.pdf | |
| PWC | https://paperswithcode.com/paper/improving-adversarial-discriminative-domain |
| Repo | |
| Framework | |
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
| Title | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning |
| Authors | Qimai Li, Zhichao Han, Xiao-Ming Wu |
| Abstract | Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semisupervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms are not clear and it still requires a considerable amount of labeled data for validation and model selection. In this paper, we develop deeper insights into the GCN model and address its fundamental limits. First, we show that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Second, to overcome the limits of the GCN model with shallow architectures, we propose both co-training and self-training approaches to train GCNs. Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation. Extensive experiments on benchmarks have verified our theory and proposals. |
| Tasks | Model Selection |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.07606v1 |
| http://arxiv.org/pdf/1801.07606v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeper-insights-into-graph-convolutional |
| Repo | |
| Framework | |
Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
| Title | Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization |
| Authors | Shiyang Yan, Yuan Xie, Fangyu Wu, Jeremy S. Smith, Wenjin Lu, Bailing Zhang |
| Abstract | Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the successful deep learning models, especially the CNN model and Long Short-Term Memories (LSTMs) with attention mechanism, we propose a hierarchical attention model by utilizing both of the global CNN features and the local object features for more effective feature representation and reasoning in image captioning. The generative adversarial network (GAN), together with a reinforcement learning (RL) algorithm, is applied to solve the exposure bias problem in RNN-based supervised training for language problems. In addition, through the automatic measurement of the consistency between the generated caption and the image content by the discriminator in the GAN framework and RL optimization, we make the finally generated sentences more accurate and natural. Comprehensive experiments show the improved performance of the hierarchical attention mechanism and the effectiveness of our RL-based optimization method. Our model achieves state-of-the-art results on several important metrics in the MSCOCO dataset, using only greedy inference. |
| Tasks | Image Captioning |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05253v2 |
| http://arxiv.org/pdf/1811.05253v2.pdf | |
| PWC | https://paperswithcode.com/paper/image-captioning-based-on-a-hierarchical |
| Repo | |
| Framework | |
Self-Referenced Deep Learning
| Title | Self-Referenced Deep Learning |
| Authors | Xu Lan, Xiatian Zhu, Shaogang Gong |
| Abstract | Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create stronger target networks compared to the vanilla non-teacher based learning strategy, this scheme needs to train additionally a large teacher model with expensive computational cost. In this work, we present a Self-Referenced Deep Learning (SRDL) strategy. Unlike both vanilla optimisation and existing knowledge distillation, SRDL distils the knowledge discovered by the in-training target model back to itself to regularise the subsequent learning procedure therefore eliminating the need for training a large teacher model. SRDL improves the model generalisation performance compared to vanilla learning and conventional knowledge distillation approaches with negligible extra computational cost. Extensive evaluations show that a variety of deep networks benefit from SRDL resulting in enhanced deployment performance on both coarse-grained object categorisation tasks (CIFAR10, CIFAR100, Tiny ImageNet, and ImageNet) and fine-grained person instance identification tasks (Market-1501). |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07598v1 |
| http://arxiv.org/pdf/1811.07598v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-referenced-deep-learning |
| Repo | |
| Framework | |
Multitaper Spectral Estimation HDP-HMMs for EEG Sleep Inference
| Title | Multitaper Spectral Estimation HDP-HMMs for EEG Sleep Inference |
| Authors | Leon Chlon, Andrew Song, Sandya Subramanian, Hugo Soulat, John Tauber, Demba Ba, Michael Prerau |
| Abstract | Electroencephalographic (EEG) monitoring of neural activity is widely used for sleep disorder diagnostics and research. The standard of care is to manually classify 30-second epochs of EEG time-domain traces into 5 discrete sleep stages. Unfortunately, this scoring process is subjective and time-consuming, and the defined stages do not capture the heterogeneous landscape of healthy and clinical neural dynamics. This motivates the search for a data-driven and principled way to identify the number and composition of salient, reoccurring brain states present during sleep. To this end, we propose a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), combined with wide-sense stationary (WSS) time series spectral estimation to construct a generative model for personalized subject sleep states. In addition, we employ multitaper spectral estimation to further reduce the large variance of the spectral estimates inherent to finite-length EEG measurements. By applying our method to both simulated and human sleep data, we arrive at three main results: 1) a Bayesian nonparametric automated algorithm that recovers general temporal dynamics of sleep, 2) identification of subject-specific “microstates” within canonical sleep stages, and 3) discovery of stage-dependent sub-oscillations with shared spectral signatures across subjects. |
| Tasks | EEG, Time Series |
| Published | 2018-05-18 |
| URL | http://arxiv.org/abs/1805.07300v1 |
| http://arxiv.org/pdf/1805.07300v1.pdf | |
| PWC | https://paperswithcode.com/paper/multitaper-spectral-estimation-hdp-hmms-for |
| Repo | |
| Framework | |
Clustering Prominent People and Organizations in Topic-Specific Text Corpora
| Title | Clustering Prominent People and Organizations in Topic-Specific Text Corpora |
| Authors | Abdulkareem Alsudais, Hovig Tchalian |
| Abstract | Named entities in text documents are the names of people, organization, location or other types of objects in the documents that exist in the real world. A persisting research challenge is to use computational techniques to identify such entities in text documents. Once identified, several text mining tools and algorithms can be utilized to leverage these discovered named entities and improve NLP applications. In this paper, a method that clusters prominent names of people and organizations based on their semantic similarity in a text corpus is proposed. The method relies on common named entity recognition techniques and on recent word embeddings models. The semantic similarity scores generated using the word embeddings models for the named entities are used to cluster similar entities of the people and organizations types. Two human judges evaluated ten variations of the method after it was run on a corpus that consists of 4,821 articles on a specific topic. The performance of the method was measured using three quantitative measures. The results of these three metrics demonstrate that the method is effective in clustering semantically similar named entities. |
| Tasks | Named Entity Recognition, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2018-07-27 |
| URL | https://arxiv.org/abs/1807.10800v2 |
| https://arxiv.org/pdf/1807.10800v2.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-prominent-people-and-organizations |
| Repo | |
| Framework | |
A Topological Regularizer for Classifiers via Persistent Homology
| Title | A Topological Regularizer for Classifiers via Persistent Homology |
| Authors | Chao Chen, Xiuyan Ni, Qinxun Bai, Yusu Wang |
| Abstract | Regularization plays a crucial role in supervised learning. Most existing methods enforce a global regularization in a structure agnostic manner. In this paper, we initiate a new direction and propose to enforce the structural simplicity of the classification boundary by regularizing over its topological complexity. In particular, our measurement of topological complexity incorporates the importance of topological features (e.g., connected components, handles, and so on) in a meaningful manner, and provides a direct control over spurious topological structures. We incorporate the new measurement as a topological penalty in training classifiers. We also pro- pose an efficient algorithm to compute the gradient of such penalty. Our method pro- vides a novel way to topologically simplify the global structure of the model, without having to sacrifice too much of the flexibility of the model. We demonstrate the effectiveness of our new topological regularizer on a range of synthetic and real-world datasets. |
| Tasks | |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10714v3 |
| http://arxiv.org/pdf/1806.10714v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-topological-regularizer-for-classifiers-via |
| Repo | |
| Framework | |
Robust fusion algorithms for unsupervised change detection between multi-band optical images - A comprehensive case study
| Title | Robust fusion algorithms for unsupervised change detection between multi-band optical images - A comprehensive case study |
| Authors | Vinicius Ferraris, Nicolas Dobigeon, Marie Chabert |
| Abstract | Unsupervised change detection techniques are generally constrained to two multi-band optical images acquired at different times through sensors sharing the same spatial and spectral resolution. This scenario is suitable for a straight comparison of homologous pixels such as pixel-wise differencing. However, in some specific cases such as emergency situations, the only available images may be those acquired through different kinds of sensors with different resolutions. Recently some change detection techniques dealing with images with different spatial and spectral resolutions, have been proposed. Nevertheless, they are focused on a specific scenario where one image has a high spatial and low spectral resolution while the other has a low spatial and high spectral resolution. This paper addresses the problem of detecting changes between any two multi-band optical images disregarding their spatial and spectral resolution disparities. We propose a method that effectively uses the available information by modeling the two observed images as spatially and spectrally degraded versions of two (unobserved) latent images characterized by the same high spatial and high spectral resolutions. Covering the same scene, the latent images are expected to be globally similar except for possible changes in spatially sparse locations. Thus, the change detection task is envisioned through a robust fusion task which enforces the differences between the estimated latent images to be spatially sparse. We show that this robust fusion can be formulated as an inverse problem which is iteratively solved using an alternate minimization strategy. The proposed framework is implemented for an exhaustive list of applicative scenarios and applied to real multi-band optical images. A comparison with state-of-the-art change detection methods evidences the accuracy of the proposed robust fusion-based strategy. |
| Tasks | |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.03068v1 |
| http://arxiv.org/pdf/1804.03068v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-fusion-algorithms-for-unsupervised |
| Repo | |
| Framework | |
CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation
| Title | CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation |
| Authors | Caroline Etienne, Guillaume Fidanza, Andrei Petrovskii, Laurence Devillers, Benoit Schmauch |
| Abstract | In this work we design a neural network for recognizing emotions in speech, using the IEMOCAP dataset. Following the latest advances in audio analysis, we use an architecture involving both convolutional layers, for extracting high-level features from raw spectrograms, and recurrent ones for aggregating long-term dependencies. We examine the techniques of data augmentation with vocal track length perturbation, layer-wise optimizer adjustment, batch normalization of recurrent layers and obtain highly competitive results of 64.5% for weighted accuracy and 61.7% for unweighted accuracy on four emotions. |
| Tasks | Data Augmentation, Emotion Recognition, Speech Emotion Recognition |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05630v2 |
| http://arxiv.org/pdf/1802.05630v2.pdf | |
| PWC | https://paperswithcode.com/paper/cnnlstm-architecture-for-speech-emotion |
| Repo | |
| Framework | |
Hierarchical visuomotor control of humanoids
| Title | Hierarchical visuomotor control of humanoids |
| Authors | Josh Merel, Arun Ahuja, Vu Pham, Saran Tunyasuvunakool, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Greg Wayne |
| Abstract | We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioception and high-level coordination of the low-level skills informed by vision. We develop an architecture capable of surprisingly flexible, task-directed motor control of a relatively high-DoF humanoid body by combining pre-training of low-level motor controllers with a high-level, task-focused controller that switches among low-level sub-policies. The resulting system is able to control a physically-simulated humanoid body to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment. For a supplementary video link, see https://youtu.be/7GISvfbykLE . |
| Tasks | |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09656v2 |
| http://arxiv.org/pdf/1811.09656v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-visuomotor-control-of-humanoids |
| Repo | |
| Framework | |
