January 26, 2020

2973 words 14 mins read

Paper Group ANR 1517

Deep Convolutional Neural Network for Automated Detection of Mind Wandering using EEG Signals. ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System. Machine Learning for Seizure Type Classification: Setting the benchmark. Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I). Clustering and Recogniti …

Deep Convolutional Neural Network for Automated Detection of Mind Wandering using EEG Signals


Title	Deep Convolutional Neural Network for Automated Detection of Mind Wandering using EEG Signals
Authors	Seyedroohollah Hosseini, Xuan Guo
Abstract	Mind wandering (MW) is a ubiquitous phenomenon which reflects a shift in attention from task-related to task-unrelated thoughts. There is a need for intelligent interfaces that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. In this paper, we propose a deep learning model for MW detection using Electroencephalogram (EEG) signals. Specifically, we develop a channel-wise deep convolutional neural network (CNN) model to classify the features of focusing state and MW extracted from EEG signals. This is the first study that employs CNN to automatically detect MW using only EEG data. The experimental results on the collected dataset demonstrate promising performance with 91.78% accuracy, 92.84% sensitivity, and 90.73% specificity.
Tasks	EEG
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01799v1
PDF	http://arxiv.org/pdf/1902.01799v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-neural-network-for
Repo
Framework

ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System


Title	ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System
Authors	Oren Pereg, Daniel Korat, Moshe Wasserblat, Jonathan Mamou, Ido Dagan
Abstract	We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training data, hence can be rapidly and cost-effectively used across different domains in applied setups. The system flow includes three stages: First, it generates domain-specific aspect and opinion lexicons based on an unlabeled dataset; second, it enables the user to view and edit those lexicons (weak supervision); and finally, it enables the user to select an unlabeled target dataset from the same domain, classify it, and generate an aspect-based sentiment report. ABSApp has been successfully used in a number of real-life use cases, among them movie review analysis and convention impact analysis.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05608v1
PDF	https://arxiv.org/pdf/1909.05608v1.pdf
PWC	https://paperswithcode.com/paper/absapp-a-portable-weakly-supervised-aspect
Repo
Framework

Machine Learning for Seizure Type Classification: Setting the benchmark


Title	Machine Learning for Seizure Type Classification: Setting the benchmark
Authors	Subhrajit Roy, Umar Asif, Jianbin Tang, Stefan Harrer
Abstract	Accurate classification of seizure types plays a crucial role in the treatment and disease management of epileptic patients. Epileptic seizure type not only impacts on the choice of drugs but also on the range of activities a patient can safely engage in. With recent advances being made towards artificial intelligence enabled automatic seizure detection, the next frontier is the automatic classification of seizure types. On that note, in this paper, we undertake the first study to explore the application of machine learning algorithms for multi-class seizure type classification. We used the recently released TUH EEG Seizure Corpus and conducted a thorough search space exploration to evaluate the performance of a combination of various pre-processing techniques, machine learning algorithms, and corresponding hyperparameters on this task. We show that our algorithms can reach a weighted F1 score of up to 0.907 thereby setting the first benchmark for scalp EEG based multi-class seizure type classification.
Tasks	EEG, Seizure Detection
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01012v1
PDF	http://arxiv.org/pdf/1902.01012v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-seizure-type
Repo
Framework

Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I)


Title	Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I)
Authors	Fernando J. Corbacho
Abstract	Artificial Intelligence frameworks should allow for ever more autonomous and general systems in contrast to very narrow and restricted (human pre-defined) domain systems, in analogy to how the brain works. Self-constructive Artificial Intelligence ($SCAI$) is one such possible framework. We herein propose that $SCAI$ is based on three principles of organization: self-growing, self-experimental and self-repairing. Self-growing: the ability to autonomously and incrementally construct structures and functionality as needed to solve encountered (sub)problems. Self-experimental: the ability to internally simulate, anticipate and take decisions based on these expectations. Self-repairing: the ability to autonomously re-construct a previously successful functionality or pattern of interaction lost from a possible sub-component failure (damage). To implement these principles of organization, a constructive architecture capable of evolving adaptive autonomous agents is required. We present Schema-based learning as one such architecture capable of incrementally constructing a myriad of internal models of three kinds: predictive schemas, dual (inverse models) schemas and goal schemas as they are necessary to autonomously develop increasing functionality. We claim that artificial systems, whether in the digital or in the physical world, can benefit very much form this constructive architecture and should be organized around these principles of organization. To illustrate the generality of the proposed framework, we include several test cases in structural adaptive navigation in artificial intelligence systems in Paper II of this series, and resilient robot motor control in Paper III of this series. Paper IV of this series will also include $SCAI$ for problem structural discovery in predictive Business Intelligence.
Tasks
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01989v1
PDF	http://arxiv.org/pdf/1901.01989v1.pdf
PWC	https://paperswithcode.com/paper/towards-self-constructive-artificial
Repo
Framework

Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks


Title	Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks
Authors	Kun Su, Eli Shlizerman
Abstract	Encoder-decoder recurrent neural network models (RNN Seq2Seq) have achieved great success in ubiquitous areas of computation and applications. It was shown to be successful in modeling data with both temporal and spatial dependencies for translation or prediction tasks. In this study, we propose an embedding approach to visualize and interpret the representation of data by these models. Furthermore, we show that the embedding is an effective method for unsupervised learning and can be utilized to estimate the optimality of model training. In particular, we demonstrate that embedding space projections of the decoder states of RNN Seq2Seq model trained on sequences prediction are organized in clusters capturing similarities and differences in the dynamics of these sequences. Such performance corresponds to an unsupervised clustering of any spatio-temporal features and can be employed for time-dependent problems such as temporal segmentation, clustering of dynamic activity, self-supervised classification, action recognition, failure prediction, etc. We test and demonstrate the application of the embedding methodology to time-sequences of 3D human body poses. We show that the methodology provides a high-quality unsupervised categorization of movements.
Tasks	Dimensionality Reduction
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12176v2
PDF	https://arxiv.org/pdf/1905.12176v2.pdf
PWC	https://paperswithcode.com/paper/dimension-reduction-approach-for
Repo
Framework

Reducing audio membership inference attack accuracy to chance: 4 defenses


Title	Reducing audio membership inference attack accuracy to chance: 4 defenses
Authors	Michael Lomnitz, Nina Lopatina, Paul Gamble, Zigfried Hampel-Arias, Lucas Tindall, Felipe A. Mejia, Maria Alejandra Barrios
Abstract	It is critical to understand the privacy and robustness vulnerabilities of machine learning models, as their implementation expands in scope. In membership inference attacks, adversaries can determine whether a particular set of data was used in training, putting the privacy of the data at risk. Existing work has mostly focused on image related tasks; we generalize this type of attack to speaker identification on audio samples. We demonstrate attack precision of 85.9% and recall of 90.8% for LibriSpeech, and 78.3% precision and 90.7% recall for VOiCES (Voices Obscured in Complex Environmental Settings). We find that implementing defenses such as prediction obfuscation, defensive distillation or adversarial training, can reduce attack accuracy to chance.
Tasks	Inference Attack, Speaker Identification
Published	2019-10-31
URL	https://arxiv.org/abs/1911.01888v1
PDF	https://arxiv.org/pdf/1911.01888v1.pdf
PWC	https://paperswithcode.com/paper/reducing-audio-membership-inference-attack
Repo
Framework

Large deviations for the perceptron model and consequences for active learning


Title	Large deviations for the perceptron model and consequences for active learning
Authors	Hugo Cui, Luca Saglietti, Lenka Zdeborová
Abstract	Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to analyze the large deviations for the accuracy achieved after supervised learning on a subset of the original pool. These large deviations then provide optimal achievable performance boundaries for any active learning algorithm. We show that the optimal learning performance can be efficiently approached by simple message-passing active learning algorithms. We also provide a comparison with the performance of some other popular active learning strategies.
Tasks	Active Learning
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03927v1
PDF	https://arxiv.org/pdf/1912.03927v1.pdf
PWC	https://paperswithcode.com/paper/large-deviations-for-the-perceptron-model-and
Repo
Framework

Memory-Augmented Recurrent Networks for Dialogue Coherence


Title	Memory-Augmented Recurrent Networks for Dialogue Coherence
Authors	David Donahue, Yuanliang Meng, Anna Rumshisky
Abstract	Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time. Other recent approaches exploit an attention mechanism to extract useful information from past conversational utterances, but this introduces an increased computational complexity. In this work, we explore the use of the Neural Turing Machine (NTM) to provide a more permanent and flexible storage mechanism for maintaining dialogue coherence. Specifically, we introduce two separate dialogue architectures based on this NTM design. The first design features a sequence-to-sequence architecture with two separate NTM modules, one for each participant in the conversation. The second memory architecture incorporates a single NTM module, which stores parallel context information for both speakers. This second design also replaces the sequence-to-sequence architecture with a neural language model, to allow for longer context of the NTM and greater understanding of the dialogue history. We report perplexity performance for both models, and compare them to existing baselines.
Tasks	Language Modelling
Published	2019-10-16
URL	https://arxiv.org/abs/1910.10487v1
PDF	https://arxiv.org/pdf/1910.10487v1.pdf
PWC	https://paperswithcode.com/paper/memory-augmented-recurrent-networks-for
Repo
Framework

$hv$-Block Cross Validation is not a BIBD: a Note on the Paper by Jeff Racine (2000)


Title	$hv$-Block Cross Validation is not a BIBD: a Note on the Paper by Jeff Racine (2000)
Authors	Wenjie Zheng
Abstract	This note corrects a mistake in the paper “consistent cross-validatory model-selection for dependent data: $hv$-block cross-validation” by Racine (2000). In his paper, he implied that the therein proposed $hv$-block cross-validation is consistent in the sense of Shao (1993). To get this intuition, he relied on the speculation that $hv$-block is a balanced incomplete block design (BIBD). This note demonstrates that this is not the case, and thus the theoretical consistency of $hv$-block remains an open question. In addition, I also provide a Python program counting the number of occurrences of each sample and each pair of samples.
Tasks	Model Selection
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08904v1
PDF	https://arxiv.org/pdf/1910.08904v1.pdf
PWC	https://paperswithcode.com/paper/hv-block-cross-validation-is-not-a-bibd-a
Repo
Framework

(Newtonian) Space-Time Algebra


Title	(Newtonian) Space-Time Algebra
Authors	James E. Smith
Abstract	The space-time (s-t) algebra provides a mathematical model for communication and computation using values encoded as events in discretized linear (Newtonian) time. Consequently, the input-output behavior of s-t algebra and implemented functions are consistent with the flow of time. The s-t algebra and functions are formally defined. A network design framework for s-t functions is described, and the design of temporal neural networks, a form of spiking neural networks, is discussed as an extended case study. Finally, the relationship with Allen’s interval algebra is briefly discussed.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/2001.04242v3
PDF	https://arxiv.org/pdf/2001.04242v3.pdf
PWC	https://paperswithcode.com/paper/newtonian-space-time-algebra
Repo
Framework

On the Use of Diversity Mechanisms in Dynamic Constrained Continuous Optimization


Title	On the Use of Diversity Mechanisms in Dynamic Constrained Continuous Optimization
Authors	Maryam Hasani-Shoreh, Frank Neumann
Abstract	Population diversity plays a key role in evolutionary algorithms that enables global exploration and avoids premature convergence. This is especially more crucial in dynamic optimization in which diversity can ensure that the population keeps track of the global optimum by adapting to the changing environment. Dynamic constrained optimization problems (DCOPs) have been the target for many researchers in recent years as they comprehend many of the current real-world problems. Regardless of the importance of diversity in dynamic optimization, there is not an extensive study investigating the effects of diversity promotion techniques in DCOPs so far. To address this gap, this paper aims to investigate how the use of different diversity mechanisms may influence the behavior of algorithms in DCOPs. To achieve this goal, we apply and adapt the most common diversity promotion mechanisms for dynamic environments using differential evolution (DE) as our base algorithm. The results show that applying diversity techniques to solve DCOPs in most test cases lead to significant enhancement in the baseline algorithm in terms of modified offline error values.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.06062v1
PDF	https://arxiv.org/pdf/1910.06062v1.pdf
PWC	https://paperswithcode.com/paper/on-the-use-of-diversity-mechanisms-in-dynamic
Repo
Framework

ImageGCN: Multi-Relational Image Graph Convolutional Networks for Disease Identification with Chest X-rays


Title	ImageGCN: Multi-Relational Image Graph Convolutional Networks for Disease Identification with Chest X-rays
Authors	Chengsheng Mao, Liang Yao, Yuan Luo
Abstract	Image representation is a fundamental task in computer vision. However, most of the existing approaches for image representation ignore the relations between images and consider each input image independently. Intuitively, relations between images can help to understand the images and maintain model consistency over related images. In this paper, we consider modeling the image-level relations to generate more informative image representations, and propose ImageGCN, an end-to-end graph convolutional network framework for multi-relational image modeling. We also apply ImageGCN to chest X-ray (CXR) images where rich relational information is available for disease identification. Unlike previous image representation models, ImageGCN learns the representation of an image using both its original pixel features and the features of related images. Besides learning informative representations for images, ImageGCN can also be used for object detection in a weakly supervised manner. The Experimental results on ChestX-ray14 dataset demonstrate that ImageGCN can outperform respective baselines in both disease identification and localization tasks and can achieve comparable and often better results than the state-of-the-art methods.
Tasks	Object Detection
Published	2019-03-31
URL	http://arxiv.org/abs/1904.00325v1
PDF	http://arxiv.org/pdf/1904.00325v1.pdf
PWC	https://paperswithcode.com/paper/imagegcn-multi-relational-image-graph
Repo
Framework

Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding


Title	Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Authors	Dhanasekar Sundararaman, Vivek Subramanian, Guoyin Wang, Shijing Si, Dinghan Shen, Dong Wang, Lawrence Carin
Abstract	Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder based on their relationships to all tokens in a sequence. Recent studies have shown that although such models are capable of learning syntactic features purely by seeing examples, explicitly feeding this information to deep learning models can significantly enhance their performance. Leveraging syntactic information like part of speech (POS) may be particularly beneficial in limited training data settings for complex models such as the Transformer. We show that the syntax-infused Transformer with multiple features achieves an improvement of 0.7 BLEU when trained on the full WMT 14 English to German translation dataset and a maximum improvement of 1.99 BLEU points when trained on a fraction of the dataset. In addition, we find that the incorporation of syntax into BERT fine-tuning outperforms baseline on a number of downstream tasks from the GLUE benchmark.
Tasks	Machine Translation
Published	2019-11-10
URL	https://arxiv.org/abs/1911.06156v1
PDF	https://arxiv.org/pdf/1911.06156v1.pdf
PWC	https://paperswithcode.com/paper/syntax-infused-transformer-and-bert-models
Repo
Framework

Hunting for supernovae articles in the universe of scientometrics


Title	Hunting for supernovae articles in the universe of scientometrics
Authors	Dimitrios Katsaros
Abstract	This short note records an unusual situation with some Google Scholar’s profiles that imply the existence of “supernovae” articles, i.e., articles whose impact – in terms of number of citations – in a single year gets (almost) an order of magnitude higher than the previous year and immediate drops (and remains steady) to a very low level after the next year. We analyse the issue and resolve the situation providing an answer whether there exist supernovae articles.
Tasks
Published	2019-12-15
URL	https://arxiv.org/abs/1912.07090v1
PDF	https://arxiv.org/pdf/1912.07090v1.pdf
PWC	https://paperswithcode.com/paper/hunting-for-supernovae-articles-in-the
Repo
Framework

Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction


Title	Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
Authors	Andreas Kofler, Markus Haltmeier, Tobias Schaeffter, Marc Kachelrieß, Marc Dewey, Christian Wald, Christoph Kolbitsch
Abstract	In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks and cascaded neural networks have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by decoupling the regularization of the solution from ensuring consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained neural network which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative networks. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude.
Tasks	Image Reconstruction
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09395v2
PDF	https://arxiv.org/pdf/1912.09395v2.pdf
PWC	https://paperswithcode.com/paper/neural-networks-based-regularization-of-large
Repo
Framework