January 29, 2020

3166 words 15 mins read

Paper Group ANR 673

Machine Learning in/for Blockchain: Future and Challenges. Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER. Learning stochastic differential equations using RNN with log signature features. Multi-atlas image registration of clinical data with automated quality assessment using ventricle segment …

Machine Learning in/for Blockchain: Future and Challenges


Title	Machine Learning in/for Blockchain: Future and Challenges
Authors	Fang Chen, Hong Wan, Hua Cai, Guang Cheng
Abstract	Machine learning (including deep and reinforcement learning) and blockchain are two of the most noticeable technologies in recent years. The first one is the foundation of artificial intelligence and big data, and the second one has significantly disrupted the financial industry. Both technologies are data-driven, and thus there are rapidly growing interests in integrating them for more secure and efficient data sharing and analysis. In this paper, we review the research on combining blockchain and machine learning technologies and demonstrate that they can collaborate efficiently and effectively. In the end, we point out some future directions and expect more researches on deeper integration of the two promising technologies.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.06189v1
PDF	https://arxiv.org/pdf/1909.06189v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-infor-blockchain-future-and
Repo
Framework

Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER


Title	Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER
Authors	Phillip Keung, Yichao Lu, Vikas Bhardwaj
Abstract	Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in zero-shot and zero-resource cross-lingual settings, where only labeled English data is used to finetune the model. We improve upon multilingual BERT’s zero-resource cross-lingual performance via adversarial learning. We report the magnitude of the improvement on the multilingual MLDoc text classification and CoNLL 2002/2003 named entity recognition tasks. Furthermore, we show that language-adversarial training encourages BERT to align the embeddings of English documents and their translations, which may be the cause of the observed performance gains.
Tasks	Named Entity Recognition, Text Classification, Word Embeddings
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00153v3
PDF	https://arxiv.org/pdf/1909.00153v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-with-contextual
Repo
Framework

Learning stochastic differential equations using RNN with log signature features


Title	Learning stochastic differential equations using RNN with log signature features
Authors	Shujian Liao, Terry Lyons, Weixin Yang, Hao Ni
Abstract	This paper contributes to the challenge of learning a function on streamed multimodal data through evaluation. The core of the result of our paper is the combination of two quite different approaches to this problem. One comes from the mathematically principled technology of signatures and log-signatures as representations for streamed data, while the other draws on the techniques of recurrent neural networks (RNN). The ability of the former to manage high sample rate streams and the latter to manage large scale nonlinear interactions allows hybrid algorithms that are easy to code, quicker to train, and of lower complexity for a given accuracy. We illustrate the approach by approximating the unknown functional as a controlled differential equation. Linear functionals on solutions of controlled differential equations are the natural universal class of functions on data streams. Following this approach, we propose a hybrid Logsig-RNN algorithm that learns functionals on streamed data. By testing on various datasets, i.e. synthetic data, NTU RGB+D 120 skeletal action data, and Chalearn2013 gesture data, our algorithm achieves the outstanding accuracy with superior efficiency and robustness.
Tasks	Skeleton Based Action Recognition
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08286v2
PDF	https://arxiv.org/pdf/1908.08286v2.pdf
PWC	https://paperswithcode.com/paper/learning-stochastic-differential-equations-1
Repo
Framework

Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation


Title	Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation
Authors	Florian Dubost, Marleen de Bruijne, Marco Nardin, Adrian V. Dalca, Kathleen L. Donahue, Anne-Katrin Giese, Mark R. Etherton, Ona Wu, Marius de Groot, Wiro Niessen, Meike Vernooij, Natalia S. Rost, Markus D. Schirmer
Abstract	Registration is a core component of many imaging pipelines. In case of clinical scans, with lower resolution and sometimes substantial motion artifacts, registration can produce poor results. Visual assessment of registration quality in large clinical datasets is inefficient. In this work, we propose to automatically assess the quality of registration to an atlas in clinical FLAIR MRI scans of the brain. The method consists of automatically segmenting the ventricles of a given scan using a neural network, and comparing the segmentation to the atlas’ ventricles propagated to image space. We used the proposed method to improve clinical image registration to a general atlas by computing multiple registrations and then selecting the registration that yielded the highest ventricle overlap. Methods were evaluated in a single-site dataset of more than 1000 scans, as well as a multi-center dataset comprising 142 clinical scans from 12 sites. The automated ventricle segmentation reached a Dice coefficient with manual annotations of 0.89 in the single-site dataset, and 0.83 in the multi-center dataset. Registration via age-specific atlases could improve ventricle overlap compared to a direct registration to the general atlas (Dice similarity coefficient increase up to 0.15). Experiments also showed that selecting scans with the registration quality assessment method could improve the quality of average maps of white matter hyperintensity burden, instead of using all scans for the computation of the white matter hyperintensity map. In this work, we demonstrated the utility of an automated tool for assessing image registration quality in clinical scans. This image quality assessment step could ultimately assist in the translation of automated neuroimaging pipelines to the clinic.
Tasks	Image Quality Assessment, Image Registration
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00695v2
PDF	https://arxiv.org/pdf/1907.00695v2.pdf
PWC	https://paperswithcode.com/paper/automated-image-registration-quality
Repo
Framework

Label Consistent Transform Learning for Hyperspectral Image Classification


Title	Label Consistent Transform Learning for Hyperspectral Image Classification
Authors	Jyoti Maggu, Hemant K. Aggarwal, Angshul Majumdar
Abstract	This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency constraint. The proposed technique is especially suited for hyper-spectral image classification problems owing to its ability to learn from fewer samples. We have compared our proposed method on state-of-the-art techniques like label consistent KSVD, Stacked Autoencoder, Deep Belief Network and Convolutional Neural Network. Our method yields considerably better results (more than 0.1 improvement in Kappa coefficient) than all the aforesaid techniques.
Tasks	Hyperspectral Image Classification, Image Classification, Representation Learning, Unsupervised Representation Learning
Published	2019-12-11
URL	https://arxiv.org/abs/1912.11405v1
PDF	https://arxiv.org/pdf/1912.11405v1.pdf
PWC	https://paperswithcode.com/paper/label-consistent-transform-learning-for
Repo
Framework

Historical and Modern Features for Buddha Statue Classification


Title	Historical and Modern Features for Buddha Statue Classification
Authors	Benjamin Renoust, Matheus Oliveira Franca, Jacob Chan, Noa Garcia, Van Le, Ayaka Uesaka, Yuta Nakashima, Hajime Nagahara, Jueren Wang, Yutaka Fujioka
Abstract	While Buddhism has spread along the Silk Roads, many pieces of art have been displaced. Only a few experts may identify these works, subjectively to their experience. The construction of Buddha statues was taught through the definition of canon rules, but the applications of those rules greatly varies across time and space. Automatic art analysis aims at supporting these challenges. We propose to automatically recover the proportions induced by the construction guidelines, in order to use them and compare between different deep learning features for several classification tasks, in a medium size but rich dataset of Buddha statues, collected with experts of Buddhism art history.
Tasks	Art Analysis
Published	2019-09-17
URL	https://arxiv.org/abs/1909.12921v2
PDF	https://arxiv.org/pdf/1909.12921v2.pdf
PWC	https://paperswithcode.com/paper/historical-and-modern-features-for-buddha
Repo
Framework

Sharp Bounds for Genetic Drift in EDAs


Title	Sharp Bounds for Genetic Drift in EDAs
Authors	Benjamin Doerr, Weijie Zheng
Abstract	Estimation of Distribution Algorithms (EDAs) are one branch of Evolutionary Algorithms (EAs) in the broad sense that they evolve a probabilistic model instead of a population. Many existing algorithms fall into this category. Analogous to genetic drift in EAs, EDAs also encounter the phenomenon that updates of the probabilistic model not justified by the fitness move the sampling frequencies to the boundary values. This can result in a considerable performance loss. This paper proves the first sharp estimates of the boundary hitting time of the sampling frequency of a neutral bit for several univariate EDAs. For the UMDA that selects $\mu$ best individuals from $\lambda$ offspring each generation, we prove that the expected first iteration when the frequency of the neutral bit leaves the middle range $[\tfrac 14, \tfrac 34]$ and the expected first time it is absorbed in 0 or 1 are both $\Theta(\mu)$. The corresponding hitting times are $\Theta(K^2)$ for the cGA with hypothetical population size $K$. This paper further proves that for PBIL with parameters $\mu$, $\lambda$, and $\rho$, in an expected number of $\Theta(\mu/\rho^2)$ iterations the sampling frequency of a neutral bit leaves the interval $[\Theta(\rho/\mu),1-\Theta(\rho/\mu)]$ and then always the same value is sampled for this bit, that is, the frequency approaches the corresponding boundary value with maximum speed. For the lower bounds implicit in these statements, we also show exponential tail bounds. If a bit is not neutral, but neutral or has a preference for ones, then the lower bounds on the times to reach a low frequency value still hold. An analogous statement holds for bits that are neutral or prefer the value zero.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14389v1
PDF	https://arxiv.org/pdf/1910.14389v1.pdf
PWC	https://paperswithcode.com/paper/sharp-bounds-for-genetic-drift-in-edas
Repo
Framework

Look, Investigate, and Classify: A Deep Hybrid Attention Method for Breast Cancer Classification


Title	Look, Investigate, and Classify: A Deep Hybrid Attention Method for Breast Cancer Classification
Authors	Bolei Xu, Jingxin Liu, Xianxu Hou, Bozhi Liu, Jon Garibaldi, Ian O. Ellis, Andy Green, Linlin Shen, Guoping Qiu
Abstract	One issue with computer based histopathology image analysis is that the size of the raw image is usually very large. Taking the raw image as input to the deep learning model would be computationally expensive while resizing the raw image to low resolution would incur information loss. In this paper, we present a novel deep hybrid attention approach to breast cancer classification. It first adaptively selects a sequence of coarse regions from the raw image by a hard visual attention algorithm, and then for each such region it is able to investigate the abnormal parts based on a soft-attention mechanism. A recurrent network is then built to make decisions to classify the image region and also to predict the location of the image region to be investigated at the next time step. As the region selection process is non-differentiable, we optimize the whole network through a reinforcement approach to learn an optimal policy to classify the regions. Based on this novel Look, Investigate and Classify approach, we only need to process a fraction of the pixels in the raw image resulting in significant saving in computational resources without sacrificing performances. Our approach is evaluated on a public breast cancer histopathology database, where it demonstrates superior performance to the state-of-the-art deep learning approaches, achieving around 96% classification accuracy while only 15% of raw pixels are used.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1902.10946v1
PDF	http://arxiv.org/pdf/1902.10946v1.pdf
PWC	https://paperswithcode.com/paper/look-investigate-and-classify-a-deep-hybrid
Repo
Framework

A Convergent Off-Policy Temporal Difference Algorithm


Title	A Convergent Off-Policy Temporal Difference Algorithm
Authors	Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi, Shalabh Bhatnagar
Abstract	Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of off-policy prediction. Temporal Difference (TD) learning algorithms are a popular class of algorithms for solving the prediction problem. TD algorithms with linear function approximation are shown to be convergent when the samples are generated from the target policy (known as on-policy prediction). However, it has been well established in the literature that off-policy TD algorithms under linear function approximation diverge. In this work, we propose a convergent on-line off-policy TD algorithm under linear function approximation. The main idea is to penalize the updates of the algorithm in a way as to ensure convergence of the iterates. We provide a convergence analysis of our algorithm. Through numerical evaluations, we further demonstrate the effectiveness of our algorithm.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05697v1
PDF	https://arxiv.org/pdf/1911.05697v1.pdf
PWC	https://paperswithcode.com/paper/a-convergent-off-policy-temporal-difference
Repo
Framework

Smart Laptop Bag with Machine Learning for Activity Recognition


Title	Smart Laptop Bag with Machine Learning for Activity Recognition
Authors	Dwij Sukeshkumar Sheth, Shantanu Singh, Prakhar S Mathur, Vydeki D
Abstract	In todays world of smart living, the smart laptop bag, presented in this paper, provides a better solution to keep track of our precious possessions and monitoring them in real time. As the world moves towards a much tech-savvy direction, the novel laptop bag discussed here facilitates the user to perform location tracking, ambiance monitoring, user-state monitoring etc. in one device. The innovative design uses cloud computing and machine learning algorithms to monitor the health of the user and many parameters of the bag. The emergency alert system in this bag could be trained to send appropriate notifications to emergency contacts of the user, in case of abnormal health conditions or theft of the bag. The experimental smart laptop bag uses deep neural network, which was trained and tested over the various parameters from the bag and produces above 95% accurate results.
Tasks	Activity Recognition
Published	2019-04-14
URL	http://arxiv.org/abs/1904.11882v1
PDF	http://arxiv.org/pdf/1904.11882v1.pdf
PWC	https://paperswithcode.com/paper/190411882
Repo
Framework


Title	A Comparative Analysis of Distributional Term Representations for Author Profiling in Social Media
Authors	Miguel Á. Álvarez-Carmona, Esaú Villatoro-Tello, Manuel Montes-y-Gómez, Luis Villaseñor-Pienda
Abstract	Author Profiling (AP) aims at predicting specific characteristics from a group of authors by analyzing their written documents. Many research has been focused on determining suitable features for modeling writing patterns from authors. Reported results indicate that content-based features continue to be the most relevant and discriminant features for solving this task. Thus, in this paper, we present a thorough analysis regarding the appropriateness of different distributional term representations (DTR) for the AP task. In this regard, we introduce a novel framework for supervised AP using these representations and, supported on it. We approach a comparative analysis of representations such as DOR, TCOR, SSR, and word2vec in the AP problem. We also compare the performance of the DTRs against classic approaches including popular topic-based methods. The obtained results indicate that DTRs are suitable for solving the AP task in social media domains as they achieve competitive results while providing meaningful interpretability.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08780v1
PDF	https://arxiv.org/pdf/1905.08780v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-analysis-of-distributional-term
Repo
Framework

Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites


Title	Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites
Authors	Alberto Alvarez, Steve Dahlskog, Jose Font, Julian Togelius
Abstract	We propose the use of quality-diversity algorithms for mixed-initiative game content generation. This idea is implemented as a new feature of the Evolutionary Dungeon Designer, a system for mixed-initiative design of the type of levels you typically find in computer role playing games. The feature uses the MAP-Elites algorithm, an illumination algorithm which divides the population into a number of cells depending on their values along several behavioral dimensions. Users can flexibly and dynamically choose relevant dimensions of variation, and incorporate suggestions produced by the algorithm in their map designs. At the same time, any modifications performed by the human feed back into MAP-Elites, and are used to generate further suggestions.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05175v1
PDF	https://arxiv.org/pdf/1906.05175v1.pdf
PWC	https://paperswithcode.com/paper/empowering-quality-diversity-in-dungeon
Repo
Framework

Automatic Nonrigid Histological Image Registration with Adaptive Multistep Algorithm


Title	Automatic Nonrigid Histological Image Registration with Adaptive Multistep Algorithm
Authors	Marek Wodzinski, Andrzej Skalski
Abstract	In this paper, we present a short description of the method proposed to ANHIR challenge organized jointly with the IEEE ISBI 2019 conference. We propose a method consisting of preprocessing, initial alignment, nonrigid registration algorithms and a method to automatically choose the best result. The method turned out to be robust (99.792% robustness) and accurate (0.38% average median rTRE). The main drawback of the proposed method is relatively high computation time. However, this aspect can be easily improved by cleaning the code and proposing a GPU implementation.
Tasks	Image Registration
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00982v1
PDF	http://arxiv.org/pdf/1904.00982v1.pdf
PWC	https://paperswithcode.com/paper/automatic-nonrigid-histological-image
Repo
Framework

Context-Aware Query Selection for Active Learning in Event Recognition


Title	Context-Aware Query Selection for Active Learning in Event Recognition
Authors	Mahmudul Hasan, Sujoy Paul, Anastasios I. Mourikis, Amit K. Roy-Chowdhury
Abstract	Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects. However, these approaches require data to be labeled, entirely available beforehand, and not designed to be updated continuously, which make them unsuitable for surveillance applications. In contrast, we propose a continuous-learning framework for context-aware activity recognition from unlabeled video, which has two distinct advantages over existing methods. First, it employs a novel active-learning technique that not only exploits the informativeness of the individual activities but also utilizes their contextual information during query selection; this leads to significant reduction in expensive manual annotation effort. Second, the learned models can be adapted online as more data is available. We formulate a conditional random field model that encodes the context and devise an information-theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative queries, which are labeled by a human. These labels are combined with graphical inference techniques for incremental updates. We provide a theoretical formulation of the active learning framework with an analytic solution. Experiments on six challenging datasets demonstrate that our framework achieves superior performance with significantly less manual labeling.
Tasks	Active Learning, Activity Recognition
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04406v1
PDF	http://arxiv.org/pdf/1904.04406v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-query-selection-for-active
Repo
Framework

Revisiting Deep Architectures for Head Motion Prediction in 360° Videos


Title	Revisiting Deep Architectures for Head Motion Prediction in 360° Videos
Authors	Miguel Fabian Romero Rondon, Lucile Sassatelli, Ramon Aparicio Pardo, Frederic Precioso
Abstract	Head motion prediction is an important problem with 360\degree\ videos, in particular to inform the streaming decisions. Various methods tackling this problem with deep neural networks have been proposed recently. In this article we first show the startling result that all such existing methods, which attempt to benefit both from the history of past positions and knowledge of the video content, perform worse than a simple no-motion baseline. We then propose an LSTM-based architecture which processes the positional information only. It is able to establish state-of-the-art performance and we consider it our position-only baseline. Through a thorough root cause analysis, we first show that the content can indeed inform the head position prediction for horizons longer than 2 to 3s, the trajectory inertia being predominant earlier. We also identify that a sequence-to-sequence auto-regressive framework is crucial to improve the prediction accuracy over longer prediction windows, and that a dedicated recurrent network handling the time series of positions is necessary to reach the performance of the position-only baseline in the early prediction steps. This allows to make the most of the positional information and ground-truth saliency. Finally we show how the level of noise in the estimated saliency impacts the architecture’s performance, and we propose a new architecture establishing state-of-the-art performance with estimated saliency, supporting its assets with an ablation study.
Tasks	motion prediction, Time Series
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11702v2
PDF	https://arxiv.org/pdf/1911.11702v2.pdf
PWC	https://paperswithcode.com/paper/revisiting-deep-architectures-for-head-motion
Repo
Framework