Paper Group ANR 155
Wavelet Convolutional Neural Networks. Lagged correlation-based deep learning for directional trend change prediction in financial time series. Evaluating Gaussian Process Metamodels and Sequential Designs for Noisy Level Set Estimation. Found a good match: should I keep searching? - Accuracy and Performance in Iris Matching Using 1-to-First Search …
Wavelet Convolutional Neural Networks
| Title | Wavelet Convolutional Neural Networks |
| Authors | Shin Fujieda, Kohei Takayama, Toshiya Hachisuka |
| Abstract | Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant performance improvement in many challenging tasks. Since CNNs process images directly in the spatial domain, they are essentially spatial approaches. Given that spatial and spectral approaches are known to have different characteristics, it will be interesting to incorporate a spectral approach into CNNs. We propose a novel CNN architecture, wavelet CNNs, which combines a multiresolution analysis and CNNs into one model. Our insight is that a CNN can be viewed as a limited form of a multiresolution analysis. Based on this insight, we supplement missing parts of the multiresolution analysis via wavelet transform and integrate them as additional components in the entire architecture. Wavelet CNNs allow us to utilize spectral information which is mostly lost in conventional CNNs but useful in most image processing tasks. We evaluate the practical performance of wavelet CNNs on texture classification and image annotation. The experiments show that wavelet CNNs can achieve better accuracy in both tasks than existing models while having significantly fewer parameters than conventional CNNs. |
| Tasks | Image Classification, Object Recognition, Texture Classification |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.08620v1 |
| http://arxiv.org/pdf/1805.08620v1.pdf | |
| PWC | https://paperswithcode.com/paper/wavelet-convolutional-neural-networks |
| Repo | |
| Framework | |
Lagged correlation-based deep learning for directional trend change prediction in financial time series
| Title | Lagged correlation-based deep learning for directional trend change prediction in financial time series |
| Authors | Ben Moews, J. Michael Herrmann, Gbenga Ibikunle |
| Abstract | Trend change prediction in complex systems with a large number of noisy time series is a problem with many applications for real-world phenomena, with stock markets as a notoriously difficult to predict example of such systems. We approach predictions of directional trend changes via complex lagged correlations between them, excluding any information about the target series from the respective inputs to achieve predictions purely based on such correlations with other series. We propose the use of deep neural networks that employ step-wise linear regressions with exponential smoothing in the preparatory feature engineering for this task, with regression slopes as trend strength indicators for a given time interval. We apply this method to historical stock market data from 2011 to 2016 as a use case example of lagged correlations between large numbers of time series that are heavily influenced by externally arising new information as a random factor. The results demonstrate the viability of the proposed approach, with state-of-the-art accuracies and accounting for the statistical significance of the results for additional validation, as well as important implications for modern financial economics. |
| Tasks | Feature Engineering, Time Series |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11287v2 |
| http://arxiv.org/pdf/1811.11287v2.pdf | |
| PWC | https://paperswithcode.com/paper/lagged-correlation-based-deep-learning-for |
| Repo | |
| Framework | |
Evaluating Gaussian Process Metamodels and Sequential Designs for Noisy Level Set Estimation
| Title | Evaluating Gaussian Process Metamodels and Sequential Designs for Noisy Level Set Estimation |
| Authors | Xiong Lyu, Mickael Binois, Michael Ludkovski |
| Abstract | We consider the problem of learning the level set for which a noisy black-box function exceeds a given threshold. To efficiently reconstruct the level set, we investigate Gaussian process (GP) metamodels. Our focus is on strongly stochastic samplers, in particular with heavy-tailed simulation noise and low signal-to-noise ratio. To guard against noise misspecification, we assess the performance of three variants: (i) GPs with Student-$t$ observations; (ii) Student-$t$ processes (TPs); and (iii) classification GPs modeling the sign of the response. In conjunction with these metamodels, we analyze several acquisition functions for guiding the sequential experimental designs, extending existing stepwise uncertainty reduction criteria to the stochastic contour-finding context. This also motivates our development of (approximate) updating formulas to efficiently compute such acquisition functions. Our schemes are benchmarked by using a variety of synthetic experiments in 1–6 dimensions. We also consider an application of level set estimation for determining the optimal exercise policy of Bermudan options in finance. |
| Tasks | |
| Published | 2018-07-18 |
| URL | https://arxiv.org/abs/1807.06712v2 |
| https://arxiv.org/pdf/1807.06712v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-gaussian-process-metamodels-and |
| Repo | |
| Framework | |
Found a good match: should I keep searching? - Accuracy and Performance in Iris Matching Using 1-to-First Search
| Title | Found a good match: should I keep searching? - Accuracy and Performance in Iris Matching Using 1-to-First Search |
| Authors | Andrey Kuehlkamp, Kevin Bowyer |
| Abstract | Iris recognition is used in many applications around the world, with enrollment sizes as large as over one billion persons in India’s Aadhaar program. Large enrollment sizes can require special optimizations in order to achieve fast database searches. One such optimization that has been used in some operational scenarios is 1:First search. In this approach, instead of scanning the entire database, the search is terminated when the first sufficiently good match is found. This saves time, but ignores potentially better matches that may exist in the unexamined portion of the enrollments. At least one prominent and successful border-crossing program used this approach for nearly a decade, in order to allow users a fast “token-free” search. Our work investigates the search accuracy of 1:First and compares it to the traditional 1:N search. Several different scenarios are considered trying to emulate real environments as best as possible: a range of enrollment sizes, closed- and open-set configurations, two iris matchers, and different permutations of the galleries. Results confirm the expected accuracy degradation using 1:First search, and also allow us to identify acceptable working parameters where significant search time reduction is achieved, while maintaining accuracy similar to 1:N search. |
| Tasks | Iris Recognition |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08394v1 |
| http://arxiv.org/pdf/1803.08394v1.pdf | |
| PWC | https://paperswithcode.com/paper/found-a-good-match-should-i-keep-searching |
| Repo | |
| Framework | |
Feature Learning and Classification in Neuroimaging: Predicting Cognitive Impairment from Magnetic Resonance Imaging
| Title | Feature Learning and Classification in Neuroimaging: Predicting Cognitive Impairment from Magnetic Resonance Imaging |
| Authors | Shan Shi, Farouk Nathoo |
| Abstract | Due to the rapid innovation of technology and the desire to find and employ biomarkers for neurodegenerative disease, high-dimensional data classification problems are routinely encountered in neuroimaging studies. To avoid over-fitting and to explore relationships between disease and potential biomarkers, feature learning and selection plays an important role in classifier construction and is an important area in machine learning. In this article, we review several important feature learning and selection techniques including lasso-based methods, PCA, the two-sample t-test, and stacked auto-encoders. We compare these approaches using a numerical study involving the prediction of Alzheimer’s disease from Magnetic Resonance Imaging. |
| Tasks | |
| Published | 2018-06-17 |
| URL | http://arxiv.org/abs/1806.06415v1 |
| http://arxiv.org/pdf/1806.06415v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-learning-and-classification-in |
| Repo | |
| Framework | |
Interruptible Algorithms for Multiproblem Solving
| Title | Interruptible Algorithms for Multiproblem Solving |
| Authors | Spyros Angelopoulos, Alejandro Lopez-Ortiz |
| Abstract | In this paper we address the problem of designing an interruptible system in a setting in which $n$ problem instances, all equally important, must be solved concurrently. The system involves scheduling executions of contract algorithms (which offer a trade-off between allowable computation time and quality of the solution) in m identical parallel processors. When an interruption occurs, the system must report a solution to each of the $n$ problem instances. The quality of this output is then compared to the best-possible algorithm that has foreknowledge of the interruption time and must, likewise, produce solutions to all $n$ problem instances. This extends the well-studied setting in which only one problem instance is queried at interruption time. In this work we first introduce new measures for evaluating the performance of interruptible systems in this setting. In particular, we propose the deficiency of a schedule as a performance measure that meets the requirements of the problem at hand. We then present a schedule whose performance we prove that is within a small factor from optimal in the general, multiprocessor setting. We also show several lower bounds on the deficiency of schedules on a single processor. More precisely, we prove a general lower bound of (n+1)/n, an improved lower bound for the two-problem setting (n=2), and a tight lower bound for the class of round-robin schedules. Our techniques can also yield a simpler, alternative proof of the main result of [Bernstein et al, IJCAI 2003] concerning the performance of cyclic schedules in multiprocessor environments. |
| Tasks | |
| Published | 2018-10-26 |
| URL | http://arxiv.org/abs/1810.11291v1 |
| http://arxiv.org/pdf/1810.11291v1.pdf | |
| PWC | https://paperswithcode.com/paper/interruptible-algorithms-for-multiproblem |
| Repo | |
| Framework | |
360° Stance Detection
| Title | 360° Stance Detection |
| Authors | Sebastian Ruder, John Glover, Afshin Mehrabani, Parsa Ghaffari |
| Abstract | The proliferation of fake news and filter bubbles makes it increasingly difficult to form an unbiased, balanced opinion towards a topic. To ameliorate this, we propose 360{\deg} Stance Detection, a tool that aggregates news with multiple perspectives on a topic. It presents them on a spectrum ranging from support to opposition, enabling the user to base their opinion on multiple pieces of diverse evidence. |
| Tasks | Stance Detection |
| Published | 2018-04-03 |
| URL | http://arxiv.org/abs/1804.00982v1 |
| http://arxiv.org/pdf/1804.00982v1.pdf | |
| PWC | https://paperswithcode.com/paper/360-stance-detection |
| Repo | |
| Framework | |
Cross-Sensor Iris Recognition: LG4000-to-LG2200 Comparison
| Title | Cross-Sensor Iris Recognition: LG4000-to-LG2200 Comparison |
| Authors | Nicolaie Popescu-Bodorin, Lucian Stefanita Grigore, Valentina Emilia Balas, Cristina Madalina Noaica, Ionut Axenie, Justinian Popa, Cristian Munteanu, Victor Stroescu, Ionut Manu, Alexandru Herea, Kartal Horasanli, Iulia Maria Motoc |
| Abstract | Cross-sensor comparison experimental results reported here show that the procedure defined and simulated during the Cross-Sensor Comparison Competition 2013 by our team for migrating / upgrading LG2200 based to LG4000 based biometric systems leads to better LG4000-to-LG2200 cross-sensor iris recognition results than previously reported, both in terms of user comfort and in terms of system safety. On the other hand, LG2200-to-LG400 migration/upgrade procedure defined and implemented by us is applicable to solve interoperability issues between LG2200 based and LG4000 based systems, but also to other pairs of systems having the same shift in the quality of acquired images. |
| Tasks | Iris Recognition |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1801.01695v1 |
| http://arxiv.org/pdf/1801.01695v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-sensor-iris-recognition-lg4000-to |
| Repo | |
| Framework | |
Stance Detection on Tweets: An SVM-based Approach
| Title | Stance Detection on Tweets: An SVM-based Approach |
| Authors | Dilek Küçük, Fazli Can |
| Abstract | Stance detection is a subproblem of sentiment analysis where the stance of the author of a piece of natural language text for a particular target (either explicitly stated in the text or not) is explored. The stance output is usually given as Favor, Against, or Neither. In this paper, we target at stance detection on sports-related tweets and present the performance results of our SVM-based stance classifiers on such tweets. First, we describe three versions of our proprietary tweet data set annotated with stance information, all of which are made publicly available for research purposes. Next, we evaluate SVM classifiers using different feature sets for stance detection on this data set. The employed features are based on unigrams, bigrams, hashtags, external links, emoticons, and lastly, named entities. The results indicate that joint use of the features based on unigrams, hashtags, and named entities by SVM classifiers is a plausible approach for stance detection problem on sports-related tweets. |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08910v1 |
| http://arxiv.org/pdf/1803.08910v1.pdf | |
| PWC | https://paperswithcode.com/paper/stance-detection-on-tweets-an-svm-based |
| Repo | |
| Framework | |
Mean-based Heuristic Search for Real-Time Planning
| Title | Mean-based Heuristic Search for Real-Time Planning |
| Authors | Damien Pellier, Bruno Bouzy, Marc Métivier |
| Abstract | In this paper, we introduce a new heuristic search algorithm based on mean values for real-time planning, called MHSP. It consists in associating the principles of UCT, a bandit-based algorithm which gave very good results in computer games, and especially in Computer Go, with heuristic search in order to obtain a real-time planner in the context of classical planning. MHSP is evaluated on different planning problems and compared to existing algorithms performing on-line search and learning. Besides, our results highlight the capacity of MHSP to return plans in a real-time manner which tend to an optimal plan over the time which is faster and of better quality compared to existing algorithms in the literature. |
| Tasks | |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09150v1 |
| http://arxiv.org/pdf/1810.09150v1.pdf | |
| PWC | https://paperswithcode.com/paper/mean-based-heuristic-search-for-real-time |
| Repo | |
| Framework | |
Advancing Acoustic-to-Word CTC Model
| Title | Advancing Acoustic-to-Word CTC Model |
| Authors | Jinyu Li, Guoli Ye, Amit Das, Rui Zhao, Yifan Gong |
| Abstract | The acoustic-to-word model based on the connectionist temporal classification (CTC) criterion was shown as a natural end-to-end (E2E) model directly targeting words as output units. However, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue as it can only model limited number of words in the output layer and maps all the remaining words into an OOV output node. Hence, such a word-based CTC model can only recognize the frequent words modeled by the network output nodes. Our first attempt to improve the acoustic-to-word model is a hybrid CTC model which consults a letter-based CTC when the word-based CTC model emits OOV tokens during testing time. Then, we propose a much better solution by training a mixed-unit CTC model which decomposes all the OOV words into sequences of frequent words and multi-letter units. Evaluated on a 3400 hours Microsoft Cortana voice assistant task, the final acoustic-to-word solution improves the baseline word-based CTC by relative 12.09% word error rate (WER) reduction when combined with our proposed attention CTC. Such an E2E model without using any language model (LM) or complex decoder outperforms the traditional context-dependent phoneme CTC which has strong LM and decoder by relative 6.79%. |
| Tasks | Language Modelling |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05566v1 |
| http://arxiv.org/pdf/1803.05566v1.pdf | |
| PWC | https://paperswithcode.com/paper/advancing-acoustic-to-word-ctc-model |
| Repo | |
| Framework | |
Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention
| Title | Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention |
| Authors | Kuntal Dey, Ritvik Shrivastava, Saroj Kaushik |
| Abstract | The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in FAVOR of (positive), is AGAINST (negative), or is NONE (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a FAVOR or AGAINST stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset, we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture. |
| Tasks | Stance Detection |
| Published | 2018-01-09 |
| URL | http://arxiv.org/abs/1801.03032v1 |
| http://arxiv.org/pdf/1801.03032v1.pdf | |
| PWC | https://paperswithcode.com/paper/topical-stance-detection-for-twitter-a-two |
| Repo | |
| Framework | |
Generative models for local network community detection
| Title | Generative models for local network community detection |
| Authors | Twan van Laarhoven |
| Abstract | Local network community detection aims to find a single community in a large network, while inspecting only a small part of that network around a given seed node. This is much cheaper than finding all communities in a network. Most methods for local community detection are formulated as ad-hoc optimization problems. In this work, we instead start from a generative model for networks with community structure. By assuming that the network is uniform, we can approximate the structure of unobserved parts of the network to obtain a method for local community detection. We apply this local approximation technique to two variants of the stochastic block model. To our knowledge, this results in the first local community detection methods based on probabilistic models. Interestingly, in the limit, one of the proposed approximations corresponds to conductance, a popular metric in this field. Experiments on real and synthetic datasets show comparable or improved results compared to state-of-the-art local community detection algorithms. |
| Tasks | Community Detection, Local Community Detection |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04469v1 |
| http://arxiv.org/pdf/1804.04469v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-models-for-local-network-community |
| Repo | |
| Framework | |
Auto-Meta: Automated Gradient Based Meta Learner Search
| Title | Auto-Meta: Automated Gradient Based Meta Learner Search |
| Authors | Jaehong Kim, Sangyeul Lee, Sungwan Kim, Moonsu Cha, Jung Kwon Lee, Youngduck Choi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim |
| Abstract | Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that automated architecture search synergizes with the effect of gradient-based meta learning. We adopt the progressive neural architecture search \cite{liu:pnas_google:DBLP:journals/corr/abs-1712-00559} to find optimal architectures for meta-learners. The gradient based meta-learner whose architecture was automatically found achieved state-of-the-art results on the 5-shot 5-way Mini-ImageNet classification problem with $74.65%$ accuracy, which is $11.54%$ improvement over the result obtained by the first gradient-based meta-learner called MAML \cite{finn:maml:DBLP:conf/icml/FinnAL17}. To our best knowledge, this work is the first successful neural architecture search implementation in the context of meta learning. |
| Tasks | Meta-Learning, Neural Architecture Search |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.06927v2 |
| http://arxiv.org/pdf/1806.06927v2.pdf | |
| PWC | https://paperswithcode.com/paper/auto-meta-automated-gradient-based-meta |
| Repo | |
| Framework | |
Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations
| Title | Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations |
| Authors | Sebastian Curi, Kfir Y. Levy, Andreas Krause |
| Abstract | We address the problem of estimating the inputs of a dynamical system from measurements of the system’s outputs. To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error. This optimal trade-off is done efficiently and adaptively in every time step. Experimentally, we show that our method often produces estimates with substantially lower error compared to the state-of-the-art. Finally, we consider the more complex \emph{Learning-from-Observations} framework, where an agent should learn a controller from the outputs of an expert’s demonstration. We incorporate our estimation algorithm as a building block inside this framework and show that it enables learning controllers successfully. |
| Tasks | Imitation Learning |
| Published | 2018-06-19 |
| URL | https://arxiv.org/abs/1806.07200v2 |
| https://arxiv.org/pdf/1806.07200v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-imitation-learning |
| Repo | |
| Framework | |
