Paper Group ANR 8
An Online Learning Approach to Buying and Selling Demand Response. Learning Spherical Convolution for Fast Features from 360° Imagery. Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification. Tensor network language model. AppTechMiner: Mining Applications and Techniques from Scientific Articles. Scale-Space …
An Online Learning Approach to Buying and Selling Demand Response
| Title | An Online Learning Approach to Buying and Selling Demand Response |
| Authors | Kia Khezeli, Eilyan Bitar |
| Abstract | We adopt the perspective of an aggregator, which seeks to coordinate its purchase of demand reductions from a fixed group of residential electricity customers, with its sale of the aggregate demand reduction in a two-settlement wholesale energy market. The aggregator procures reductions in demand by offering its customers a uniform price for reductions in consumption relative to their predetermined baselines. Prior to its realization of the aggregate demand reduction, the aggregator must also determine how much energy to sell into the two-settlement energy market. In the day-ahead market, the aggregator commits to a forward contract, which calls for the delivery of energy in the real-time market. The underlying aggregate demand curve, which relates the aggregate demand reduction to the aggregator’s offered price, is assumed to be affine and subject to unobservable, random shocks. Assuming that both the parameters of the demand curve and the distribution of the random shocks are initially unknown to the aggregator, we investigate the extent to which the aggregator might dynamically adapt its offered prices and forward contracts to maximize its expected profit over a time window of $T$ days. Specifically, we design a dynamic pricing and contract offering policy that resolves the aggregator’s need to learn the unknown demand model with its desire to maximize its cumulative expected profit over time. In particular, the proposed pricing policy is proven to incur a regret over $T$ days that is no greater than $O(\log(T)\sqrt{T})$. |
| Tasks | |
| Published | 2017-07-23 |
| URL | http://arxiv.org/abs/1707.07342v3 |
| http://arxiv.org/pdf/1707.07342v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-learning-approach-to-buying-and |
| Repo | |
| Framework | |
Learning Spherical Convolution for Fast Features from 360° Imagery
| Title | Learning Spherical Convolution for Fast Features from 360° Imagery |
| Authors | Yu-Chuan Su, Kristen Grauman |
| Abstract | While 360{\deg} cameras offer tremendous new possibilities in vision, graphics, and augmented reality, the spherical images they produce make core feature extraction non-trivial. Convolutional neural networks (CNNs) trained on images from perspective cameras yield “flat” filters, yet 360{\deg} images cannot be projected to a single plane without significant distortion. A naive solution that repeatedly projects the viewing sphere to all tangent planes is accurate, but much too computationally intensive for real problems. We propose to learn a spherical convolutional network that translates a planar CNN to process 360{\deg} imagery directly in its equirectangular projection. Our approach learns to reproduce the flat filter outputs on 360{\deg} data, sensitive to the varying distortion effects across the viewing sphere. The key benefits are 1) efficient feature extraction for 360{\deg} images and video, and 2) the ability to leverage powerful pre-trained networks researchers have carefully honed (together with massive labeled image training sets) for perspective images. We validate our approach compared to several alternative methods in terms of both raw CNN output accuracy as well as applying a state-of-the-art “flat” object detector to 360{\deg} data. Our method yields the most accurate results while saving orders of magnitude in computation versus the existing exact reprojection solution. |
| Tasks | |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00919v3 |
| http://arxiv.org/pdf/1708.00919v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spherical-convolution-for-fast |
| Repo | |
| Framework | |
Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification
| Title | Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification |
| Authors | Achintya Kr. Sarkar, Zheng-Hua Tan |
| Abstract | In this paper, we present a time-contrastive learning (TCL) based bottleneck (BN)feature extraction method for speech signals with an application to text-dependent (TD) speaker verification (SV). It is well-known that speech signals exhibit quasi-stationary behavior in and only in a short interval, and the TCL method aims to exploit this temporal structure. More specifically, it trains deep neural networks (DNNs) to discriminate temporal events obtained by uniformly segmenting speech signals, in contrast to existing DNN based BN feature extraction methods that train DNNs using labeled data to discriminate speakers or pass-phrases or phones or a combination of them. In the context of speaker verification, speech data of fixed pass-phrases are used for TCL-BN training, while the pass-phrases used for TCL-BN training are excluded from being used for SV, so that the learned features can be considered generic. The method is evaluated on the RedDots Challenge 2016 database. Experimental results show that TCL-BN is superior to the existing speaker and pass-phrase discriminant BN features and the Mel-frequency cepstral coefficient feature for text-dependent speaker verification. |
| Tasks | Speaker Verification, Text-Dependent Speaker Verification |
| Published | 2017-04-06 |
| URL | https://arxiv.org/abs/1704.02373v3 |
| https://arxiv.org/pdf/1704.02373v3.pdf | |
| PWC | https://paperswithcode.com/paper/time-contrastive-learning-based-dnn |
| Repo | |
| Framework | |
Tensor network language model
| Title | Tensor network language model |
| Authors | Vasily Pestun, Yiannis Vlassopoulos |
| Abstract | We propose a new statistical model suitable for machine learning of systems with long distance correlations such as natural languages. The model is based on directed acyclic graph decorated by multi-linear tensor maps in the vertices and vector spaces in the edges, called tensor network. Such tensor networks have been previously employed for effective numerical computation of the renormalization group flow on the space of effective quantum field theories and lattice models of statistical mechanics. We provide explicit algebro-geometric analysis of the parameter moduli space for tree graphs, discuss model properties and applications such as statistical translation. |
| Tasks | Language Modelling, Tensor Networks |
| Published | 2017-10-27 |
| URL | http://arxiv.org/abs/1710.10248v2 |
| http://arxiv.org/pdf/1710.10248v2.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-network-language-model |
| Repo | |
| Framework | |
AppTechMiner: Mining Applications and Techniques from Scientific Articles
| Title | AppTechMiner: Mining Applications and Techniques from Scientific Articles |
| Authors | Mayank Singh, Soham Dan, Sanyam Agarwal, Pawan Goyal, Animesh Mukherjee |
| Abstract | This paper presents AppTechMiner, a rule-based information extraction framework that automatically constructs a knowledge base of all application areas and problem solving techniques. Techniques include tools, methods, datasets or evaluation metrics. We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article. Our system achieves high average precision (~82%) and recall (~84%) in knowledge base creation. It also performs well in application and technique assignment to an individual article (average accuracy ~66%). In the end, we further present two use cases presenting a trivial information retrieval system and an extensive temporal analysis of the usage of techniques and application areas. At present, we demonstrate the framework for the domain of computational linguistics but this can be easily generalized to any other field of research. |
| Tasks | Information Retrieval |
| Published | 2017-09-10 |
| URL | http://arxiv.org/abs/1709.03064v2 |
| http://arxiv.org/pdf/1709.03064v2.pdf | |
| PWC | https://paperswithcode.com/paper/apptechminer-mining-applications-and |
| Repo | |
| Framework | |
Scale-Space Anisotropic Total Variation for Limited Angle Tomography
| Title | Scale-Space Anisotropic Total Variation for Limited Angle Tomography |
| Authors | Yixing Huang, Oliver Taubmann, Xiaolin Huang, Viktor Haase, Guenter Lauritsch, Andreas Maier |
| Abstract | This paper addresses streak reduction in limited angle tomography. Although the iterative reweighted total variation (wTV) algorithm reduces small streaks well, it is rather inept at eliminating large ones since total variation (TV) regularization is scale-dependent and may regard these streaks as homogeneous areas. Hence, the main purpose of this paper is to reduce streak artifacts at various scales. We propose the scale-space anisotropic total variation (ssaTV) algorithm in two different implementations. The first implementation (ssaTV-1) utilizes an anisotropic gradient-like operator which uses 2s neighboring pixels along the streaks’ normal direction at each scale s. The second implementation (ssaTV-2) makes use of anisotropic down-sampling and up-sampling operations, similarly oriented along the streaks’ normal direction, to apply TV regularization at various scales. Experiments on numerical and clinical data demonstrate that both ssaTV algorithms reduce streak artifacts more effectively and efficiently than wTV, particularly when using multiple scales. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.06930v2 |
| http://arxiv.org/pdf/1712.06930v2.pdf | |
| PWC | https://paperswithcode.com/paper/scale-space-anisotropic-total-variation-for |
| Repo | |
| Framework | |
Joint PoS Tagging and Stemming for Agglutinative Languages
| Title | Joint PoS Tagging and Stemming for Agglutinative Languages |
| Authors | Necva Bölücü, Burcu Can |
| Abstract | The number of word forms in agglutinative languages is theoretically infinite and this variety in word forms introduces sparsity in many natural language processing tasks. Part-of-speech tagging (PoS tagging) is one of these tasks that often suffers from sparsity. In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. We use stemming to reduce sparsity in PoS tagging. Two tasks are jointly performed to provide a mutual benefit in both tasks. Our results show that joint POS tagging and stemming improves PoS tagging scores. We present results for Turkish and Finnish as agglutinative languages and English as a morphologically poor language. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08942v1 |
| http://arxiv.org/pdf/1705.08942v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-pos-tagging-and-stemming-for |
| Repo | |
| Framework | |
Manyopt: An Extensible Tool for Mixed, Non-Linear Optimization Through SMT Solving
| Title | Manyopt: An Extensible Tool for Mixed, Non-Linear Optimization Through SMT Solving |
| Authors | Andrea Callia D’Iddio, Michael Huth |
| Abstract | Optimization of Mixed-Integer Non-Linear Programming (MINLP) supports important decisions in applications such as Chemical Process Engineering. But current solvers have limited ability for deductive reasoning or the use of domain-specific theories, and the management of integrality constraints does not yet exploit automated reasoning tools such as SMT solvers. This seems to limit both scalability and reach of such tools in practice. We therefore present a tool, ManyOpt, for MINLP optimization that enables experimentation with reduction techniques which transform a MINLP problem to feasibility checking realized by an SMT solver. ManyOpt is similar to the SAT solver ManySAT in that it runs a specified number of such reduction techniques in parallel to get the strongest result on a given MINLP problem. The tool is implemented in layers, which we may see as features and where reduction techniques are feature vectors. Some of these features are inspired by known MINLP techniques whereas others are novel and specific to SMT. Our experimental results on standard benchmarks demonstrate the benefits of this approach. The tool supports a variety of SMT solvers and is easily extensible with new features, courtesy of its layered structure. For example, logical formulas for deductive reasoning are easily added to constrain further the optimization of a MINLP problem of interest. |
| Tasks | |
| Published | 2017-02-04 |
| URL | http://arxiv.org/abs/1702.01332v1 |
| http://arxiv.org/pdf/1702.01332v1.pdf | |
| PWC | https://paperswithcode.com/paper/manyopt-an-extensible-tool-for-mixed-non |
| Repo | |
| Framework | |
DeepKey: An EEG and Gait Based Dual-Authentication System
| Title | DeepKey: An EEG and Gait Based Dual-Authentication System |
| Authors | Xiang Zhang, Lina Yao, Chaoran Huang, Tao Gu, Zheng Yang, Yunhao Liu |
| Abstract | Biometric authentication involves various technologies to identify individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, traditional biometric authentication systems (e.g., face recognition, iris, retina, voice, and fingerprint) are facing an increasing risk of being tricked by biometric tools such as anti-surveillance masks, contact lenses, vocoder, or fingerprint films. In this paper, we design a multimodal biometric authentication system named Deepkey, which uses both Electroencephalography (EEG) and gait signals to better protect against such risk. Deepkey consists of two key components: an Invalid ID Filter Model to block unauthorized subjects and an identification model based on attention-based Recurrent Neural Network (RNN) to identify a subjects EEG IDs and gait IDs in parallel. The subject can only be granted access while all the components produce consistent evidence to match the users proclaimed identity. We implement Deepkey with a live deployment in our university and conduct extensive empirical experiments to study its technical feasibility in practice. DeepKey achieves the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) of 0 and 1.0%, respectively. The preliminary results demonstrate that Deepkey is feasible, show consistent superior performance compared to a set of methods, and has the potential to be applied to the authentication deployment in real world settings. |
| Tasks | EEG, Face Recognition, Gait Identification |
| Published | 2017-06-06 |
| URL | https://arxiv.org/abs/1706.01606v2 |
| https://arxiv.org/pdf/1706.01606v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepkey-an-eeg-and-gait-based-dual |
| Repo | |
| Framework | |
Sobolev Training for Neural Networks
| Title | Sobolev Training for Neural Networks |
| Authors | Wojciech Marian Czarnecki, Simon Osindero, Max Jaderberg, Grzegorz Świrszcz, Razvan Pascanu |
| Abstract | At the heart of deep learning we aim to use neural networks as function approximators - training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to input-output pairs from the ground truth, however it is becoming more common to have access to derivatives of the target output with respect to the input - for example when the ground truth function is itself a neural network such as in network compression or distillation. Generally these target derivatives are not computed, or are ignored. This paper introduces Sobolev Training for neural networks, which is a method for incorporating these target derivatives in addition the to target values while training. By optimising neural networks to not only approximate the function’s outputs but also the function’s derivatives we encode additional information about the target function within the parameters of the neural network. Thereby we can improve the quality of our predictors, as well as the data-efficiency and generalization capabilities of our learned function approximation. We provide theoretical justifications for such an approach as well as examples of empirical evidence on three distinct domains: regression on classical optimisation datasets, distilling policies of an agent playing Atari, and on large-scale applications of synthetic gradients. In all three domains the use of Sobolev Training, employing target derivatives in addition to target values, results in models with higher accuracy and stronger generalisation. |
| Tasks | |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.04859v3 |
| http://arxiv.org/pdf/1706.04859v3.pdf | |
| PWC | https://paperswithcode.com/paper/sobolev-training-for-neural-networks |
| Repo | |
| Framework | |
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
| Title | Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? |
| Authors | Nima Tajbakhsh, Jae Y. Shin, Suryakanth R. Gurudu, R. Todd Hurst, Christopher B. Kendall, Michael B. Gotway, Jianming Liang |
| Abstract | Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: \emph{Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch?} To address this question, we considered 4 distinct medical imaging applications in 3 specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from 3 different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that (1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; (2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; (3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and (4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data. |
| Tasks | Transfer Learning |
| Published | 2017-06-02 |
| URL | http://arxiv.org/abs/1706.00712v1 |
| http://arxiv.org/pdf/1706.00712v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-medical |
| Repo | |
| Framework | |
Exponential improvements for quantum-accessible reinforcement learning
| Title | Exponential improvements for quantum-accessible reinforcement learning |
| Authors | Vedran Dunjko, Yi-Kai Liu, Xingyao Wu, Jacob M. Taylor |
| Abstract | Quantum computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification. However, less is known about the advantages that quantum computers may bring in the setting of reinforcement learning, where learning is achieved via interaction with a task environment. Here, we consider a special case of reinforcement learning, where the task environment allows quantum access. In addition, we impose certain “naturalness” conditions on the task environment, which rule out the kinds of oracle problems that are studied in quantum query complexity (and for which quantum speedups are well-known). Within this framework of quantum-accessible reinforcement learning environments, we demonstrate that quantum agents can achieve exponential improvements in learning efficiency, surpassing previous results that showed only quadratic improvements. A key step in the proof is to construct task environments that encode well-known oracle problems, such as Simon’s problem and Recursive Fourier Sampling, while satisfying the above “naturalness” conditions for reinforcement learning. Our results suggest that quantum agents may perform well in certain game-playing scenarios, where the game has recursive structure, and the agent can learn by playing against itself. |
| Tasks | |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1710.11160v3 |
| http://arxiv.org/pdf/1710.11160v3.pdf | |
| PWC | https://paperswithcode.com/paper/exponential-improvements-for-quantum |
| Repo | |
| Framework | |
Efficient acquisition rules for model-based approximate Bayesian computation
| Title | Efficient acquisition rules for model-based approximate Bayesian computation |
| Authors | Marko Järvenpää, Michael U. Gutmann, Arijus Pleska, Aki Vehtari, Pekka Marttinen |
| Abstract | Approximate Bayesian computation (ABC) is a method for Bayesian inference when the likelihood is unavailable but simulating from the model is possible. However, many ABC algorithms require a large number of simulations, which can be costly. To reduce the computational cost, Bayesian optimisation (BO) and surrogate models such as Gaussian processes have been proposed. Bayesian optimisation enables one to intelligently decide where to evaluate the model next but common BO strategies are not designed for the goal of estimating the posterior distribution. Our paper addresses this gap in the literature. We propose to compute the uncertainty in the ABC posterior density, which is due to a lack of simulations to estimate this quantity accurately, and define a loss function that measures this uncertainty. We then propose to select the next evaluation location to minimise the expected loss. Experiments show that the proposed method often produces the most accurate approximations as compared to common BO strategies. |
| Tasks | Bayesian Inference, Bayesian Optimisation, Gaussian Processes |
| Published | 2017-04-03 |
| URL | http://arxiv.org/abs/1704.00520v3 |
| http://arxiv.org/pdf/1704.00520v3.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-acquisition-rules-for-model-based |
| Repo | |
| Framework | |
Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning
| Title | Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning |
| Authors | Gabriel Erion, Hugh Chen, Scott M. Lundberg, Su-In Lee |
| Abstract | We use a deep learning model trained only on a patient’s blood oxygenation data (measurable with an inexpensive fingertip sensor) to predict impending hypoxemia (low blood oxygen) more accurately than trained anesthesiologists with access to all the data recorded in a modern operating room. We also provide a simple way to visualize the reason why a patient’s risk is low or high by assigning weight to the patient’s past blood oxygen values. This work has the potential to provide cutting-edge clinical decision support in low-resource settings, where rates of surgical complication and death are substantially greater than in high-resource areas. |
| Tasks | |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00563v1 |
| http://arxiv.org/pdf/1712.00563v1.pdf | |
| PWC | https://paperswithcode.com/paper/anesthesiologist-level-forecasting-of |
| Repo | |
| Framework | |
Contextual-based Image Inpainting: Infer, Match, and Translate
| Title | Contextual-based Image Inpainting: Infer, Match, and Translate |
| Authors | Yuhang Song, Chao Yang, Zhe Lin, Xiaofeng Liu, Qin Huang, Hao Li, C. -C. Jay Kuo |
| Abstract | We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents. To this end, we propose a learning-based approach to generate visually coherent completion given a high-resolution image with missing components. In order to overcome the difficulty to directly learn the distribution of high-dimensional image data, we divide the task into inference and translation as two separate steps and model each step with a deep neural network. We also use simple heuristics to guide the propagation of local textures from the boundary to the hole. We show that, by using such techniques, inpainting reduces to the problem of learning two image-feature translation functions in much smaller space and hence easier to train. We evaluate our method on several public datasets and show that we generate results of better visual quality than previous state-of-the-art methods. |
| Tasks | Image Inpainting |
| Published | 2017-11-23 |
| URL | http://arxiv.org/abs/1711.08590v5 |
| http://arxiv.org/pdf/1711.08590v5.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-based-image-inpainting-infer-match |
| Repo | |
| Framework | |
