Paper Group ANR 202
Track Xplorer: A System for Visual Analysis of Sensor-based Motor Activity Predictions. Definition and evaluation of model-free coordination of electrical vehicle charging with reinforcement learning. VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video. Analysing Dropout and Compounding Errors in Neural Language Mo …
Track Xplorer: A System for Visual Analysis of Sensor-based Motor Activity Predictions
| Title | Track Xplorer: A System for Visual Analysis of Sensor-based Motor Activity Predictions |
| Authors | Marco Cavallo, Çağatay Demiralp |
| Abstract | With the rapid commoditization of wearable sensors, detecting human movements from sensor datasets has become increasingly common over a wide range of applications. To detect activities, data scientists iteratively experiment with different classifiers before deciding which model to deploy. Effective reasoning about and comparison of alternative classifiers are crucial in successful model development. This is, however, inherently difficult in developing classifiers for sensor data, where the intricacy of long temporal sequences, high prediction frequency, and imprecise labeling make standard evaluation methods relatively ineffective and even misleading. We introduce Track Xplorer, an interactive visualization system to query, analyze, and compare the predictions of sensor-data classifiers. Track Xplorer enables users to interactively explore and compare the results of different classifiers, and assess their accuracy with respect to the ground-truth labels and video. Through integration with a version control system, Track Xplorer supports tracking of models and their parameters without additional workload on model developers. Track Xplorer also contributes an extensible algebra over track representations to filter, compose, and compare classification outputs, enabling users to reason effectively about classifier performance. We apply Track Xplorer in a collaborative project to develop classifiers to detect movements from multisensor data gathered from Parkinson’s disease patients. We demonstrate how Track Xplorer helps identify early on possible systemic data errors, effectively track and compare the results of different classifiers, and reason about and pinpoint the causes of misclassifications. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09256v1 |
| http://arxiv.org/pdf/1806.09256v1.pdf | |
| PWC | https://paperswithcode.com/paper/track-xplorer-a-system-for-visual-analysis-of |
| Repo | |
| Framework | |
Definition and evaluation of model-free coordination of electrical vehicle charging with reinforcement learning
| Title | Definition and evaluation of model-free coordination of electrical vehicle charging with reinforcement learning |
| Authors | Nasrin Sadeghianpourhamami, Johannes Deleu, Chris Develder |
| Abstract | Initial DR studies mainly adopt model predictive control and thus require accurate models of the control problem (e.g., a customer behavior model), which are to a large extent uncertain for the EV scenario. Hence, model-free approaches, especially based on reinforcement learning (RL) are an attractive alternative. In this paper, we propose a new Markov decision process (MDP) formulation in the RL framework, to jointly coordinate a set of EV charging stations. State-of-the-art algorithms either focus on a single EV, or perform the control of an aggregate of EVs in multiple steps (e.g., aggregate load decisions in one step, then a step translating the aggregate decision to individual connected EVs). On the contrary, we propose an RL approach to jointly control the whole set of EVs at once. We contribute a new MDP formulation, with a scalable state representation that is independent of the number of EV charging stations. Further, we use a batch reinforcement learning algorithm, i.e., an instance of fitted Q-iteration, to learn the optimal charging policy. We analyze its performance using simulation experiments based on a real-world EV charging data. More specifically, we (i) explore the various settings in training the RL policy (e.g., duration of the period with training data), (ii) compare its performance to an oracle all-knowing benchmark (which provides an upper bound for performance, relying on information that is not available or at least imperfect in practice), (iii) analyze performance over time, over the course of a full year to evaluate possible performance fluctuations (e.g, across different seasons), and (iv) demonstrate the generalization capacity of a learned control policy to larger sets of charging stations. |
| Tasks | |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1809.10679v2 |
| http://arxiv.org/pdf/1809.10679v2.pdf | |
| PWC | https://paperswithcode.com/paper/definition-and-evaluation-of-model-free |
| Repo | |
| Framework | |
VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video
| Title | VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video |
| Authors | Xuesong Niu, Hu Han, Shiguang Shan, Xilin Chen |
| Abstract | Heart rate (HR) is an important physiological signal that reflects the physical and emotional activities of humans. Traditional HR measurements are mainly based on contact monitors, which are inconvenient and may cause discomfort for the subjects. Recently, methods have been proposed for remote HR estimation from face videos. However, most of the existing methods focus on well-controlled scenarios, their generalization ability into less-constrained scenarios are not known. At the same time, lacking large-scale databases has limited the use of deep representation learning methods in remote HR estimation. In this paper, we introduce a large-scale multi-modal HR database (named as VIPL-HR), which contains 2,378 visible light videos (VIS) and 752 near-infrared (NIR) videos of 107 subjects. Our VIPL-HR database also contains various variations such as head movements, illumination variations, and acquisition device changes. We also learn a deep HR estimator (named as RhythmNet) with the proposed spatial-temporal representation, which achieves promising results on both the public-domain and our VIPL-HR HR estimation databases. We would like to put the VIPL-HR database into the public domain. |
| Tasks | Representation Learning |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.04927v2 |
| http://arxiv.org/pdf/1810.04927v2.pdf | |
| PWC | https://paperswithcode.com/paper/vipl-hr-a-multi-modal-database-for-pulse |
| Repo | |
| Framework | |
Analysing Dropout and Compounding Errors in Neural Language Models
| Title | Analysing Dropout and Compounding Errors in Neural Language Models |
| Authors | James O’ Neill, Danushka Bollegala |
| Abstract | This paper carries out an empirical analysis of various dropout techniques for language modelling, such as Bernoulli dropout, Gaussian dropout, Curriculum Dropout, Variational Dropout and Concrete Dropout. Moreover, we propose an extension of variational dropout to concrete dropout and curriculum dropout with varying schedules. We find these extensions to perform well when compared to standard dropout approaches, particularly variational curriculum dropout with a linear schedule. Largest performance increases are made when applying dropout on the decoder layer. Lastly, we analyze where most of the errors occur at test time as a post-analysis step to determine if the well-known problem of compounding errors is apparent and to what end do the proposed methods mitigate this issue for each dataset. We report results on a 2-hidden layer LSTM, GRU and Highway network with embedding dropout, dropout on the gated hidden layers and the output projection layer for each model. We report our results on Penn-TreeBank and WikiText-2 word-level language modelling datasets, where the former reduces the long-tail distribution through preprocessing and one which preserves rare words in the training and test set. |
| Tasks | Language Modelling |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.00998v1 |
| http://arxiv.org/pdf/1811.00998v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysing-dropout-and-compounding-errors-in |
| Repo | |
| Framework | |
Capacity Control of ReLU Neural Networks by Basis-path Norm
| Title | Capacity Control of ReLU Neural Networks by Basis-path Norm |
| Authors | Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu |
| Abstract | Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property of ReLU into account. It has been shown that the generalization error bound in terms of the path norm explains the empirical generalization behaviors of the ReLU neural networks better than that of other capacity measures. Moreover, optimization algorithms which take path norm as the regularization term to the loss function, like Path-SGD, have been shown to achieve better generalization performance. However, the path norm counts the values of all paths, and hence the capacity measure based on path norm could be improperly influenced by the dependency among different paths. It is also known that each path of a ReLU network can be represented by a small group of linearly independent basis paths with multiplication and division operation, which indicates that the generalization behavior of the network only depends on only a few basis paths. Motivated by this, we propose a new norm \emph{Basis-path Norm} based on a group of linearly independent paths to measure the capacity of neural networks more accurately. We establish a generalization error bound based on this basis path norm, and show it explains the generalization behaviors of ReLU networks more accurately than previous capacity measures via extensive experiments. In addition, we develop optimization algorithms which minimize the empirical risk regularized by the basis-path norm. Our experiments on benchmark datasets demonstrate that the proposed regularization method achieves clearly better performance on the test set than the previous regularization approaches. |
| Tasks | |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.07122v1 |
| http://arxiv.org/pdf/1809.07122v1.pdf | |
| PWC | https://paperswithcode.com/paper/capacity-control-of-relu-neural-networks-by |
| Repo | |
| Framework | |
The Virtuous Machine - Old Ethics for New Technology?
| Title | The Virtuous Machine - Old Ethics for New Technology? |
| Authors | Nicolas Berberich, Klaus Diepold |
| Abstract | Modern AI and robotic systems are characterized by a high and ever-increasing level of autonomy. At the same time, their applications in fields such as autonomous driving, service robotics and digital personal assistants move closer to humans. From the combination of both developments emerges the field of AI ethics which recognizes that the actions of autonomous machines entail moral dimensions and tries to answer the question of how we can build moral machines. In this paper we argue for taking inspiration from Aristotelian virtue ethics by showing that it forms a suitable combination with modern AI due to its focus on learning from experience. We furthermore propose that imitation learning from moral exemplars, a central concept in virtue ethics, can solve the value alignment problem. Finally, we show that an intelligent system endowed with the virtues of temperance and friendship to humans would not pose a control problem as it would not have the desire for limitless self-improvement. |
| Tasks | Autonomous Driving, Imitation Learning |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10322v1 |
| http://arxiv.org/pdf/1806.10322v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-virtuous-machine-old-ethics-for-new |
| Repo | |
| Framework | |
Ain’t Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language
| Title | Ain’t Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language |
| Authors | Jakub Bednarek, Karol Piaskowski, Krzysztof Krawiec |
| Abstract | Program synthesis from natural language (NL) is practical for humans and, once technically feasible, would significantly facilitate software development and revolutionize end-user programming. We present SAPS, an end-to-end neural network capable of mapping relatively complex, multi-sentence NL specifications to snippets of executable code. The proposed architecture relies exclusively on neural components, and is trained on abstract syntax trees, combined with a pretrained word embedding and a bi-directional multi-layer LSTM for processing of word sequences. The decoder features a doubly-recurrent LSTM, for which we propose novel signal propagation schemes and soft attention mechanism. When applied to a large dataset of problems proposed in a previous study, SAPS performs on par with or better than the method proposed there, producing correct programs in over 92% of cases. In contrast to other methods, it does not require post-processing of the resulting programs, and uses a fixed-dimensional latent representation as the only interface between the NL analyzer and the source code generator. |
| Tasks | Program Synthesis |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09717v2 |
| http://arxiv.org/pdf/1810.09717v2.pdf | |
| PWC | https://paperswithcode.com/paper/aint-nobody-got-time-for-coding-structure |
| Repo | |
| Framework | |
Learning data augmentation policies using augmented random search
| Title | Learning data augmentation policies using augmented random search |
| Authors | Mingyang Geng, Kele Xu, Bo Ding, Huaimin Wang, Lei Zhang |
| Abstract | Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment searches for the augmentation polices in the discrete search space, which may lead to a sub-optimal solution. In this paper, we employ the Augmented Random Search method (ARS) to improve the performance of AutoAugment. Our key contribution is to change the discrete search space to continuous space, which will improve the searching performance and maintain the diversities between sub-policies. With the proposed method, state-of-the-art accuracies are achieved on CIFAR-10, CIFAR-100, and ImageNet (without additional data). Our code is available at https://github.com/gmy2013/ARS-Aug. |
| Tasks | Data Augmentation |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04768v1 |
| http://arxiv.org/pdf/1811.04768v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-data-augmentation-policies-using |
| Repo | |
| Framework | |
Bayesian Counterfactual Risk Minimization
| Title | Bayesian Counterfactual Risk Minimization |
| Authors | Ben London, Ted Sandler |
| Abstract | We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, potentially data-dependent, regularization technique for CRM. Experimental results indicate that this technique outperforms standard $L_2$ regularization, and that it is competitive with variance regularization while being both simpler to implement and more computationally efficient. |
| Tasks | |
| Published | 2018-06-29 |
| URL | https://arxiv.org/abs/1806.11500v5 |
| https://arxiv.org/pdf/1806.11500v5.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-counterfactual-risk-minimization |
| Repo | |
| Framework | |
Constructing Graph Node Embeddings via Discrimination of Similarity Distributions
| Title | Constructing Graph Node Embeddings via Discrimination of Similarity Distributions |
| Authors | Stanislav Tsepa, Maxim Panov |
| Abstract | The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science. In this work we propose a novel framework, which is aimed to find embeddings by \textit{discriminating distributions of similarities (DDoS)} between nodes in the graph. The general idea is implemented by maximizing the \textit{earth mover distance} between distributions of decoded similarities of similar and dissimilar nodes. The resulting algorithm generates embeddings which give a state-of-the-art performance in the problem of link prediction in real-world graphs. |
| Tasks | Link Prediction |
| Published | 2018-10-06 |
| URL | http://arxiv.org/abs/1810.03032v1 |
| http://arxiv.org/pdf/1810.03032v1.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-graph-node-embeddings-via |
| Repo | |
| Framework | |
Beyond Binomial and Negative Binomial: Adaptation in Bernoulli Parameter Estimation
| Title | Beyond Binomial and Negative Binomial: Adaptation in Bernoulli Parameter Estimation |
| Authors | Safa C. Medin, John Murray-Bruce, David Castañón, Vivek K Goyal |
| Abstract | Estimating the parameter of a Bernoulli process arises in many applications, including photon-efficient active imaging where each illumination period is regarded as a single Bernoulli trial. Motivated by acquisition efficiency when multiple Bernoulli processes are of interest, we formulate the allocation of trials under a constraint on the mean as an optimal resource allocation problem. An oracle-aided trial allocation demonstrates that there can be a significant advantage from varying the allocation for different processes and inspires a simple trial allocation gain quantity. Motivated by realizing this gain without an oracle, we present a trellis-based framework for representing and optimizing stopping rules. Considering the convenient case of Beta priors, three implementable stopping rules with similar performances are explored, and the simplest of these is shown to asymptotically achieve the oracle-aided trial allocation. These approaches are further extended to estimating functions of a Bernoulli parameter. In simulations inspired by realistic active imaging scenarios, we demonstrate significant mean-squared error improvements: up to 4.36 dB for the estimation of p and up to 1.80 dB for the estimation of log p. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.08801v2 |
| http://arxiv.org/pdf/1809.08801v2.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-binomial-and-negative-binomial |
| Repo | |
| Framework | |
A Co-Matching Model for Multi-choice Reading Comprehension
| Title | A Co-Matching Model for Multi-choice Reading Comprehension |
| Authors | Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang |
| Abstract | Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance. |
| Tasks | Reading Comprehension |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.04068v1 |
| http://arxiv.org/pdf/1806.04068v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-co-matching-model-for-multi-choice-reading |
| Repo | |
| Framework | |
Instance-level Facial Attributes Transfer with Geometry-Aware Flow
| Title | Instance-level Facial Attributes Transfer with Geometry-Aware Flow |
| Authors | Weidong Yin, Ziwei Liu, Chen Change Loy |
| Abstract | We address the problem of instance-level facial attribute transfer without paired training data, e.g. faithfully transferring the exact mustache from a source face to a target face. This is a more challenging task than the conventional semantic-level attribute transfer, which only preserves the generic attribute style instead of instance-level traits. We propose the use of geometry-aware flow, which serves as a well-suited representation for modeling the transformation between instance-level facial attributes. Specifically, we leverage the facial landmarks as the geometric guidance to learn the differentiable flows automatically, despite of the large pose gap existed. Geometry-aware flow is able to warp the source face attribute into the target face context and generate a warp-and-blend result. To compensate for the potential appearance gap between source and target faces, we propose a hallucination sub-network that produces an appearance residual to further refine the warp-and-blend result. Finally, a cycle-consistency framework consisting of both attribute transfer module and attribute removal module is designed, so that abundant unpaired face images can be used as training data. Extensive evaluations validate the capability of our approach in transferring instance-level facial attributes faithfully across large pose and appearance gaps. Thanks to the flow representation, our approach can readily be applied to generate realistic details on high-resolution images. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12670v1 |
| http://arxiv.org/pdf/1811.12670v1.pdf | |
| PWC | https://paperswithcode.com/paper/instance-level-facial-attributes-transfer |
| Repo | |
| Framework | |
From Bayesian Inference to Logical Bayesian Inference: A New Mathematical Frame for Semantic Communication and Machine Learning
| Title | From Bayesian Inference to Logical Bayesian Inference: A New Mathematical Frame for Semantic Communication and Machine Learning |
| Authors | Chenguang Lu |
| Abstract | Bayesian Inference (BI) uses the Bayes’ posterior whereas Logical Bayesian Inference (LBI) uses the truth function or membership function as the inference tool. LBI was proposed because BI was not compatible with the classical Bayes’ prediction and didn’t use logical probability and hence couldn’t express semantic meaning. In LBI, statistical probability and logical probability are strictly distinguished, used at the same time, and linked by the third kind of Bayes’ Theorem. The Shannon channel consists of a set of transition probability functions whereas the semantic channel consists of a set of truth functions. When a sample is large enough, we can directly derive the semantic channel from Shannon’s channel. Otherwise, we can use parameters to construct truth functions and use the Maximum Semantic Information (MSI) criterion to optimize the truth functions. The MSI criterion is equivalent to the Maximum Likelihood (ML) criterion, and compatible with the Regularized Least Square (RLS) criterion. By matching the two channels one with another, we can obtain the Channels’ Matching (CM) algorithm. This algorithm can improve multi-label classifications, maximum likelihood estimations (including unseen instance classifications), and mixture models. In comparison with BI, LBI 1) uses the prior P(X) of X instead of that of Y or {\theta} and fits cases where the source P(X) changes, 2) can be used to solve the denotations of labels, and 3) is more compatible with the classical Bayes’ prediction and likelihood method. LBI also provides a confirmation measure between -1 and 1 for induction. |
| Tasks | Bayesian Inference |
| Published | 2018-09-03 |
| URL | http://arxiv.org/abs/1809.01577v1 |
| http://arxiv.org/pdf/1809.01577v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-bayesian-inference-to-logical-bayesian |
| Repo | |
| Framework | |
Inference Over Programs That Make Predictions
| Title | Inference Over Programs That Make Predictions |
| Authors | Yura Perov |
| Abstract | This abstract extends on the previous work (arXiv:1407.2646, arXiv:1606.00075) on program induction using probabilistic programming. It describes possible further steps to extend that work, such that, ultimately, automatic probabilistic program synthesis can generalise over any reasonable set of inputs and outputs, in particular in regard to text, image and video data. |
| Tasks | Probabilistic Programming, Program Synthesis |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01190v1 |
| http://arxiv.org/pdf/1810.01190v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-over-programs-that-make-predictions |
| Repo | |
| Framework | |
