Paper Group ANR 778
Learning like humans with Deep Symbolic Networks. Standard detectors aren’t (currently) fooled by physical adversarial stop signs. Non-Projective Dependency Parsing with Non-Local Transitions. Submodular Trajectory Optimization for Aerial 3D Scanning. An Unsupervised Approach for Overlapping Cervical Cell Cytoplasm Segmentation. A Semi-Supervised A …
Learning like humans with Deep Symbolic Networks
| Title | Learning like humans with Deep Symbolic Networks |
| Authors | Qunzhi Zhang, Didier Sornette |
| Abstract | We introduce the Deep Symbolic Network (DSN) model, which aims at becoming the white-box version of Deep Neural Networks (DNN). The DSN model provides a simple, universal yet powerful structure, similar to DNN, to represent any knowledge of the world, which is transparent to humans. The conjecture behind the DSN model is that any type of real world objects sharing enough common features are mapped into human brains as a symbol. Those symbols are connected by links, representing the composition, correlation, causality, or other relationships between them, forming a deep, hierarchical symbolic network structure. Powered by such a structure, the DSN model is expected to learn like humans, because of its unique characteristics. First, it is universal, using the same structure to store any knowledge. Second, it can learn symbols from the world and construct the deep symbolic networks automatically, by utilizing the fact that real world objects have been naturally separated by singularities. Third, it is symbolic, with the capacity of performing causal deduction and generalization. Fourth, the symbols and the links between them are transparent to us, and thus we will know what it has learned or not - which is the key for the security of an AI system. Fifth, its transparency enables it to learn with relatively small data. Sixth, its knowledge can be accumulated. Last but not least, it is more friendly to unsupervised learning than DNN. We present the details of the model, the algorithm powering its automatic learning ability, and describe its usefulness in different use cases. The purpose of this paper is to generate broad interest to develop it within an open source project centered on the Deep Symbolic Network (DSN) model towards the development of general AI. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03377v2 |
| http://arxiv.org/pdf/1707.03377v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-like-humans-with-deep-symbolic |
| Repo | |
| Framework | |
Standard detectors aren’t (currently) fooled by physical adversarial stop signs
| Title | Standard detectors aren’t (currently) fooled by physical adversarial stop signs |
| Authors | Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth |
| Abstract | An adversarial example is an example that has been adjusted to produce the wrong label when presented to a system at test time. If adversarial examples existed that could fool a detector, they could be used to (for example) wreak havoc on roads populated with smart vehicles. Recently, we described our difficulties creating physical adversarial stop signs that fool a detector. More recently, Evtimov et al. produced a physical adversarial stop sign that fools a proxy model of a detector. In this paper, we show that these physical adversarial stop signs do not fool two standard detectors (YOLO and Faster RCNN) in standard configuration. Evtimov et al.‘s construction relies on a crop of the image to the stop sign; this crop is then resized and presented to a classifier. We argue that the cropping and resizing procedure largely eliminates the effects of rescaling and of view angle. Whether an adversarial attack is robust under rescaling and change of view direction remains moot. We argue that attacking a classifier is very different from attacking a detector, and that the structure of detectors - which must search for their own bounding box, and which cannot estimate that box very accurately - likely makes it difficult to make adversarial patterns. Finally, an adversarial pattern on a physical object that could fool a detector would have to be adversarial in the face of a wide family of parametric distortions (scale; view angle; box shift inside the detector; illumination; and so on). Such a pattern would be of great theoretical and practical interest. There is currently no evidence that such patterns exist. |
| Tasks | Adversarial Attack |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03337v2 |
| http://arxiv.org/pdf/1710.03337v2.pdf | |
| PWC | https://paperswithcode.com/paper/standard-detectors-arent-currently-fooled-by |
| Repo | |
| Framework | |
Non-Projective Dependency Parsing with Non-Local Transitions
| Title | Non-Projective Dependency Parsing with Non-Local Transitions |
| Authors | Daniel Fernández-González, Carlos Gómez-Rodríguez |
| Abstract | We present a novel transition system, based on the Covington non-projective parser, introducing non-local transitions that can directly create arcs involving nodes to the left of the current focus positions. This avoids the need for long sequences of No-Arc transitions to create long-distance arcs, thus alleviating error propagation. The resulting parser outperforms the original version and achieves the best accuracy on the Stanford Dependencies conversion of the Penn Treebank among greedy transition-based algorithms. |
| Tasks | Dependency Parsing |
| Published | 2017-10-25 |
| URL | http://arxiv.org/abs/1710.09340v3 |
| http://arxiv.org/pdf/1710.09340v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-projective-dependency-parsing-with-non |
| Repo | |
| Framework | |
Submodular Trajectory Optimization for Aerial 3D Scanning
| Title | Submodular Trajectory Optimization for Aerial 3D Scanning |
| Authors | Mike Roberts, Debadeepta Dey, Anh Truong, Sudipta Sinha, Shital Shah, Ashish Kapoor, Pat Hanrahan, Neel Joshi |
| Abstract | Drones equipped with cameras are emerging as a powerful tool for large-scale aerial 3D scanning, but existing automatic flight planners do not exploit all available information about the scene, and can therefore produce inaccurate and incomplete 3D models. We present an automatic method to generate drone trajectories, such that the imagery acquired during the flight will later produce a high-fidelity 3D model. Our method uses a coarse estimate of the scene geometry to plan camera trajectories that: (1) cover the scene as thoroughly as possible; (2) encourage observations of scene geometry from a diverse set of viewing angles; (3) avoid obstacles; and (4) respect a user-specified flight time budget. Our method relies on a mathematical model of scene coverage that exhibits an intuitive diminishing returns property known as submodularity. We leverage this property extensively to design a trajectory planning algorithm that reasons globally about the non-additive coverage reward obtained across a trajectory, jointly with the cost of traveling between views. We evaluate our method by using it to scan three large outdoor scenes, and we perform a quantitative evaluation using a photorealistic video game simulator. |
| Tasks | |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00703v3 |
| http://arxiv.org/pdf/1705.00703v3.pdf | |
| PWC | https://paperswithcode.com/paper/submodular-trajectory-optimization-for-aerial |
| Repo | |
| Framework | |
An Unsupervised Approach for Overlapping Cervical Cell Cytoplasm Segmentation
| Title | An Unsupervised Approach for Overlapping Cervical Cell Cytoplasm Segmentation |
| Authors | Pranav Kumar, S L Happy, Swarnadip Chatterjee, Debdoot Sheet, Aurobinda Routray |
| Abstract | The poor contrast and the overlapping of cervical cell cytoplasm are the major issues in the accurate segmentation of cervical cell cytoplasm. This paper presents an automated unsupervised cytoplasm segmentation approach which can effectively find the cytoplasm boundaries in overlapping cells. The proposed approach first segments the cell clumps from the cervical smear image and detects the nuclei in each cell clump. A modified Otsu method with prior class probability is proposed for accurate segmentation of nuclei from the cell clumps. Using distance regularized level set evolution, the contour around each nucleus is evolved until it reaches the cytoplasm boundaries. Promising results were obtained by experimenting on ISBI 2015 challenge dataset. |
| Tasks | |
| Published | 2017-02-17 |
| URL | http://arxiv.org/abs/1702.05506v1 |
| http://arxiv.org/pdf/1702.05506v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-approach-for-overlapping |
| Repo | |
| Framework | |
A Semi-Supervised Approach to Detecting Stance in Tweets
| Title | A Semi-Supervised Approach to Detecting Stance in Tweets |
| Authors | Amita Misra, Brian Ecker, Theodore Handleman, Nicolas Hahn, Marilyn Walker |
| Abstract | Stance classification aims to identify, for a particular issue under discussion, whether the speaker or author of a conversational turn has Pro (Favor) or Con (Against) stance on the issue. Detecting stance in tweets is a new task proposed for SemEval-2016 Task6, involving predicting stance for a dataset of tweets on the topics of abortion, atheism, climate change, feminism and Hillary Clinton. Given the small size of the dataset, our team created our own topic-specific training corpus by developing a set of high precision hashtags for each topic that were used to query the twitter API, with the aim of developing a large training corpus without additional human labeling of tweets for stance. The hashtags selected for each topic were predicted to be stance-bearing on their own. Experimental results demonstrate good performance for our features for opinion-target pairs based on generalizing dependency features using sentiment lexicons. |
| Tasks | |
| Published | 2017-09-03 |
| URL | http://arxiv.org/abs/1709.01895v1 |
| http://arxiv.org/pdf/1709.01895v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-supervised-approach-to-detecting |
| Repo | |
| Framework | |
Seeing What Is Not There: Learning Context to Determine Where Objects Are Missing
| Title | Seeing What Is Not There: Learning Context to Determine Where Objects Are Missing |
| Authors | Jin Sun, David W. Jacobs |
| Abstract | Most of computer vision focuses on what is in an image. We propose to train a standalone object-centric context representation to perform the opposite task: seeing what is not there. Given an image, our context model can predict where objects should exist, even when no object instances are present. Combined with object detection results, we can perform a novel vision task: finding where objects are missing in an image. Our model is based on a convolutional neural network structure. With a specially designed training strategy, the model learns to ignore objects and focus on context only. It is fully convolutional thus highly efficient. Experiments show the effectiveness of the proposed approach in one important accessibility task: finding city street regions where curb ramps are missing, which could help millions of people with mobility disabilities. |
| Tasks | Object Detection |
| Published | 2017-02-26 |
| URL | http://arxiv.org/abs/1702.07971v1 |
| http://arxiv.org/pdf/1702.07971v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-what-is-not-there-learning-context-to |
| Repo | |
| Framework | |
Sentence-level dialects identification in the greater China region
| Title | Sentence-level dialects identification in the greater China region |
| Authors | Fan Xu, Mingwen Wang, Maoxi Li |
| Abstract | Identifying the different varieties of the same language is more challenging than unrelated languages identification. In this paper, we propose an approach to discriminate language varieties or dialects of Mandarin Chinese for the Mainland China, Hong Kong, Taiwan, Macao, Malaysia and Singapore, a.k.a., the Greater China Region (GCR). When applied to the dialects identification of the GCR, we find that the commonly used character-level or word-level uni-gram feature is not very efficient since there exist several specific problems such as the ambiguity and context-dependent characteristic of words in the dialects of the GCR. To overcome these challenges, we use not only the general features like character-level n-gram, but also many new word-level features, including PMI-based and word alignment-based features. A series of evaluation results on both the news and open-domain dataset from Wikipedia show the effectiveness of the proposed approach. |
| Tasks | Word Alignment |
| Published | 2017-01-08 |
| URL | http://arxiv.org/abs/1701.01908v1 |
| http://arxiv.org/pdf/1701.01908v1.pdf | |
| PWC | https://paperswithcode.com/paper/sentence-level-dialects-identification-in-the |
| Repo | |
| Framework | |
Language modeling with Neural trans-dimensional random fields
| Title | Language modeling with Neural trans-dimensional random fields |
| Authors | Bin Wang, Zhijian Ou |
| Abstract | Trans-dimensional random field language models (TRF LMs) have recently been introduced, where sentences are modeled as a collection of random fields. The TRF approach has been shown to have the advantages of being computationally more efficient in inference than LSTM LMs with close performance and being able to flexibly integrating rich features. In this paper we propose neural TRFs, beyond of the previous discrete TRFs that only use linear potentials with discrete features. The idea is to use nonlinear potentials with continuous features, implemented by neural networks (NNs), in the TRF framework. Neural TRFs combine the advantages of both NNs and TRFs. The benefits of word embedding, nonlinear feature learning and larger context modeling are inherited from the use of NNs. At the same time, the strength of efficient inference by avoiding expensive softmax is preserved. A number of technical contributions, including employing deep convolutional neural networks (CNNs) to define the potentials and incorporating the joint stochastic approximation (JSA) strategy in the training algorithm, are developed in this work, which enable us to successfully train neural TRF LMs. Various LMs are evaluated in terms of speech recognition WERs by rescoring the 1000-best lists of WSJ’92 test data. The results show that neural TRF LMs not only improve over discrete TRF LMs, but also perform slightly better than LSTM LMs with only one fifth of parameters and 16x faster inference efficiency. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2017-07-23 |
| URL | http://arxiv.org/abs/1707.07240v3 |
| http://arxiv.org/pdf/1707.07240v3.pdf | |
| PWC | https://paperswithcode.com/paper/language-modeling-with-neural-trans |
| Repo | |
| Framework | |
Extractive Summarization: Limits, Compression, Generalized Model and Heuristics
| Title | Extractive Summarization: Limits, Compression, Generalized Model and Heuristics |
| Authors | Rakesh Verma, Daniel Lee |
| Abstract | Due to its promise to alleviate information overload, text summarization has attracted the attention of many researchers. However, it has remained a serious challenge. Here, we first prove empirical limits on the recall (and F1-scores) of extractive summarizers on the DUC datasets under ROUGE evaluation for both the single-document and multi-document summarization tasks. Next we define the concept of compressibility of a document and present a new model of summarization, which generalizes existing models in the literature and integrates several dimensions of the summarization, viz., abstractive versus extractive, single versus multi-document, and syntactic versus semantic. Finally, we examine some new and existing single-document summarization algorithms in a single framework and compare with state of the art summarizers on DUC data. |
| Tasks | Document Summarization, Multi-Document Summarization, Text Summarization |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05550v1 |
| http://arxiv.org/pdf/1704.05550v1.pdf | |
| PWC | https://paperswithcode.com/paper/extractive-summarization-limits-compression |
| Repo | |
| Framework | |
Manifold Learning Using Kernel Density Estimation and Local Principal Components Analysis
| Title | Manifold Learning Using Kernel Density Estimation and Local Principal Components Analysis |
| Authors | Kitty Mohammed, Hariharan Narayanan |
| Abstract | We consider the problem of recovering a $d-$dimensional manifold $\mathcal{M} \subset \mathbb{R}^n$ when provided with noiseless samples from $\mathcal{M}$. There are many algorithms (e.g., Isomap) that are used in practice to fit manifolds and thus reduce the dimensionality of a given data set. Ideally, the estimate $\mathcal{M}\mathrm{put}$ of $\mathcal{M}$ should be an actual manifold of a certain smoothness; furthermore, $\mathcal{M}\mathrm{put}$ should be arbitrarily close to $\mathcal{M}$ in Hausdorff distance given a large enough sample. Generally speaking, existing manifold learning algorithms do not meet these criteria. Fefferman, Mitter, and Narayanan (2016) have developed an algorithm whose output is provably a manifold. The key idea is to define an approximate squared-distance function (asdf) to $\mathcal{M}$. Then, $\mathcal{M}\mathrm{put}$ is given by the set of points where the gradient of the asdf is orthogonal to the subspace spanned by the largest $n - d$ eigenvectors of the Hessian of the asdf. As long as the asdf meets certain regularity conditions, $\mathcal{M}\mathrm{put}$ is a manifold that is arbitrarily close in Hausdorff distance to $\mathcal{M}$. In this paper, we define two asdfs that can be calculated from the data and show that they meet the required regularity conditions. The first asdf is based on kernel density estimation, and the second is based on estimation of tangent spaces using local principal components analysis. |
| Tasks | Density Estimation |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03615v1 |
| http://arxiv.org/pdf/1709.03615v1.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-learning-using-kernel-density |
| Repo | |
| Framework | |
Shape-Based Approach to Household Load Curve Clustering and Prediction
| Title | Shape-Based Approach to Household Load Curve Clustering and Prediction |
| Authors | Thanchanok Teeraratkul, Daniel O’Neill, Sanjay Lall |
| Abstract | Consumer Demand Response (DR) is an important research and industry problem, which seeks to categorize, predict and modify consumer’s energy consumption. Unfortunately, traditional clustering methods have resulted in many hundreds of clusters, with a given consumer often associated with several clusters, making it difficult to classify consumers into stable representative groups and to predict individual energy consumption patterns. In this paper, we present a shape-based approach that better classifies and predicts consumer energy consumption behavior at the household level. The method is based on Dynamic Time Warping. DTW seeks an optimal alignment between energy consumption patterns reflecting the effect of hidden patterns of regular consumer behavior. Using real consumer 24-hour load curves from Opower Corporation, our method results in a 50% reduction in the number of representative groups and an improvement in prediction accuracy measured under DTW distance. We extend the approach to estimate which electrical devices will be used and in which hours. |
| Tasks | |
| Published | 2017-02-05 |
| URL | http://arxiv.org/abs/1702.01414v1 |
| http://arxiv.org/pdf/1702.01414v1.pdf | |
| PWC | https://paperswithcode.com/paper/shape-based-approach-to-household-load-curve |
| Repo | |
| Framework | |
Well-supported phylogenies using largest subsets of core-genes by discrete particle swarm optimization
| Title | Well-supported phylogenies using largest subsets of core-genes by discrete particle swarm optimization |
| Authors | Reem Alsrraj, Bassam AlKindy, Christophe Guyeux, Laurent Philippe, Jean-François Couchot |
| Abstract | The number of complete chloroplastic genomes increases day after day, making it possible to rethink plants phylogeny at the biomolecular era. Given a set of close plants sharing in the order of one hundred of core chloroplastic genes, this article focuses on how to extract the largest subset of sequences in order to obtain the most supported species tree. Due to computational complexity, a discrete and distributed Particle Swarm Optimization (DPSO) is proposed. It is finally applied to the core genes of Rosales order. |
| Tasks | |
| Published | 2017-06-25 |
| URL | http://arxiv.org/abs/1706.08514v1 |
| http://arxiv.org/pdf/1706.08514v1.pdf | |
| PWC | https://paperswithcode.com/paper/well-supported-phylogenies-using-largest |
| Repo | |
| Framework | |
Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
| Title | Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge |
| Authors | Emmanuel de Bezenac, Arthur Pajot, Patrick Gallinari |
| Abstract | We consider the use of Deep Learning methods for modeling complex phenomena like those occurring in natural physical processes. With the large amount of data gathered on these phenomena the data intensive paradigm could begin to challenge more traditional approaches elaborated over the years in fields like maths or physics. However, despite considerable successes in a variety of application domains, the machine learning field is not yet ready to handle the level of complexity required by such problems. Using an example application, namely Sea Surface Temperature Prediction, we show how general background knowledge gained from physics could be used as a guideline for designing efficient Deep Learning models. In order to motivate the approach and to assess its generality we demonstrate a formal link between the solution of a class of differential equations underlying a large family of physical phenomena and the proposed model. Experiments and comparison with series of baselines including a state of the art numerical approach is then provided. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07970v2 |
| http://arxiv.org/pdf/1711.07970v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-physical-processes |
| Repo | |
| Framework | |
Robust Online Multi-Task Learning with Correlative and Personalized Structures
| Title | Robust Online Multi-Task Learning with Correlative and Personalized Structures |
| Authors | Peng Yang, Peilin Zhao, Xin Gao |
| Abstract | Multi-Task Learning (MTL) can enhance a classifier’s generalization performance by learning multiple related tasks simultaneously. Conventional MTL works under the offline or batch setting, and suffers from expensive training cost and poor scalability. To address such inefficiency issues, online learning techniques have been applied to solve MTL problems. However, most existing algorithms of online MTL constrain task relatedness into a presumed structure via a single weight matrix, which is a strict restriction that does not always hold in practice. In this paper, we propose a robust online MTL framework that overcomes this restriction by decomposing the weight matrix into two components: the first one captures the low-rank common structure among tasks via a nuclear norm and the second one identifies the personalized patterns of outlier tasks via a group lasso. Theoretical analysis shows the proposed algorithm can achieve a sub-linear regret with respect to the best linear model in hindsight. Even though the above framework achieves good performance, the nuclear norm that simply adds all nonzero singular values together may not be a good low-rank approximation. To improve the results, we use a log-determinant function as a non-convex rank approximation. The gradient scheme is applied to optimize log-determinant function and can obtain a closed-form solution for this refined problem. Experimental results on a number of real-world applications verify the efficacy of our method. |
| Tasks | Multi-Task Learning |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01824v1 |
| http://arxiv.org/pdf/1706.01824v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-online-multi-task-learning-with |
| Repo | |
| Framework | |
