Paper Group ANR 564
Measuring and Discovering Correlations in Large Data Sets. How to avoid ethically relevant Machine Consciousness. Disaggregation of SMAP L3 Brightness Temperatures to 9km using Kernel Machines. Corpus-level Fine-grained Entity Typing Using Contextual Information. Existence of Hierarchies and Human’s Pursuit of Top Hierarchy Lead to Power Law. Learn …
Measuring and Discovering Correlations in Large Data Sets
| Title | Measuring and Discovering Correlations in Large Data Sets |
| Authors | Lijue Liu, Ming Li, Sha Wen |
| Abstract | In this paper, a class of statistics named ART (the alternant recursive topology statistics) is proposed to measure the properties of correlation between two variables. A wide range of bi-variable correlations both linear and nonlinear can be evaluated by ART efficiently and equitably even if nothing is known about the specific types of those relationships. ART compensates the disadvantages of Reshef’s model in which no polynomial time precise algorithm exists and the “local random” phenomenon can not be identified. As a class of nonparametric exploration statistics, ART is applied for analyzing a dataset of 10 American classical indexes, as a result, lots of bi-variable correlations are discovered. |
| Tasks | |
| Published | 2016-01-07 |
| URL | http://arxiv.org/abs/1602.07960v1 |
| http://arxiv.org/pdf/1602.07960v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-and-discovering-correlations-in |
| Repo | |
| Framework | |
How to avoid ethically relevant Machine Consciousness
| Title | How to avoid ethically relevant Machine Consciousness |
| Authors | Aleksander Lodwich |
| Abstract | This paper discusses the root cause of systems perceiving the self experience and how to exploit adaptive and learning features without introducing ethically problematic system properties. |
| Tasks | |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1606.00058v2 |
| http://arxiv.org/pdf/1606.00058v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-to-avoid-ethically-relevant-machine |
| Repo | |
| Framework | |
Disaggregation of SMAP L3 Brightness Temperatures to 9km using Kernel Machines
| Title | Disaggregation of SMAP L3 Brightness Temperatures to 9km using Kernel Machines |
| Authors | Subit Chakrabarti, Tara Bongiovanni, Jasmeet Judge, Anand Rangarajan, Sanjay Ranka |
| Abstract | In this study, a machine learning algorithm is used for disaggregation of SMAP brightness temperatures (T$_{\textrm{B}}$) from 36km to 9km. It uses image segmentation to cluster the study region based on meteorological and land cover similarity, followed by a support vector machine based regression that computes the value of the disaggregated T$_{\textrm{B}}$ at all pixels. High resolution remote sensing products such as land surface temperature, normalized difference vegetation index, enhanced vegetation index, precipitation, soil texture, and land-cover were used for disaggregation. The algorithm was implemented in Iowa, United States, from April to July 2015, and compared with the SMAP L3_SM_AP T$_{\textrm{B}}$ product at 9km. It was found that the disaggregated T$_{\textrm{B}}$ were very similar to the SMAP-T$_{\textrm{B}}$ product, even for vegetated areas with a mean difference $\leq$ 5K. However, the standard deviation of the disaggregation was lower by 7K than that of the AP product. The probability density functions of the disaggregated T$_{\textrm{B}}$ were similar to the SMAP-T$_{\textrm{B}}$. The results indicate that this algorithm may be used for disaggregating T$_{\textrm{B}}$ using complex non-linear correlations on a grid. |
| Tasks | Semantic Segmentation |
| Published | 2016-01-20 |
| URL | http://arxiv.org/abs/1601.05350v2 |
| http://arxiv.org/pdf/1601.05350v2.pdf | |
| PWC | https://paperswithcode.com/paper/disaggregation-of-smap-l3-brightness |
| Repo | |
| Framework | |
Corpus-level Fine-grained Entity Typing Using Contextual Information
| Title | Corpus-level Fine-grained Entity Typing Using Contextual Information |
| Authors | Yadollah Yaghoobzadeh, Hinrich Schütze |
| Abstract | This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class such as “food” or “artist”. The application of entity typing we are interested in is knowledge base completion, specifically, to learn which classes an entity is a member of. We propose FIGMENT to tackle this problem. FIGMENT is embedding-based and combines (i) a global model that scores based on aggregated contextual information of an entity and (ii) a context model that first scores the individual occurrences of an entity and then aggregates the scores. In our evaluation, FIGMENT strongly outperforms an approach to entity typing that relies on relations obtained by an open information extraction system. |
| Tasks | Entity Typing, Knowledge Base Completion, Open Information Extraction |
| Published | 2016-06-25 |
| URL | http://arxiv.org/abs/1606.07901v1 |
| http://arxiv.org/pdf/1606.07901v1.pdf | |
| PWC | https://paperswithcode.com/paper/corpus-level-fine-grained-entity-typing-using |
| Repo | |
| Framework | |
Existence of Hierarchies and Human’s Pursuit of Top Hierarchy Lead to Power Law
| Title | Existence of Hierarchies and Human’s Pursuit of Top Hierarchy Lead to Power Law |
| Authors | Shuiyuan Yu, Junying Liang, Haitao Liu |
| Abstract | The power law is ubiquitous in natural and social phenomena, and is considered as a universal relationship between the frequency and its rank for diverse social systems. However, a general model is still lacking to interpret why these seemingly unrelated systems share great similarity. Through a detailed analysis of natural language texts and simulation experiments based on the proposed ‘Hierarchical Selection Model’, we found that the existence of hierarchies and human’s pursuit of top hierarchy lead to the power law. Further, the power law is a statistical and emergent performance of hierarchies, and it is the universality of hierarchies that contributes to the ubiquity of the power law. |
| Tasks | |
| Published | 2016-09-24 |
| URL | http://arxiv.org/abs/1609.07680v1 |
| http://arxiv.org/pdf/1609.07680v1.pdf | |
| PWC | https://paperswithcode.com/paper/existence-of-hierarchies-and-humans-pursuit |
| Repo | |
| Framework | |
Learning Subclass Representations for Visually-varied Image Classification
| Title | Learning Subclass Representations for Visually-varied Image Classification |
| Authors | Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic |
| Abstract | In this paper, we present a subclass-representation approach that predicts the probability of a social image belonging to one particular class. We explore the co-occurrence of user-contributed tags to find subclasses with a strong connection to the top level class. We then project each image on to the resulting subclass space to generate a subclass representation for the image. The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes. The novelty is also that the images are classified into smaller classes, which have a chance of being more visually stable and easier to model. These subclasses are used as a latent space and images are represented in this space by their probability of relatedness to all of the subclasses. In contrast to approaches directly modeling each top-level class based on the image content, the proposed method can exploit more information for visually diverse classes. The approach is evaluated on a set of $2$ million photos with 10 classes, released by the Multimedia 2013 Yahoo! Large-scale Flickr-tag Image Classification Grand Challenge. Experiments show that the proposed system delivers sound performance for visually diverse classes compared with methods that directly model top classes. |
| Tasks | Image Classification |
| Published | 2016-01-12 |
| URL | http://arxiv.org/abs/1601.02913v1 |
| http://arxiv.org/pdf/1601.02913v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-subclass-representations-for |
| Repo | |
| Framework | |
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
| Title | Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance |
| Authors | Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin |
| Abstract | At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model’s behavior. Assumed in this question are three properties of the interpretable output: coverage, precision, and effort. Coverage refers to how often humans think they can predict the model’s behavior, precision to how accurate humans are in those predictions, and effort is either the up-front effort required in interpreting the model, or the effort required to make predictions about a model’s behavior. In this work, we propose anchor-LIME (aLIME), a model-agnostic technique that produces high-precision rule-based explanations for which the coverage boundaries are very clear. We compare aLIME to linear LIME with simulated experiments, and demonstrate the flexibility of aLIME with qualitative examples from a variety of domains and tasks. |
| Tasks | Interpretable Machine Learning |
| Published | 2016-11-17 |
| URL | http://arxiv.org/abs/1611.05817v1 |
| http://arxiv.org/pdf/1611.05817v1.pdf | |
| PWC | https://paperswithcode.com/paper/nothing-else-matters-model-agnostic |
| Repo | |
| Framework | |
Meaningful Models: Utilizing Conceptual Structure to Improve Machine Learning Interpretability
| Title | Meaningful Models: Utilizing Conceptual Structure to Improve Machine Learning Interpretability |
| Authors | Nick Condry |
| Abstract | The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind’s construction of concepts and meaning can be used to create more interpretable machine learning models. By proposing a novel method of classifying concepts, in terms of ‘form’ and ‘function’, we elucidate the nature of meaning and offer proposals to improve model understandability. As machine learning begins to permeate daily life, interpretable models may serve as a bridge between domain-expert authors and non-expert users. |
| Tasks | Interpretable Machine Learning |
| Published | 2016-07-01 |
| URL | http://arxiv.org/abs/1607.00279v1 |
| http://arxiv.org/pdf/1607.00279v1.pdf | |
| PWC | https://paperswithcode.com/paper/meaningful-models-utilizing-conceptual |
| Repo | |
| Framework | |
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
| Title | Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval |
| Authors | Xiu-Shen Wei, Jian-Hao Luo, Jianxin Wu, Zhi-Hua Zhou |
| Abstract | Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require annotations for images in the new domain. In this paper, we focus on a novel and challenging task in the pure unsupervised setting: fine-grained image retrieval. Even with image labels, fine-grained images are difficult to classify, let alone the unsupervised retrieval task. We propose the Selective Convolutional Descriptor Aggregation (SCDA) method. SCDA firstly localizes the main object in fine-grained images, a step that discards the noisy background and keeps useful deep descriptors. The selected descriptors are then aggregated and dimensionality reduced into a short feature vector using the best practices we found. SCDA is unsupervised, using no image label or bounding box annotation. Experiments on six fine-grained datasets confirm the effectiveness of SCDA for fine-grained image retrieval. Besides, visualization of the SCDA features shows that they correspond to visual attributes (even subtle ones), which might explain SCDA’s high mean average precision in fine-grained retrieval. Moreover, on general image retrieval datasets, SCDA achieves comparable retrieval results with state-of-the-art general image retrieval approaches. |
| Tasks | Image Retrieval, Object Proposal Generation |
| Published | 2016-04-18 |
| URL | http://arxiv.org/abs/1604.04994v2 |
| http://arxiv.org/pdf/1604.04994v2.pdf | |
| PWC | https://paperswithcode.com/paper/selective-convolutional-descriptor |
| Repo | |
| Framework | |
Person Re-identification for Real-world Surveillance Systems
| Title | Person Re-identification for Real-world Surveillance Systems |
| Authors | Furqan M. Khan, Francois Bremond |
| Abstract | Appearance based person re-identification in a real-world video surveillance system with non-overlapping camera views is a challenging problem for many reasons. Current state-of-the-art methods often address the problem by relying on supervised learning of similarity metrics or ranking functions to implicitly model appearance transformation between cameras for each camera pair, or group, in the system. This requires considerable human effort to annotate data. Furthermore, the learned models are camera specific and not transferable from one set of cameras to another. Therefore, the annotation process is required after every network expansion or camera replacement, which strongly limits their applicability. Alternatively, we propose a novel modeling approach to harness complementary appearance information without supervised learning that significantly outperforms current state-of-the-art unsupervised methods on multiple benchmark datasets. |
| Tasks | Person Re-Identification |
| Published | 2016-07-20 |
| URL | http://arxiv.org/abs/1607.05975v1 |
| http://arxiv.org/pdf/1607.05975v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-for-real-world |
| Repo | |
| Framework | |
Variational methods for Conditional Multimodal Deep Learning
| Title | Variational methods for Conditional Multimodal Deep Learning |
| Authors | Gaurav Pandey, Ambedkar Dukkipati |
| Abstract | In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a joint distribution over multiple modalities using a deep multimodal architecture, we observe that such models aren’t very effective at conditional generation. Hence, we address the problem by learning conditional distributions between the modalities. We use variational methods for maximizing the corresponding conditional log-likelihood. The resultant deep model, which we refer to as conditional multimodal autoencoder (CMMA), forces the latent representation obtained from a single modality alone to be `close’ to the joint representation obtained from multiple modalities. We use the proposed model to generate faces from attributes. We show that the faces generated from attributes using the proposed model, are qualitatively and quantitatively more representative of the attributes from which they were generated, than those obtained by other deep generative models. We also propose a secondary task, whereby the existing faces are modified by modifying the corresponding attributes. We observe that the modifications in face introduced by the proposed model are representative of the corresponding modifications in attributes. | |
| Tasks | |
| Published | 2016-03-06 |
| URL | http://arxiv.org/abs/1603.01801v2 |
| http://arxiv.org/pdf/1603.01801v2.pdf | |
| PWC | https://paperswithcode.com/paper/variational-methods-for-conditional |
| Repo | |
| Framework | |
Ordering as privileged information
| Title | Ordering as privileged information |
| Authors | Thomas Vacek |
| Abstract | We propose to accelerate the rate of convergence of the pattern recognition task by directly minimizing the variance diameters of certain hypothesis spaces, which are critical quantities in fast-convergence results.We show that the variance diameters can be controlled by dividing hypothesis spaces into metric balls based on a new order metric. This order metric can be minimized as an ordinal regression problem, leading to a LUPI (Learning Using Privileged Information) application where we take the privileged information as some desired ordering, and construct a faster-converging hypothesis space by empirically restricting some larger hypothesis space according to that ordering. We give a risk analysis of the approach. We discuss the difficulties with model selection and give an innovative technique for selecting multiple model parameters. Finally, we provide some data experiments. |
| Tasks | Model Selection |
| Published | 2016-06-30 |
| URL | http://arxiv.org/abs/1606.09577v1 |
| http://arxiv.org/pdf/1606.09577v1.pdf | |
| PWC | https://paperswithcode.com/paper/ordering-as-privileged-information |
| Repo | |
| Framework | |
Lower Bounds on Active Learning for Graphical Model Selection
| Title | Lower Bounds on Active Learning for Graphical Model Selection |
| Authors | Jonathan Scarlett, Volkan Cevher |
| Abstract | We consider the problem of estimating the underlying graph associated with a Markov random field, with the added twist that the decoding algorithm can iteratively choose which subsets of nodes to sample based on the previous samples, resulting in an active learning setting. Considering both Ising and Gaussian models, we provide algorithm-independent lower bounds for high-probability recovery within the class of degree-bounded graphs. Our main results are minimax lower bounds for the active setting that match the best known lower bounds for the passive setting, which in turn are known to be tight in several cases of interest. Our analysis is based on Fano’s inequality, along with novel mutual information bounds for the active learning setting, and the application of restricted graph ensembles. While we consider ensembles that are similar or identical to those used in the passive setting, we require different analysis techniques, with a key challenge being bounding a mutual information quantity associated with observed subsets of nodes, as opposed to full observations. |
| Tasks | Active Learning, Model Selection |
| Published | 2016-07-08 |
| URL | http://arxiv.org/abs/1607.02413v2 |
| http://arxiv.org/pdf/1607.02413v2.pdf | |
| PWC | https://paperswithcode.com/paper/lower-bounds-on-active-learning-for-graphical |
| Repo | |
| Framework | |
Turing learning: a metric-free approach to inferring behavior and its application to swarms
| Title | Turing learning: a metric-free approach to inferring behavior and its application to swarms |
| Authors | Wei Li, Melvin Gauci, Roderich Gross |
| Abstract | We propose Turing Learning, a novel system identification method for inferring the behavior of natural or artificial systems. Turing Learning simultaneously optimizes two populations of computer programs, one representing models of the behavior of the system under investigation, and the other representing classifiers. By observing the behavior of the system as well as the behaviors produced by the models, two sets of data samples are obtained. The classifiers are rewarded for discriminating between these two sets, that is, for correctly categorizing data samples as either genuine or counterfeit. Conversely, the models are rewarded for ‘tricking’ the classifiers into categorizing their data samples as genuine. Unlike other methods for system identification, Turing Learning does not require predefined metrics to quantify the difference between the system and its models. We present two case studies with swarms of simulated robots and prove that the underlying behaviors cannot be inferred by a metric-based system identification method. By contrast, Turing Learning infers the behaviors with high accuracy. It also produces a useful by-product - the classifiers - that can be used to detect abnormal behavior in the swarm. Moreover, we show that Turing Learning also successfully infers the behavior of physical robot swarms. The results show that collective behaviors can be directly inferred from motion trajectories of individuals in the swarm, which may have significant implications for the study of animal collectives. Furthermore, Turing Learning could prove useful whenever a behavior is not easily characterizable using metrics, making it suitable for a wide range of applications. |
| Tasks | |
| Published | 2016-03-15 |
| URL | http://arxiv.org/abs/1603.04904v2 |
| http://arxiv.org/pdf/1603.04904v2.pdf | |
| PWC | https://paperswithcode.com/paper/turing-learning-a-metric-free-approach-to |
| Repo | |
| Framework | |
Neural Machine Translation with External Phrase Memory
| Title | Neural Machine Translation with External Phrase Memory |
| Authors | Yaohua Tang, Fandong Meng, Zhengdong Lu, Hang Li, Philip L. H. Yu |
| Abstract | In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator. |
| Tasks | Machine Translation |
| Published | 2016-06-06 |
| URL | http://arxiv.org/abs/1606.01792v1 |
| http://arxiv.org/pdf/1606.01792v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-with-external |
| Repo | |
| Framework | |
