Paper Group ANR 332
Exploiting Cyclic Symmetry in Convolutional Neural Networks. Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence. Optimizing positional scoring rules for rank aggregation. Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN). Challenges of Feature Selection for Big Data Analytics. Exa …
Exploiting Cyclic Symmetry in Convolutional Neural Networks
| Title | Exploiting Cyclic Symmetry in Convolutional Neural Networks |
| Authors | Sander Dieleman, Jeffrey De Fauw, Koray Kavukcuoglu |
| Abstract | Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data. Encoding these properties into the network architecture, as we are already used to doing for translation equivariance by using convolutional layers, could result in a more efficient use of the parameter budget by relieving the model from learning them. We introduce four operations which can be inserted into neural network models as layers, and which can be combined to make these models partially equivariant to rotations. They also enable parameter sharing across different orientations. We evaluate the effect of these architectural modifications on three datasets which exhibit rotational symmetry and demonstrate improved performance with smaller models. |
| Tasks | Data Augmentation |
| Published | 2016-02-08 |
| URL | http://arxiv.org/abs/1602.02660v2 |
| http://arxiv.org/pdf/1602.02660v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-cyclic-symmetry-in-convolutional |
| Repo | |
| Framework | |
Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence
| Title | Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence |
| Authors | Mark O. Riedl |
| Abstract | Narrative intelligence is the ability to craft, tell, understand, and respond affectively to stories. We argue that instilling artificial intelligences with computational narrative intelligence affords a number of applications beneficial to humans. We lay out some of the machine learning challenges necessary to solve to achieve computational narrative intelligence. Finally, we argue that computational narrative is a practical step towards machine enculturation, the teaching of sociocultural values to machines. |
| Tasks | |
| Published | 2016-02-21 |
| URL | http://arxiv.org/abs/1602.06484v1 |
| http://arxiv.org/pdf/1602.06484v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-narrative-intelligence-a-human |
| Repo | |
| Framework | |
Optimizing positional scoring rules for rank aggregation
| Title | Optimizing positional scoring rules for rank aggregation |
| Authors | Ioannis Caragiannis, Xenophon Chatzigeorgiou, George A. Krimpas, Alexandros A. Voudouris |
| Abstract | Nowadays, several crowdsourcing projects exploit social choice methods for computing an aggregate ranking of alternatives given individual rankings provided by workers. Motivated by such systems, we consider a setting where each worker is asked to rank a fixed (small) number of alternatives and, then, a positional scoring rule is used to compute the aggregate ranking. Among the apparently infinite such rules, what is the best one to use? To answer this question, we assume that we have partial access to an underlying true ranking. Then, the important optimization problem to be solved is to compute the positional scoring rule whose outcome, when applied to the profile of individual rankings, is as close as possible to the part of the underlying true ranking we know. We study this fundamental problem from a theoretical viewpoint and present positive and negative complexity results and, furthermore, complement our theoretical findings with experiments on real-world and synthetic data. |
| Tasks | |
| Published | 2016-09-18 |
| URL | http://arxiv.org/abs/1609.07460v2 |
| http://arxiv.org/pdf/1609.07460v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-positional-scoring-rules-for-rank |
| Repo | |
| Framework | |
Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)
| Title | Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN) |
| Authors | Amir Ghaderi, Vassilis Athitsos |
| Abstract | Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing this problem is to create features from unlabeled data. In this paper we propose a new method for training a CNN, with no need for labeled instances. This method for unsupervised feature learning is then successfully applied to a challenging object recognition task. The proposed algorithm is relatively simple, but attains accuracy comparable to that of more sophisticated methods. The proposed method is significantly easier to train, compared to existing CNN methods, making fewer requirements on manually labeled training data. It is also shown to be resistant to overfitting. We provide results on some well-known datasets, namely STL-10, CIFAR-10, and CIFAR-100. The results show that our method provides competitive performance compared with existing alternative methods. Selective Convolutional Neural Network (S-CNN) is a simple and fast algorithm, it introduces a new way to do unsupervised feature learning, and it provides discriminative features which generalize well. |
| Tasks | Object Recognition |
| Published | 2016-06-07 |
| URL | http://arxiv.org/abs/1606.02210v1 |
| http://arxiv.org/pdf/1606.02210v1.pdf | |
| PWC | https://paperswithcode.com/paper/selective-unsupervised-feature-learning-with |
| Repo | |
| Framework | |
Challenges of Feature Selection for Big Data Analytics
| Title | Challenges of Feature Selection for Big Data Analytics |
| Authors | Jundong Li, Huan Liu |
| Abstract | We are surrounded by huge amounts of large-scale high dimensional data. It is desirable to reduce the dimensionality of data for many learning tasks due to the curse of dimensionality. Feature selection has shown its effectiveness in many applications by building simpler and more comprehensive model, improving learning performance, and preparing clean, understandable data. Recently, some unique characteristics of big data such as data velocity and data variety present challenges to the feature selection problem. In this paper, we envision these challenges of feature selection for big data analytics. In particular, we first give a brief introduction about feature selection and then detail the challenges of feature selection for structured, heterogeneous and streaming data as well as its scalability and stability issues. At last, to facilitate and promote the feature selection research, we present an open-source feature selection repository (scikit-feature), which consists of most of current popular feature selection algorithms. |
| Tasks | Feature Selection |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.01875v1 |
| http://arxiv.org/pdf/1611.01875v1.pdf | |
| PWC | https://paperswithcode.com/paper/challenges-of-feature-selection-for-big-data |
| Repo | |
| Framework | |
Exact and efficient top-K inference for multi-target prediction by querying separable linear relational models
| Title | Exact and efficient top-K inference for multi-target prediction by querying separable linear relational models |
| Authors | Michiel Stock, Krzysztof Dembczynski, Bernard De Baets, Willem Waegeman |
| Abstract | Many complex multi-target prediction problems that concern large target spaces are characterised by a need for efficient prediction strategies that avoid the computation of predictions for all targets explicitly. Examples of such problems emerge in several subfields of machine learning, such as collaborative filtering, multi-label classification, dyadic prediction and biological network inference. In this article we analyse efficient and exact algorithms for computing the top-$K$ predictions in the above problem settings, using a general class of models that we refer to as separable linear relational models. We show how to use those inference algorithms, which are modifications of well-known information retrieval methods, in a variety of machine learning settings. Furthermore, we study the possibility of scoring items incompletely, while still retaining an exact top-K retrieval. Experimental results in several application domains reveal that the so-called threshold algorithm is very scalable, performing often many orders of magnitude more efficiently than the naive approach. |
| Tasks | Information Retrieval, Multi-Label Classification |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04278v1 |
| http://arxiv.org/pdf/1606.04278v1.pdf | |
| PWC | https://paperswithcode.com/paper/exact-and-efficient-top-k-inference-for-multi |
| Repo | |
| Framework | |
Error analysis of regularized least-square regression with Fredholm kernel
| Title | Error analysis of regularized least-square regression with Fredholm kernel |
| Authors | Yanfang Tao, Peipei Yuan, Biqin Song |
| Abstract | Learning with Fredholm kernel has attracted increasing attention recently since it can effectively utilize the data information to improve the prediction performance. Despite rapid progress on theoretical and experimental evaluations, its generalization analysis has not been explored in learning theory literature. In this paper, we establish the generalization bound of least square regularized regression with Fredholm kernel, which implies that the fast learning rate O(l^{-1}) can be reached under mild capacity conditions. Simulated examples show that this Fredholm regression algorithm can achieve the satisfactory prediction performance. |
| Tasks | |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06670v1 |
| http://arxiv.org/pdf/1611.06670v1.pdf | |
| PWC | https://paperswithcode.com/paper/error-analysis-of-regularized-least-square |
| Repo | |
| Framework | |
The Robustness of Estimator Composition
| Title | The Robustness of Estimator Composition |
| Authors | Pingfan Tang, Jeff M. Phillips |
| Abstract | We formalize notions of robustness for composite estimators via the notion of a breakdown point. A composite estimator successively applies two (or more) estimators: on data decomposed into disjoint parts, it applies the first estimator on each part, then the second estimator on the outputs of the first estimator. And so on, if the composition is of more than two estimators. Informally, the breakdown point is the minimum fraction of data points which if significantly modified will also significantly modify the output of the estimator, so it is typically desirable to have a large breakdown point. Our main result shows that, under mild conditions on the individual estimators, the breakdown point of the composite estimator is the product of the breakdown points of the individual estimators. We also demonstrate several scenarios, ranging from regression to statistical testing, where this analysis is easy to apply, useful in understanding worst case robustness, and sheds powerful insights onto the associated data analysis. |
| Tasks | |
| Published | 2016-09-05 |
| URL | http://arxiv.org/abs/1609.01226v1 |
| http://arxiv.org/pdf/1609.01226v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-robustness-of-estimator-composition |
| Repo | |
| Framework | |
Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks
| Title | Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks |
| Authors | Naoya Takahashi, Tofigh Naghibi, Beat Pfister |
| Abstract | Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation estimation and acoustic modeling method which only takes the orthographic transcription to jointly estimate a set of sub-word units and a reliable dictionary. Experimental results show that the proposed method which is based on semi-supervised training of a deep neural network largely outperforms phoneme based continuous speech recognition on the TIMIT dataset. |
| Tasks | Speech Recognition |
| Published | 2016-06-15 |
| URL | http://arxiv.org/abs/1606.05007v1 |
| http://arxiv.org/pdf/1606.05007v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-pronunciation-generation-by |
| Repo | |
| Framework | |
:telephone::person::sailboat::whale::okhand:; or “Call me Ishmael” - How do you translate emoji?
| Title | :telephone::person::sailboat::whale::okhand:; or “Call me Ishmael” - How do you translate emoji? |
| Authors | Will Radford, Andrew Chisholm, Ben Hachey, Bo Han |
| Abstract | We report on an exploratory analysis of Emoji Dick, a project that leverages crowdsourcing to translate Melville’s Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word alignment and part-of-speech tagging to explore how people use emoji. Despite these simple methods, we observed differences in token and part-of-speech distributions. Experiments also suggest that semantics are preserved in the translation, and repetition is more common in emoji. |
| Tasks | Part-Of-Speech Tagging, Word Alignment |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.02027v1 |
| http://arxiv.org/pdf/1611.02027v1.pdf | |
| PWC | https://paperswithcode.com/paper/telephonepersonsailboatwhaleokhand-or-call-me-1 |
| Repo | |
| Framework | |
Failure Detection for Facial Landmark Detectors
| Title | Failure Detection for Facial Landmark Detectors |
| Authors | Andreas Steger, Radu Timofte, Luc Van Gool |
| Abstract | Most face applications depend heavily on the accuracy of the face and facial landmarks detectors employed. Prediction of attributes such as gender, age, and identity usually completely fail when the faces are badly aligned due to inaccurate facial landmark detection. Despite the impressive recent advances in face and facial landmark detection, little study is on the recovery from and detection of failures or inaccurate predictions. In this work we study two top recent facial landmark detectors and devise confidence models for their outputs. We validate our failure detection approaches on standard benchmarks (AFLW, HELEN) and correctly identify more than 40% of the failures in the outputs of the landmark detectors. Moreover, with our failure detection we can achieve a 12% error reduction on a gender estimation application at the cost of a small increase in computation. |
| Tasks | Facial Landmark Detection |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.06451v1 |
| http://arxiv.org/pdf/1608.06451v1.pdf | |
| PWC | https://paperswithcode.com/paper/failure-detection-for-facial-landmark |
| Repo | |
| Framework | |
Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier
| Title | Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier |
| Authors | Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li |
| Abstract | This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information. Specifically, depth and skeleton data are firstly augmented for deep learning and making the recognition insensitive to view variance. Secondly, depth sequences are segmented using the hand-crafted features based on skeleton joints motion histogram to exploit the local temporal information. All training se gments are clustered using an Infinite Gaussian Mixture Model (IGMM) through Bayesian estimation and labelled for training Convolutional Neural Networks (ConvNets) on the depth maps. Thus, a depth sequence can be reliably encoded into a sequence of segment labels. Finally, the sequence of labels is fed into a joint Hidden Markov Model and Support Vector Machine (HMM-SVM) classifier to explore the global temporal information for final recognition. |
| Tasks | Temporal Action Localization |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00749v1 |
| http://arxiv.org/pdf/1602.00749v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-convnets-with-hand-crafted-features |
| Repo | |
| Framework | |
Object Tracking via Dynamic Feature Selection Processes
| Title | Object Tracking via Dynamic Feature Selection Processes |
| Authors | Giorgio Roffo, Simone Melzi |
| Abstract | DFST proposes an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features. A feature selection mechanism is embedded in the Adaptive colour Names (CN) tracking system that adaptively selects the top-ranked discriminative features for tracking. DFST provides a significant gain in accuracy and precision allowing the use of a dynamic set of features that results in an increased system flexibility. DFST is based on the unsupervised method “Infinite Feature Selection” (Inf-FS), which ranks features according with their “redundancy” without using class labels. By using a fast online algorithm for learning dictionaries the size of the box is adapted during the processing. At each update, we use multiple examples around the target (at different positions and scales). DFST also improved the CN by adding micro-shift at the predicted position and bounding box adaptation. |
| Tasks | Feature Selection, Object Tracking, Visual Tracking |
| Published | 2016-09-07 |
| URL | http://arxiv.org/abs/1609.01958v1 |
| http://arxiv.org/pdf/1609.01958v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-tracking-via-dynamic-feature-selection |
| Repo | |
| Framework | |
Segmental Convolutional Neural Networks for Detection of Cardiac Abnormality With Noisy Heart Sound Recordings
| Title | Segmental Convolutional Neural Networks for Detection of Cardiac Abnormality With Noisy Heart Sound Recordings |
| Authors | Yuhao Zhang, Sandeep Ayyar, Long-Huei Chen, Ethan J. Li |
| Abstract | Heart diseases constitute a global health burden, and the problem is exacerbated by the error-prone nature of listening to and interpreting heart sounds. This motivates the development of automated classification to screen for abnormal heart sounds. Existing machine learning-based systems achieve accurate classification of heart sound recordings but rely on expert features that have not been thoroughly evaluated on noisy recordings. Here we propose a segmental convolutional neural network architecture that achieves automatic feature learning from noisy heart sound recordings. Our experiments show that our best model, trained on noisy recording segments acquired with an existing hidden semi-markov model-based approach, attains a classification accuracy of 87.5% on the 2016 PhysioNet/CinC Challenge dataset, compared to the 84.6% accuracy of the state-of-the-art statistical classifier trained and evaluated on the same dataset. Our results indicate the potential of using neural network-based methods to increase the accuracy of automated classification of heart sound recordings for improved screening of heart diseases. |
| Tasks | |
| Published | 2016-12-06 |
| URL | http://arxiv.org/abs/1612.01943v1 |
| http://arxiv.org/pdf/1612.01943v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmental-convolutional-neural-networks-for |
| Repo | |
| Framework | |
Show me the material evidence: Initial experiments on evaluating hypotheses from user-generated multimedia data
| Title | Show me the material evidence: Initial experiments on evaluating hypotheses from user-generated multimedia data |
| Authors | Bernardo Gonçalves |
| Abstract | Subjective questions such as does neymar dive', or is clinton lying’, or `is trump a fascist’, are popular queries to web search engines, as can be seen by autocompletion suggestions on Google, Yahoo and Bing. In the era of cognitive computing, beyond search, they could be handled as hypotheses issued for evaluation. Our vision is to leverage on unstructured data and metadata of the rich user-generated multimedia that is often shared as material evidence in favor or against hypotheses in social media platforms. In this paper we present two preliminary experiments along those lines and discuss challenges for a cognitive computing system that collects material evidence from user-generated multimedia towards aggregating it into some form of collective decision on the hypothesis. | |
| Tasks | |
| Published | 2016-11-11 |
| URL | http://arxiv.org/abs/1611.03652v1 |
| http://arxiv.org/pdf/1611.03652v1.pdf | |
| PWC | https://paperswithcode.com/paper/show-me-the-material-evidence-initial |
| Repo | |
| Framework | |
