Paper Group ANR 13
Decentralized Clustering and Linking by Networked Agents. A Locally Adaptive Normal Distribution. On the prediction loss of the lasso in the partially labeled setting. Determining Health Utilities through Data Mining of Social Media. On the exact learnability of graph parameters: The case of partition functions. A Binary Convolutional Encoder-decod …
Decentralized Clustering and Linking by Networked Agents
| Title | Decentralized Clustering and Linking by Networked Agents |
| Authors | Sahar Khawatmi, Ali H. Sayed, Abdelhak M. Zoubir |
| Abstract | We consider the problem of decentralized clustering and estimation over multi-task networks, where agents infer and track different models of interest. The agents do not know beforehand which model is generating their own data. They also do not know which agents in their neighborhood belong to the same cluster. We propose a decentralized clustering algorithm aimed at identifying and forming clusters of agents of similar objectives, and at guiding cooperation to enhance the inference performance. One key feature of the proposed technique is the integration of the learning and clustering tasks into a single strategy. We analyze the performance of the procedure and show that the error probabilities of types I and II decay exponentially to zero with the step-size parameter. While links between agents following different objectives are ignored in the clustering process, we nevertheless show how to exploit these links to relay critical information across the network for enhanced performance. Simulation results illustrate the performance of the proposed method in comparison to other useful techniques. |
| Tasks | |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09112v1 |
| http://arxiv.org/pdf/1610.09112v1.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-clustering-and-linking-by |
| Repo | |
| Framework | |
A Locally Adaptive Normal Distribution
| Title | A Locally Adaptive Normal Distribution |
| Authors | Georgios Arvanitidis, Lars Kai Hansen, Søren Hauberg |
| Abstract | The multivariate normal density is a monotonic function of the distance to the mean, and its ellipsoidal shape is due to the underlying Euclidean metric. We suggest to replace this metric with a locally adaptive, smoothly changing (Riemannian) metric that favors regions of high local density. The resulting locally adaptive normal distribution (LAND) is a generalization of the normal distribution to the “manifold” setting, where data is assumed to lie near a potentially low-dimensional manifold embedded in $\mathbb{R}^D$. The LAND is parametric, depending only on a mean and a covariance, and is the maximum entropy distribution under the given metric. The underlying metric is, however, non-parametric. We develop a maximum likelihood algorithm to infer the distribution parameters that relies on a combination of gradient descent and Monte Carlo integration. We further extend the LAND to mixture models, and provide the corresponding EM algorithm. We demonstrate the efficiency of the LAND to fit non-trivial probability distributions over both synthetic data, and EEG measurements of human sleep. |
| Tasks | EEG |
| Published | 2016-06-08 |
| URL | http://arxiv.org/abs/1606.02518v3 |
| http://arxiv.org/pdf/1606.02518v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-locally-adaptive-normal-distribution |
| Repo | |
| Framework | |
On the prediction loss of the lasso in the partially labeled setting
| Title | On the prediction loss of the lasso in the partially labeled setting |
| Authors | Pierre C. Bellec, Arnak S. Dalalyan, Edwin Grappin, Quentin Paris |
| Abstract | In this paper we revisit the risk bounds of the lasso estimator in the context of transductive and semi-supervised learning. In other terms, the setting under consideration is that of regression with random design under partial labeling. The main goal is to obtain user-friendly bounds on the off-sample prediction risk. To this end, the simple setting of bounded response variable and bounded (high-dimensional) covariates is considered. We propose some new adaptations of the lasso to these settings and establish oracle inequalities both in expectation and in deviation. These results provide non-asymptotic upper bounds on the risk that highlight the interplay between the bias due to the mis-specification of the linear model, the bias due to the approximate sparsity and the variance. They also demonstrate that the presence of a large number of unlabeled features may have significant positive impact in the situations where the restricted eigenvalue of the design matrix vanishes or is very small. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06179v2 |
| http://arxiv.org/pdf/1606.06179v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-prediction-loss-of-the-lasso-in-the |
| Repo | |
| Framework | |
Determining Health Utilities through Data Mining of Social Media
| Title | Determining Health Utilities through Data Mining of Social Media |
| Authors | Christopher Thompson, Josh Introne, Clint Young |
| Abstract | ‘Health utilities’ measure patient preferences for perfect health compared to specific unhealthy states, such as asthma, a fractured hip, or colon cancer. When integrated over time, these estimations are called quality adjusted life years (QALYs). Until now, characterizing health utilities (HUs) required detailed patient interviews or written surveys. While reliable and specific, this data remained costly due to efforts to locate, enlist and coordinate participants. Thus the scope, context and temporality of diseases examined has remained limited. Now that more than a billion people use social media, we propose a novel strategy: use natural language processing to analyze public online conversations for signals of the severity of medical conditions and correlate these to known HUs using machine learning. In this work, we filter a dataset that originally contained 2 billion tweets for relevant content on 60 diseases. Using this data, our algorithm successfully distinguished mild from severe diseases, which had previously been categorized only by traditional techniques. This represents progress towards two related applications: first, predicting HUs where such information is nonexistent; and second, (where rich HU data already exists) estimating temporal or geographic patterns of disease severity through data mining. |
| Tasks | |
| Published | 2016-08-13 |
| URL | http://arxiv.org/abs/1608.03938v1 |
| http://arxiv.org/pdf/1608.03938v1.pdf | |
| PWC | https://paperswithcode.com/paper/determining-health-utilities-through-data |
| Repo | |
| Framework | |
On the exact learnability of graph parameters: The case of partition functions
| Title | On the exact learnability of graph parameters: The case of partition functions |
| Authors | Nadia Labai, Johann A. Makowsky |
| Abstract | We study the exact learnability of real valued graph parameters $f$ which are known to be representable as partition functions which count the number of weighted homomorphisms into a graph $H$ with vertex weights $\alpha$ and edge weights $\beta$. M. Freedman, L. Lov'asz and A. Schrijver have given a characterization of these graph parameters in terms of the $k$-connection matrices $C(f,k)$ of $f$. Our model of learnability is based on D. Angluin’s model of exact learning using membership and equivalence queries. Given such a graph parameter $f$, the learner can ask for the values of $f$ for graphs of their choice, and they can formulate hypotheses in terms of the connection matrices $C(f,k)$ of $f$. The teacher can accept the hypothesis as correct, or provide a counterexample consisting of a graph. Our main result shows that in this scenario, a very large class of partition functions, the rigid partition functions, can be learned in time polynomial in the size of $H$ and the size of the largest counterexample in the Blum-Shub-Smale model of computation over the reals with unit cost. |
| Tasks | |
| Published | 2016-06-13 |
| URL | http://arxiv.org/abs/1606.04056v1 |
| http://arxiv.org/pdf/1606.04056v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-exact-learnability-of-graph-parameters |
| Repo | |
| Framework | |
A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
| Title | A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing |
| Authors | Zichuan Liu, Yixing Li, Fengbo Ren, Hao Yu |
| Abstract | In this paper, we develop a binary convolutional encoder-decoder network (B-CEDNet) for natural scene text processing (NSTP). It converts a text image to a class-distinguished salience map that reveals the categorical, spatial and morphological information of characters. The existing solutions are either memory consuming or run-time consuming that cannot be applied to real-time applications on resource-constrained devices such as advanced driver assistance systems. The developed network can process multiple regions containing characters by one-off forward operation, and is trained to have binary weights and binary feature maps, which lead to both remarkable inference run-time speedup and memory usage reduction. By training with over 200, 000 synthesis scene text images (size of $32\times128$), it can achieve $90%$ and $91%$ pixel-wise accuracy on ICDAR-03 and ICDAR-13 datasets. It only consumes $4.59\ ms$ inference run-time realized on GPU with a small network size of 2.14 MB, which is up to $8\times$ faster and $96%$ smaller than it full-precision version. |
| Tasks | |
| Published | 2016-12-12 |
| URL | http://arxiv.org/abs/1612.03630v1 |
| http://arxiv.org/pdf/1612.03630v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-binary-convolutional-encoder-decoder |
| Repo | |
| Framework | |
Variational Autoencoders for Semi-supervised Text Classification
| Title | Variational Autoencoders for Semi-supervised Text Classification |
| Authors | Weidi Xu, Haoze Sun, Chao Deng, Ying Tan |
| Abstract | Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the decoder’s capability to distinguish between different categorical labels is essential. Therefore, Semi-supervised Sequential Variational Autoencoder (SSVAE) is proposed, which increases the capability by feeding label into its decoder RNN at each time-step. Two specific decoder structures are investigated and both of them are verified to be effective. Besides, in order to reduce the computational complexity in training, a novel optimization method is proposed, which estimates the gradient of the unlabeled objective function by sampling, along with two variance reduction techniques. Experimental results on Large Movie Review Dataset (IMDB) and AG’s News corpus show that the proposed approach significantly improves the classification accuracy compared with pure-supervised classifiers, and achieves competitive performance against previous advanced methods. State-of-the-art results can be obtained by integrating other pretraining-based methods. |
| Tasks | Image Classification, Text Classification |
| Published | 2016-03-08 |
| URL | http://arxiv.org/abs/1603.02514v3 |
| http://arxiv.org/pdf/1603.02514v3.pdf | |
| PWC | https://paperswithcode.com/paper/variational-autoencoders-for-semi-supervised |
| Repo | |
| Framework | |
Multi-Organ Cancer Classification and Survival Analysis
| Title | Multi-Organ Cancer Classification and Survival Analysis |
| Authors | Stefan Bauer, Nicolas Carion, Peter Schüffler, Thomas Fuchs, Peter Wild, Joachim M. Buhmann |
| Abstract | Accurate and robust cell nuclei classification is the cornerstone for a wider range of tasks in digital and Computational Pathology. However, most machine learning systems require extensive labeling from expert pathologists for each individual problem at hand, with no or limited abilities for knowledge transfer between datasets and organ sites. In this paper we implement and evaluate a variety of deep neural network models and model ensembles for nuclei classification in renal cell cancer (RCC) and prostate cancer (PCa). We propose a convolutional neural network system based on residual learning which significantly improves over the state-of-the-art in cell nuclei classification. Finally, we show that the combination of tissue types during training increases not only classification accuracy but also overall survival analysis. |
| Tasks | Nuclei Classification, Survival Analysis, Transfer Learning |
| Published | 2016-06-02 |
| URL | http://arxiv.org/abs/1606.00897v2 |
| http://arxiv.org/pdf/1606.00897v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-organ-cancer-classification-and |
| Repo | |
| Framework | |
Automatic Image Annotation via Label Transfer in the Semantic Space
| Title | Automatic Image Annotation via Label Transfer in the Semantic Space |
| Authors | Tiberio Uricchio, Lamberto Ballan, Lorenzo Seidenari, Alberto Del Bimbo |
| Abstract | Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images. |
| Tasks | Denoising |
| Published | 2016-05-16 |
| URL | http://arxiv.org/abs/1605.04770v3 |
| http://arxiv.org/pdf/1605.04770v3.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-image-annotation-via-label-transfer |
| Repo | |
| Framework | |
Ear-to-ear Capture of Facial Intrinsics
| Title | Ear-to-ear Capture of Facial Intrinsics |
| Authors | Alassane Seck, William A. P. Smith, Arnaud Dessein, Bernard Tiddeman, Hannah Dee, Abhishek Dutta |
| Abstract | We present a practical approach to capturing ear-to-ear face models comprising both 3D meshes and intrinsic textures (i.e. diffuse and specular albedo). Our approach is a hybrid of geometric and photometric methods and requires no geometric calibration. Photometric measurements made in a lightstage are used to estimate view dependent high resolution normal maps. We overcome the problem of having a single photometric viewpoint by capturing in multiple poses. We use uncalibrated multiview stereo to estimate a coarse base mesh to which the photometric views are registered. We propose a novel approach to robustly stitching surface normal and intrinsic texture data into a seamless, complete and highly detailed face model. The resulting relightable models provide photorealistic renderings in any view. |
| Tasks | Calibration |
| Published | 2016-09-08 |
| URL | http://arxiv.org/abs/1609.02368v1 |
| http://arxiv.org/pdf/1609.02368v1.pdf | |
| PWC | https://paperswithcode.com/paper/ear-to-ear-capture-of-facial-intrinsics |
| Repo | |
| Framework | |
Ensembles of Generative Adversarial Networks
| Title | Ensembles of Generative Adversarial Networks |
| Authors | Yaxing Wang, Lichao Zhang, Joost van de Weijer |
| Abstract | Ensembles are a popular way to improve results of discriminative CNNs. The combination of several networks trained starting from different initializations improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways to construct ensembles. The first one is based on the fact that in the minimax game which is played to optimize the GAN objective the generator network keeps on changing even after the network can be considered optimal. As such ensembles of GANs can be constructed based on the same network initialization but just taking models which have different amount of iterations. These so-called self ensembles are much faster to train than traditional ensembles. The second method, called cascade GANs, redirects part of the training data which is badly modeled by the first GAN to another GAN. In experiments on the CIFAR10 dataset we show that ensembles of GANs obtain model probability distributions which better model the data distribution. In addition, we show that these improved results can be obtained at little additional computational cost. |
| Tasks | |
| Published | 2016-12-03 |
| URL | http://arxiv.org/abs/1612.00991v1 |
| http://arxiv.org/pdf/1612.00991v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensembles-of-generative-adversarial-networks |
| Repo | |
| Framework | |
Research on the Multiple Feature Fusion Image Retrieval Algorithm based on Texture Feature and Rough Set Theory
| Title | Research on the Multiple Feature Fusion Image Retrieval Algorithm based on Texture Feature and Rough Set Theory |
| Authors | Xiaojie Shi, Yijun Shao |
| Abstract | Recently, we have witnessed the explosive growth of images with complex information and content. In order to effectively and precisely retrieve desired images from a large-scale image database with low time-consuming, we propose the multiple feature fusion image retrieval algorithm based on the texture feature and rough set theory in this paper. In contrast to the conventional approaches that only use the single feature or standard, we fuse the different features with operation of normalization. The rough set theory will assist us to enhance the robustness of retrieval system when facing with incomplete data warehouse. To enhance the texture extraction paradigm, we use the wavelet Gabor function that holds better robustness. In addition, from the perspectives of the internal and external normalization, we re-organize extracted feature with the better combination. The numerical experiment has verified general feasibility of our methodology. We enhance the overall accuracy compared with the other state-of-the-art algorithms. |
| Tasks | Image Retrieval |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02493v1 |
| http://arxiv.org/pdf/1612.02493v1.pdf | |
| PWC | https://paperswithcode.com/paper/research-on-the-multiple-feature-fusion-image |
| Repo | |
| Framework | |
A Model of Pathways to Artificial Superintelligence Catastrophe for Risk and Decision Analysis
| Title | A Model of Pathways to Artificial Superintelligence Catastrophe for Risk and Decision Analysis |
| Authors | Anthony M. Barrett, Seth D. Baum |
| Abstract | An artificial superintelligence (ASI) is artificial intelligence that is significantly more intelligent than humans in all respects. While ASI does not currently exist, some scholars propose that it could be created sometime in the future, and furthermore that its creation could cause a severe global catastrophe, possibly even resulting in human extinction. Given the high stakes, it is important to analyze ASI risk and factor the risk into decisions related to ASI research and development. This paper presents a graphical model of major pathways to ASI catastrophe, focusing on ASI created via recursive self-improvement. The model uses the established risk and decision analysis modeling paradigms of fault trees and influence diagrams in order to depict combinations of events and conditions that could lead to AI catastrophe, as well as intervention options that could decrease risks. The events and conditions include select aspects of the ASI itself as well as the human process of ASI research, development, and management. Model structure is derived from published literature on ASI risk. The model offers a foundation for rigorous quantitative evaluation and decision making on the long-term risk of ASI catastrophe. |
| Tasks | Decision Making |
| Published | 2016-07-25 |
| URL | http://arxiv.org/abs/1607.07730v1 |
| http://arxiv.org/pdf/1607.07730v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-of-pathways-to-artificial |
| Repo | |
| Framework | |
Propagators and Solvers for the Algebra of Modular Systems
| Title | Propagators and Solvers for the Algebra of Modular Systems |
| Authors | Bart Bogaerts, Eugenia Ternovska, David Mitchell |
| Abstract | To appear in the proceedings of LPAR 21. Solving complex problems can involve non-trivial combinations of distinct knowledge bases and problem solvers. The Algebra of Modular Systems is a knowledge representation framework that provides a method for formally specifying such systems in purely semantic terms. Formally, an expression of the algebra defines a class of structures. Many expressive formalism used in practice solve the model expansion task, where a structure is given on the input and an expansion of this structure in the defined class of structures is searched (this practice overcomes the common undecidability problem for expressive logics). In this paper, we construct a solver for the model expansion task for a complex modular systems from an expression in the algebra and black-box propagators or solvers for the primitive modules. To this end, we define a general notion of propagators equipped with an explanation mechanism, an extension of the alge- bra to propagators, and a lazy conflict-driven learning algorithm. The result is a framework for seamlessly combining solving technology from different domains to produce a solver for a combined system. |
| Tasks | |
| Published | 2016-06-27 |
| URL | http://arxiv.org/abs/1606.08130v2 |
| http://arxiv.org/pdf/1606.08130v2.pdf | |
| PWC | https://paperswithcode.com/paper/propagators-and-solvers-for-the-algebra-of |
| Repo | |
| Framework | |
Locally-Optimized Inter-Subject Alignment of Functional Cortical Regions
| Title | Locally-Optimized Inter-Subject Alignment of Functional Cortical Regions |
| Authors | Marius Cătălin Iordan, Armand Joulin, Diane M. Beck, Li Fei-Fei |
| Abstract | Inter-subject registration of cortical areas is necessary in functional imaging (fMRI) studies for making inferences about equivalent brain function across a population. However, many high-level visual brain areas are defined as peaks of functional contrasts whose cortical position is highly variable. As such, most alignment methods fail to accurately map functional regions of interest (ROIs) across participants. To address this problem, we propose a locally optimized registration method that directly predicts the location of a seed ROI on a separate target cortical sheet by maximizing the functional correlation between their time courses, while simultaneously allowing for non-smooth local deformations in region topology. Our method outperforms the two most commonly used alternatives (anatomical landmark-based AFNI alignment and cortical convexity-based FreeSurfer alignment) in overlap between predicted region and functionally-defined LOC. Furthermore, the maps obtained using our method are more consistent across subjects than both baseline measures. Critically, our method represents an important step forward towards predicting brain regions without explicit localizer scans and deciphering the poorly understood relationship between the location of functional regions, their anatomical extent, and the consistency of computations those regions perform across people. |
| Tasks | |
| Published | 2016-06-07 |
| URL | http://arxiv.org/abs/1606.02349v1 |
| http://arxiv.org/pdf/1606.02349v1.pdf | |
| PWC | https://paperswithcode.com/paper/locally-optimized-inter-subject-alignment-of |
| Repo | |
| Framework | |
