Paper Group ANR 2
Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review. Voice Conversion using Convolutional Neural Networks. Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization. Computational Tradeoffs in Biological Neural Networks: Self-Stabilizing Winner-Take-All Networks. Extendin …
Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review
| Title | Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review |
| Authors | Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, Qianli Liao |
| Abstract | The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential advantage. |
| Tasks | |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00740v5 |
| http://arxiv.org/pdf/1611.00740v5.pdf | |
| PWC | https://paperswithcode.com/paper/why-and-when-can-deep-but-not-shallow |
| Repo | |
| Framework | |
Voice Conversion using Convolutional Neural Networks
| Title | Voice Conversion using Convolutional Neural Networks |
| Authors | Shariq Mobin, Joan Bruna |
| Abstract | The human auditory system is able to distinguish the vocal source of thousands of speakers, yet not much is known about what features the auditory system uses to do this. Fourier Transforms are capable of capturing the pitch and harmonic structure of the speaker but this alone proves insufficient at identifying speakers uniquely. The remaining structure, often referred to as timbre, is critical to identifying speakers but we understood little about it. In this paper we use recent advances in neural networks in order to manipulate the voice of one speaker into another by transforming not only the pitch of the speaker, but the timbre. We review generative models built with neural networks as well as architectures for creating neural networks that learn analogies. Our preliminary results converting voices from one speaker to another are encouraging. |
| Tasks | Voice Conversion |
| Published | 2016-10-27 |
| URL | http://arxiv.org/abs/1610.08927v1 |
| http://arxiv.org/pdf/1610.08927v1.pdf | |
| PWC | https://paperswithcode.com/paper/voice-conversion-using-convolutional-neural |
| Repo | |
| Framework | |
Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization
| Title | Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization |
| Authors | Georgios Evangelidis, Radu Horaud |
| Abstract | This paper addresses the problem of registering multiple point sets. Solutions to this problem are often approximated by repeatedly solving for pairwise registration, which results in an uneven treatment of the sets forming a pair: a model set and a data set. The main drawback of this strategy is that the model set may contain noise and outliers, which negatively affects the estimation of the registration parameters. In contrast, the proposed formulation treats all the point sets on an equal footing. Indeed, all the points are drawn from a central Gaussian mixture, hence the registration is cast into a clustering problem. We formally derive batch and incremental EM algorithms that robustly estimate both the GMM parameters and the rotations and translations that optimally align the sets. Moreover, the mixture’s means play the role of the registered set of points while the variances provide rich information about the contribution of each component to the alignment. We thoroughly test the proposed algorithms on simulated data and on challenging real data collected with range sensors. We compare them with several state-of-the-art algorithms, and we show their potential for surface reconstruction from depth data. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01466v2 |
| http://arxiv.org/pdf/1609.01466v2.pdf | |
| PWC | https://paperswithcode.com/paper/joint-alignment-of-multiple-point-sets-with |
| Repo | |
| Framework | |
Computational Tradeoffs in Biological Neural Networks: Self-Stabilizing Winner-Take-All Networks
| Title | Computational Tradeoffs in Biological Neural Networks: Self-Stabilizing Winner-Take-All Networks |
| Authors | Nancy Lynch, Cameron Musco, Merav Parter |
| Abstract | We initiate a line of investigation into biological neural networks from an algorithmic perspective. We develop a simplified but biologically plausible model for distributed computation in stochastic spiking neural networks and study tradeoffs between computation time and network complexity in this model. Our aim is to abstract real neural networks in a way that, while not capturing all interesting features, preserves high-level behavior and allows us to make biologically relevant conclusions. In this paper, we focus on the important winner-take-all' (WTA) problem, which is analogous to a neural leader election unit: a network consisting of $n$ input neurons and $n$ corresponding output neurons must converge to a state in which a single output corresponding to a firing input (the winner’) fires, while all other outputs remain silent. Neural circuits for WTA rely on inhibitory neurons, which suppress the activity of competing outputs and drive the network towards a converged state with a single firing winner. We attempt to understand how the number of inhibitors used affects network convergence time. We show that it is possible to significantly outperform naive WTA constructions through a more refined use of inhibition, solving the problem in $O(\theta)$ rounds in expectation with just $O(\log^{1/\theta} n)$ inhibitors for any $\theta$. An alternative construction gives convergence in $O(\log^{1/\theta} n)$ rounds with $O(\theta)$ inhibitors. We compliment these upper bounds with our main technical contribution, a nearly matching lower bound for networks using $\ge \log\log n$ inhibitors. Our lower bound uses familiar indistinguishability and locality arguments from distributed computing theory. It lets us derive a number of interesting conclusions about the structure of any network solving WTA with good probability, and the use of randomness and inhibition within such a network. |
| Tasks | |
| Published | 2016-10-06 |
| URL | http://arxiv.org/abs/1610.02084v1 |
| http://arxiv.org/pdf/1610.02084v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-tradeoffs-in-biological-neural |
| Repo | |
| Framework | |
Extending Consequence-Based Reasoning to SRIQ
| Title | Extending Consequence-Based Reasoning to SRIQ |
| Authors | Andrew Bate, Boris Motik, Bernardo Cuenca Grau, František Simančík, Ian Horrocks |
| Abstract | Consequence-based calculi are a family of reasoning algorithms for description logics (DLs), and they combine hypertableau and resolution in a way that often achieves excellent performance in practice. Up to now, however, they were proposed for either Horn DLs (which do not support disjunction), or for DLs without counting quantifiers. In this paper we present a novel consequence-based calculus for SRIQ—a rich DL that supports both features. This extension is non-trivial since the intermediate consequences that need to be derived during reasoning cannot be captured using DLs themselves. The results of our preliminary performance evaluation suggest the feasibility of our approach in practice. |
| Tasks | |
| Published | 2016-02-14 |
| URL | http://arxiv.org/abs/1602.04498v3 |
| http://arxiv.org/pdf/1602.04498v3.pdf | |
| PWC | https://paperswithcode.com/paper/extending-consequence-based-reasoning-to-sriq |
| Repo | |
| Framework | |
Randomized Primal-Dual Proximal Block Coordinate Updates
| Title | Randomized Primal-Dual Proximal Block Coordinate Updates |
| Authors | Xiang Gao, Yangyang Xu, Shuzhong Zhang |
| Abstract | In this paper we propose a randomized primal-dual proximal block coordinate updating framework for a general multi-block convex optimization model with coupled objective function and linear constraints. Assuming mere convexity, we establish its $O(1/t)$ convergence rate in terms of the objective value and feasibility measure. The framework includes several existing algorithms as special cases such as a primal-dual method for bilinear saddle-point problems (PD-S), the proximal Jacobian ADMM (Prox-JADMM) and a randomized variant of the ADMM method for multi-block convex optimization. Our analysis recovers and/or strengthens the convergence properties of several existing algorithms. For example, for PD-S our result leads to the same order of convergence rate without the previously assumed boundedness condition on the constraint sets, and for Prox-JADMM the new result provides convergence rate in terms of the objective value and the feasibility violation. It is well known that the original ADMM may fail to converge when the number of blocks exceeds two. Our result shows that if an appropriate randomization procedure is invoked to select the updating blocks, then a sublinear rate of convergence in expectation can be guaranteed for multi-block ADMM, without assuming any strong convexity. The new approach is also extended to solve problems where only a stochastic approximation of the (sub-)gradient of the objective is available, and we establish an $O(1/\sqrt{t})$ convergence rate of the extended approach for solving stochastic programming. |
| Tasks | |
| Published | 2016-05-19 |
| URL | http://arxiv.org/abs/1605.05969v3 |
| http://arxiv.org/pdf/1605.05969v3.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-primal-dual-proximal-block |
| Repo | |
| Framework | |
Instance Influence Estimation for Hyperspectral Target Signature Characterization using Extended Functions of Multiple Instances
| Title | Instance Influence Estimation for Hyperspectral Target Signature Characterization using Extended Functions of Multiple Instances |
| Authors | Sheng Zou, Alina Zare |
| Abstract | The Extended Functions of Multiple Instances (eFUMI) algorithm is a generalization of Multiple Instance Learning (MIL). In eFUMI, only bag level (i.e. set level) labels are needed to estimate target signatures from mixed data. The training bags in eFUMI are labeled positive if any data point in a bag contains or represents any proportion of the target signature and are labeled as a negative bag if all data points in the bag do not represent any target. From these imprecise labels, eFUMI has been shown to be effective at estimating target signatures in hyperspectral subpixel target detection problems. One motivating scenario for the use of eFUMI is where an analyst circles objects/regions of interest in a hyperspectral scene such that the target signatures of these objects can be estimated and be used to determine whether other instances of the object appear elsewhere in the image collection. The regions highlighted by the analyst serve as the imprecise labels for eFUMI. Often, an analyst may want to iteratively refine their imprecise labels. In this paper, we present an approach for estimating the influence on the estimated target signature if the label for a particular input data point is modified. This “instance influence estimation” guides an analyst to focus on (re-)labeling the data points that provide the largest change in the resulting estimated target signature and, thus, reduce the amount of time an analyst needs to spend refining the labels for a hyperspectral scene. Results are shown on real hyperspectral sub-pixel target detection data sets. |
| Tasks | Multiple Instance Learning |
| Published | 2016-03-21 |
| URL | http://arxiv.org/abs/1603.06496v1 |
| http://arxiv.org/pdf/1603.06496v1.pdf | |
| PWC | https://paperswithcode.com/paper/instance-influence-estimation-for |
| Repo | |
| Framework | |
Theory of the GMM Kernel
| Title | Theory of the GMM Kernel |
| Authors | Ping Li, Cun-Hui Zhang |
| Abstract | We develop some theoretical results for a robust similarity measure named “generalized min-max” (GMM). This similarity has direct applications in machine learning as a positive definite kernel and can be efficiently computed via probabilistic hashing. Owing to the discrete nature, the hashed values can also be used for efficient near neighbor search. We prove the theoretical limit of GMM and the consistency result, assuming that the data follow an elliptical distribution, which is a very general family of distributions and includes the multivariate $t$-distribution as a special case. The consistency result holds as long as the data have bounded first moment (an assumption which essentially holds for datasets commonly encountered in practice). Furthermore, we establish the asymptotic normality of GMM. Compared to the “cosine” similarity which is routinely adopted in current practice in statistics and machine learning, the consistency of GMM requires much weaker conditions. Interestingly, when the data follow the $t$-distribution with $\nu$ degrees of freedom, GMM typically provides a better measure of similarity than “cosine” roughly when $\nu<8$ (which is already very close to normal). These theoretical results will help explain the recent success of GMM in learning tasks. |
| Tasks | |
| Published | 2016-08-01 |
| URL | http://arxiv.org/abs/1608.00550v1 |
| http://arxiv.org/pdf/1608.00550v1.pdf | |
| PWC | https://paperswithcode.com/paper/theory-of-the-gmm-kernel |
| Repo | |
| Framework | |
Proximal groupoid patterns In digital images
| Title | Proximal groupoid patterns In digital images |
| Authors | Enoch A-iyeh, James F. Peters |
| Abstract | The focus of this article is on the detection and classification of patterns based on groupoids. The approach hinges on descriptive proximity of points in a set based on the neighborliness property. This approach lends support to image analysis and understanding and in studying nearness of image segments. A practical application of the approach is in terms of the analysis of natural images for pattern identification and classification. |
| Tasks | |
| Published | 2016-03-06 |
| URL | http://arxiv.org/abs/1603.01842v1 |
| http://arxiv.org/pdf/1603.01842v1.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-groupoid-patterns-in-digital-images |
| Repo | |
| Framework | |
Two decades of local binary patterns: A survey
| Title | Two decades of local binary patterns: A survey |
| Authors | Matti Pietikäinen, Guoying Zhao |
| Abstract | Texture is an important characteristic for many types of images. In recent years very discriminative and computationally efficient local texture descriptors based on local binary patterns (LBP) have been developed, which has led to significant progress in applying texture methods to different problems and applications. Due to this progress, the division between texture descriptors and more generic image or video descriptors has been disappearing. A large number of different variants of LBP have been developed to improve its robustness, and to increase its discriminative power and applicability to different types of problems. In this chapter, the most recent and important variants of LBP in 2D, spatiotemporal, 3D, and 4D domains are surveyed. Interesting new developments of LBP in 1D signal analysis are also considered. Finally, some future challenges for research are presented. |
| Tasks | |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06795v2 |
| http://arxiv.org/pdf/1612.06795v2.pdf | |
| PWC | https://paperswithcode.com/paper/two-decades-of-local-binary-patterns-a-survey |
| Repo | |
| Framework | |
Pano2CAD: Room Layout From A Single Panorama Image
| Title | Pano2CAD: Room Layout From A Single Panorama Image |
| Authors | Jiu Xu, Bjorn Stenger, Tommi Kerola, Tony Tung |
| Abstract | This paper presents a method of estimating the geometry of a room and the 3D pose of objects from a single 360-degree panorama image. Assuming Manhattan World geometry, we formulate the task as a Bayesian inference problem in which we estimate positions and orientations of walls and objects. The method combines surface normal estimation, 2D object detection and 3D object pose estimation. Quantitative results are presented on a dataset of synthetically generated 3D rooms containing objects, as well as on a subset of hand-labeled images from the public SUN360 dataset. |
| Tasks | Bayesian Inference, Object Detection, Pose Estimation |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09270v2 |
| http://arxiv.org/pdf/1609.09270v2.pdf | |
| PWC | https://paperswithcode.com/paper/pano2cad-room-layout-from-a-single-panorama |
| Repo | |
| Framework | |
On Coreferring Text-extracted Event Descriptions with the aid of Ontological Reasoning
| Title | On Coreferring Text-extracted Event Descriptions with the aid of Ontological Reasoning |
| Authors | Stefano Borgo, Loris Bozzato, Alessio Palmero Aprosio, Marco Rospocher, Luciano Serafini |
| Abstract | Systems for automatic extraction of semantic information about events from large textual resources are now available: these tools are capable to generate RDF datasets about text extracted events and this knowledge can be used to reason over the recognized events. On the other hand, text based tasks for event recognition, as for example event coreference (i.e. recognizing whether two textual descriptions refer to the same event), do not take into account ontological information of the extracted events in their process. In this paper, we propose a method to derive event coreference on text extracted event data using semantic based rule reasoning. We demonstrate our method considering a limited (yet representative) set of event types: we introduce a formal analysis on their ontological properties and, on the base of this, we define a set of coreference criteria. We then implement these criteria as RDF-based reasoning rules to be applied on text extracted event data. We evaluate the effectiveness of our approach over a standard coreference benchmark dataset. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00227v1 |
| http://arxiv.org/pdf/1612.00227v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-coreferring-text-extracted-event |
| Repo | |
| Framework | |
Approximation and inference methods for stochastic biochemical kinetics - a tutorial review
| Title | Approximation and inference methods for stochastic biochemical kinetics - a tutorial review |
| Authors | David Schnoerr, Guido Sanguinetti, Ramon Grima |
| Abstract | Stochastic fluctuations of molecule numbers are ubiquitous in biological systems. Important examples include gene expression and enzymatic processes in living cells. Such systems are typically modelled as chemical reaction networks whose dynamics are governed by the Chemical Master Equation. Despite its simple structure, no analytic solutions to the Chemical Master Equation are known for most systems. Moreover, stochastic simulations are computationally expensive, making systematic analysis and statistical inference a challenging task. Consequently, significant effort has been spent in recent decades on the development of efficient approximation and inference methods. This article gives an introduction to basic modelling concepts as well as an overview of state of the art methods. First, we motivate and introduce deterministic and stochastic methods for modelling chemical networks, and give an overview of simulation and exact solution methods. Next, we discuss several approximation methods, including the chemical Langevin equation, the system size expansion, moment closure approximations, time-scale separation approximations and hybrid methods. We discuss their various properties and review recent advances and remaining challenges for these methods. We present a comparison of several of these methods by means of a numerical case study and highlight some of their respective advantages and disadvantages. Finally, we discuss the problem of inference from experimental data in the Bayesian framework and review recent methods developed the literature. In summary, this review gives a self-contained introduction to modelling, approximations and inference methods for stochastic chemical kinetics. |
| Tasks | |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.06582v2 |
| http://arxiv.org/pdf/1608.06582v2.pdf | |
| PWC | https://paperswithcode.com/paper/approximation-and-inference-methods-for |
| Repo | |
| Framework | |
Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest
| Title | Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest |
| Authors | Korsuk Sirinukunwattana, Josien P. W. Pluim, Hao Chen, Xiaojuan Qi, Pheng-Ann Heng, Yun Bo Guo, Li Yang Wang, Bogdan J. Matuszewski, Elia Bruni, Urko Sanchez, Anton Böhm, Olaf Ronneberger, Bassem Ben Cheikh, Daniel Racoceanu, Philipp Kainz, Michael Pfeiffer, Martin Urschler, David R. J. Snead, Nasir M. Rajpoot |
| Abstract | Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer. In clinical practice, the morphology of intestinal glands, including architectural appearance and glandular formation, is used by pathologists to inform prognosis and plan the treatment of individual patients. However, achieving good inter-observer as well as intra-observer reproducibility of cancer grading is still a major challenge in modern pathology. An automated approach which quantifies the morphology of glands is a solution to the problem. This paper provides an overview to the Gland Segmentation in Colon Histology Images Challenge Contest (GlaS) held at MICCAI’2015. Details of the challenge, including organization, dataset and evaluation criteria, are presented, along with the method descriptions and evaluation results from the top performing methods. |
| Tasks | |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00275v2 |
| http://arxiv.org/pdf/1603.00275v2.pdf | |
| PWC | https://paperswithcode.com/paper/gland-segmentation-in-colon-histology-images |
| Repo | |
| Framework | |
Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain
| Title | Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain |
| Authors | Jiahao Pang, Gene Cheung |
| Abstract | Inverse imaging problems are inherently under-determined, and hence it is important to employ appropriate image priors for regularization. One recent popular prior—the graph Laplacian regularizer—assumes that the target pixel patch is smooth with respect to an appropriately chosen graph. However, the mechanisms and implications of imposing the graph Laplacian regularizer on the original inverse problem are not well understood. To address this problem, in this paper we interpret neighborhood graphs of pixel patches as discrete counterparts of Riemannian manifolds and perform analysis in the continuous domain, providing insights into several fundamental aspects of graph Laplacian regularization for image denoising. Specifically, we first show the convergence of the graph Laplacian regularizer to a continuous-domain functional, integrating a norm measured in a locally adaptive metric space. Focusing on image denoising, we derive an optimal metric space assuming non-local self-similarity of pixel patches, leading to an optimal graph Laplacian regularizer for denoising in the discrete domain. We then interpret graph Laplacian regularization as an anisotropic diffusion scheme to explain its behavior during iterations, e.g., its tendency to promote piecewise smooth signals under certain settings. To verify our analysis, an iterative image denoising algorithm is developed. Experimental results show that our algorithm performs competitively with state-of-the-art denoising methods such as BM3D for natural images, and outperforms them significantly for piecewise smooth images. |
| Tasks | Denoising, Image Denoising |
| Published | 2016-04-27 |
| URL | http://arxiv.org/abs/1604.07948v2 |
| http://arxiv.org/pdf/1604.07948v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-laplacian-regularization-for-image |
| Repo | |
| Framework | |
