Paper Group ANR 525
Bundle Optimization for Multi-aspect Embedding. Convolutional Neural Pyramid for Image Processing. Calculating Probabilities Simplifies Word Learning. Optimal and Learning Control for Autonomous Robots. Distributed Kernel K-Means for Large Scale Clustering. Towards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evo …
Bundle Optimization for Multi-aspect Embedding
| Title | Bundle Optimization for Multi-aspect Embedding |
| Authors | Qiong Zeng, Baoquan Chen, Yanir Kleiman, Daniel Cohen-Or, Yangyan Li |
| Abstract | Understanding semantic similarity among images is the core of a wide range of computer vision applications. An important step towards this goal is to collect and learn human perceptions. Interestingly, the semantic context of images is often ambiguous as images can be perceived with emphasis on different aspects, which may be contradictory to each other. In this paper, we present a method for learning the semantic similarity among images, inferring their latent aspects and embedding them into multi-spaces corresponding to their semantic aspects. We consider the multi-embedding problem as an optimization function that evaluates the embedded distances with respect to the qualitative clustering queries. The key idea of our approach is to collect and embed qualitative measures that share the same aspects in bundles. To ensure similarity aspect sharing among multiple measures, image classification queries are presented to, and solved by users. The collected image clusters are then converted into bundles of tuples, which are fed into our bundle optimization algorithm that jointly infers the aspect similarity and multi-aspect embedding. Extensive experimental results show that our approach significantly outperforms state-of-the-art multi-embedding approaches on various datasets, and scales well for large multi-aspect similarity measures. |
| Tasks | Image Classification, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-03-29 |
| URL | http://arxiv.org/abs/1703.09928v3 |
| http://arxiv.org/pdf/1703.09928v3.pdf | |
| PWC | https://paperswithcode.com/paper/bundle-optimization-for-multi-aspect |
| Repo | |
| Framework | |
Convolutional Neural Pyramid for Image Processing
| Title | Convolutional Neural Pyramid for Image Processing |
| Authors | Xiaoyong Shen, Ying-Cong Chen, Xin Tao, Jiaya Jia |
| Abstract | We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks. It is based on the essential finding that many applications require large receptive fields for structure understanding. But corresponding neural networks for regression either stack many layers or apply large kernels to achieve it, which is computationally very costly. Our pyramid structure can greatly enlarge the field while not sacrificing computation efficiency. Extra benefit includes adaptive network depth and progressive upsampling for quasi-realtime testing on VGA-size input. Our method profits a broad set of applications, such as depth/RGB image restoration, completion, noise/artifact removal, edge refinement, image filtering, image enhancement and colorization. |
| Tasks | Colorization, Image Enhancement, Image Restoration |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02071v1 |
| http://arxiv.org/pdf/1704.02071v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-pyramid-for-image |
| Repo | |
| Framework | |
Calculating Probabilities Simplifies Word Learning
| Title | Calculating Probabilities Simplifies Word Learning |
| Authors | Aida Nematzadeh, Barend Beekhuizen, Shanshan Huang, Suzanne Stevenson |
| Abstract | Children can use the statistical regularities of their environment to learn word meanings, a mechanism known as cross-situational learning. We take a computational approach to investigate how the information present during each observation in a cross-situational framework can affect the overall acquisition of word meanings. We do so by formulating various in-the-moment learning mechanisms that are sensitive to different statistics of the environment, such as counts and conditional probabilities. Each mechanism introduces a unique source of competition or mutual exclusivity bias to the model; the mechanism that maximally uses the model’s knowledge of word meanings performs the best. Moreover, the gap between this mechanism and others is amplified in more challenging learning scenarios, such as learning from few examples. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06672v1 |
| http://arxiv.org/pdf/1702.06672v1.pdf | |
| PWC | https://paperswithcode.com/paper/calculating-probabilities-simplifies-word |
| Repo | |
| Framework | |
Optimal and Learning Control for Autonomous Robots
| Title | Optimal and Learning Control for Autonomous Robots |
| Authors | Jonas Buchli, Farbod Farshidian, Alexander Winkler, Timothy Sandy, Markus Giftthaler |
| Abstract | Optimal and Learning Control for Autonomous Robots has been taught in the Robotics, Systems and Controls Masters at ETH Zurich with the aim to teach optimal control and reinforcement learning for closed loop control problems from a unified point of view. The starting point is the formulation of of an optimal control problem and deriving the different types of solutions and algorithms from there. These lecture notes aim at supporting this unified view with a unified notation wherever possible, and a bit of a translation help to compare the terminology and notation in the different fields. The course assumes basic knowledge of Control Theory, Linear Algebra and Stochastic Calculus. |
| Tasks | |
| Published | 2017-08-30 |
| URL | http://arxiv.org/abs/1708.09342v1 |
| http://arxiv.org/pdf/1708.09342v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-and-learning-control-for-autonomous |
| Repo | |
| Framework | |
Distributed Kernel K-Means for Large Scale Clustering
| Title | Distributed Kernel K-Means for Large Scale Clustering |
| Authors | Marco Jacopo Ferrarotti, Sergio Decherchi, Walter Rocchia |
| Abstract | Clustering samples according to an effective metric and/or vector space representation is a challenging unsupervised learning task with a wide spectrum of applications. Among several clustering algorithms, k-means and its kernelized version have still a wide audience because of their conceptual simplicity and efficacy. However, the systematic application of the kernelized version of k-means is hampered by its inherent square scaling in memory with the number of samples. In this contribution, we devise an approximate strategy to minimize the kernel k-means cost function in which the trade-off between accuracy and velocity is automatically ruled by the available system memory. Moreover, we define an ad-hoc parallelization scheme well suited for hybrid cpu-gpu state-of-the-art parallel architectures. We proved the effectiveness both of the approximation scheme and of the parallelization method on standard UCI datasets and on molecular dynamics (MD) data in the realm of computational chemistry. In this applicative domain, clustering can play a key role for both quantitively estimating kinetics rates via Markov State Models or to give qualitatively a human compatible summarization of the underlying chemical phenomenon under study. For these reasons, we selected it as a valuable real-world application scenario. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03013v1 |
| http://arxiv.org/pdf/1710.03013v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-kernel-k-means-for-large-scale |
| Repo | |
| Framework | |
Towards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evolution Approach
| Title | Towards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evolution Approach |
| Authors | Filipe Assunção, Nuno Lourenço, Penousal Machado, Bernardete Ribeiro |
| Abstract | Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs composed of more than one hidden-layer. On the other, there is no way to evolve networks with more than one output neuron. To properly evolve ANNs with more than one hidden-layer and multiple output nodes there is the need to know the number of neurons available in previous layers. In this paper we introduce Dynamic Structured Grammatical Evolution (DSGE): a new genotypic representation that overcomes the aforementioned limitations. By enabling the creation of dynamic rules that specify the connection possibilities of each neuron, the methodology enables the evolution of multi-layered ANNs with more than one output neuron. Results in different classification problems show that DSGE evolves effective single and multi-layered ANNs, with a varying number of output neurons. |
| Tasks | |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08493v1 |
| http://arxiv.org/pdf/1706.08493v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-the-evolution-of-multi-layered-neural |
| Repo | |
| Framework | |
Hybrid PS-V Technique: A Novel Sensor Fusion Approach for Fast Mobile Eye-Tracking with Sensor-Shift Aware Correction
| Title | Hybrid PS-V Technique: A Novel Sensor Fusion Approach for Fast Mobile Eye-Tracking with Sensor-Shift Aware Correction |
| Authors | Ioannis Rigas, Hayes Raffle, Oleg V. Komogortsev |
| Abstract | This paper introduces and evaluates a hybrid technique that fuses efficiently the eye-tracking principles of photosensor oculography (PSOG) and video oculography (VOG). The main concept of this novel approach is to use a few fast and power-economic photosensors as the core mechanism for performing high speed eye-tracking, whereas in parallel, use a video sensor operating at low sampling-rate (snapshot mode) to perform dead-reckoning error correction when sensor movements occur. In order to evaluate the proposed method, we simulate the functional components of the technique and present our results in experimental scenarios involving various combinations of horizontal and vertical eye and sensor movements. Our evaluation shows that the developed technique can be used to provide robustness to sensor shifts that otherwise could induce error larger than 5 deg. Our analysis suggests that the technique can potentially enable high speed eye-tracking at low power profiles, making it suitable to be used in emerging head-mounted devices, e.g. AR/VR headsets. |
| Tasks | Eye Tracking, Sensor Fusion |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05411v2 |
| http://arxiv.org/pdf/1707.05411v2.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-ps-v-technique-a-novel-sensor-fusion |
| Repo | |
| Framework | |
Deconvolution and Restoration of Optical Endomicroscopy Images
| Title | Deconvolution and Restoration of Optical Endomicroscopy Images |
| Authors | Ahmed Karam Eldaly, Yoann Altmann, Antonios Perperidis, Nikola Krstajic, Tushar Choudhary, Kevin Dhaliwal, Stephen McLaughlin |
| Abstract | Optical endomicroscopy (OEM) is an emerging technology platform with preclinical and clinical imaging applications. Pulmonary OEM via fibre bundles has the potential to provide in vivo, in situ molecular signatures of disease such as infection and inflammation. However, enhancing the quality of data acquired by this technique for better visualization and subsequent analysis remains a challenging problem. Cross coupling between fiber cores and sparse sampling by imaging fiber bundles are the main reasons for image degradation, and poor detection performance (i.e., inflammation, bacteria, etc.). In this work, we address the problem of deconvolution and restoration of OEM data. We propose a hierarchical Bayesian model to solve this problem and compare three estimation algorithms to exploit the resulting joint posterior distribution. The first method is based on Markov chain Monte Carlo (MCMC) methods, however, it exhibits a relatively long computational time. The second and third algorithms deal with this issue and are based on a variational Bayes (VB) approach and an alternating direction method of multipliers (ADMM) algorithm respectively. Results on both synthetic and real datasets illustrate the effectiveness of the proposed methods for restoration of OEM images. |
| Tasks | |
| Published | 2017-01-27 |
| URL | http://arxiv.org/abs/1701.08107v3 |
| http://arxiv.org/pdf/1701.08107v3.pdf | |
| PWC | https://paperswithcode.com/paper/deconvolution-and-restoration-of-optical |
| Repo | |
| Framework | |
Human Eye Visual Hyperacuity: A New Paradigm for Sensing?
| Title | Human Eye Visual Hyperacuity: A New Paradigm for Sensing? |
| Authors | Adur Lagunas, Oier Dominguez, Susana Martinez-Conde, Stephen L. Macknik, Carlos del-Rio |
| Abstract | The human eye appears to be using a low number of sensors for image capturing. Furthermore, regarding the physical dimensions of cones-photoreceptors responsible for the sharp central vision-, we may realize that these sensors are of a relatively small size and area. Nonetheless, the eye is capable to obtain high resolution images due to visual hyperacuity and presents an impressive sensitivity and dynamic range when set against conventional digital cameras of similar characteristics. This article is based on the hypothesis that the human eye may be benefiting from diffraction to improve both image resolution and acquisition process. The developed method intends to explain and simulate using MATLAB software the visual hyperacuity: the introduction of a controlled diffraction pattern at an initial stage, enables the use of a reduced number of sensors for capturing the image and makes possible a subsequent processing to improve the final image resolution. The results have been compared with the outcome of an equivalent system but in absence of diffraction, achieving promising results. The main conclusion of this work is that diffraction could be helpful for capturing images or signals when a small number of sensors available, which is far from being a resolution-limiting factor. |
| Tasks | |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00249v1 |
| http://arxiv.org/pdf/1703.00249v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-eye-visual-hyperacuity-a-new-paradigm |
| Repo | |
| Framework | |
Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
| Title | Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks |
| Authors | Sho Sonoda, Noboru Murata |
| Abstract | The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite the rapid development in its application, deep neural networks remain analytically unexplained, because the feature maps are nested and parameters are not faithful. In this paper, we address the problem of the formulation of nested complex of parameters by regarding the feature map as a transport map. Even when a feature map has different dimensions between input and output, we can regard it as a transportation map by considering that both the input and output spaces are embedded in a common high-dimensional space. In addition, the trajectory is a geometric object and thus, is independent of parameterization. In this manner, transportation can be regarded as a universal character of deep neural networks. By determining and analyzing the transportation dynamics, we can understand the behavior of a deep neural network. In this paper, we investigate a fundamental case of deep neural networks: the DAE. We derive the transport map of the DAE, and reveal that the infinitely deep DAE transports mass to decrease a certain quantity, such as entropy, of the data distribution. These results though analytically simple, shed light on the correspondence between deep neural networks and the Wasserstein gradient flows. |
| Tasks | Denoising |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04145v1 |
| http://arxiv.org/pdf/1712.04145v1.pdf | |
| PWC | https://paperswithcode.com/paper/transportation-analysis-of-denoising |
| Repo | |
| Framework | |
A Unified Framework for Low-Rank plus Sparse Matrix Recovery
| Title | A Unified Framework for Low-Rank plus Sparse Matrix Recovery |
| Authors | Xiao Zhang, Lingxiao Wang, Quanquan Gu |
| Abstract | We propose a unified framework to solve general low-rank plus sparse matrix recovery problems based on matrix factorization, which covers a broad family of objective functions satisfying the restricted strong convexity and smoothness conditions. Based on projected gradient descent and the double thresholding operator, our proposed generic algorithm is guaranteed to converge to the unknown low-rank and sparse matrices at a locally linear rate, while matching the best-known robustness guarantee (i.e., tolerance for sparsity). At the core of our theory is a novel structural Lipschitz gradient condition for low-rank plus sparse matrices, which is essential for proving the linear convergence rate of our algorithm, and we believe is of independent interest to prove fast rates for general superposition-structured models. We illustrate the application of our framework through two concrete examples: robust matrix sensing and robust PCA. Experiments on both synthetic and real datasets corroborate our theory. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06525v3 |
| http://arxiv.org/pdf/1702.06525v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-low-rank-plus-sparse |
| Repo | |
| Framework | |
Initialising Kernel Adaptive Filters via Probabilistic Inference
| Title | Initialising Kernel Adaptive Filters via Probabilistic Inference |
| Authors | Iván Castro, Cristóbal Silva, Felipe Tobar |
| Abstract | We present a probabilistic framework for both (i) determining the initial settings of kernel adaptive filters (KAFs) and (ii) constructing fully-adaptive KAFs whereby in addition to weights and dictionaries, kernel parameters are learnt sequentially. This is achieved by formulating the estimator as a probabilistic model and defining dedicated prior distributions over the kernel parameters, weights and dictionary, enforcing desired properties such as sparsity. The model can then be trained using a subset of data to initialise standard KAFs or updated sequentially each time a new observation becomes available. Due to the nonlinear/non-Gaussian properties of the model, learning and inference is achieved using gradient-based maximum-a-posteriori optimisation and Markov chain Monte Carlo methods, and can be confidently used to compute predictions. The proposed framework was validated on nonlinear time series of both synthetic and real-world nature, where it outperformed standard KAFs in terms of mean square error and the sparsity of the learnt dictionaries. |
| Tasks | Time Series |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03450v1 |
| http://arxiv.org/pdf/1707.03450v1.pdf | |
| PWC | https://paperswithcode.com/paper/initialising-kernel-adaptive-filters-via |
| Repo | |
| Framework | |
The $\mathcal{E}$-Average Common Submatrix: Approximate Searching in a Restricted Neighborhood
| Title | The $\mathcal{E}$-Average Common Submatrix: Approximate Searching in a Restricted Neighborhood |
| Authors | Alessia Amelio, Darko Brodić |
| Abstract | This paper introduces a new (dis)similarity measure for 2D arrays, extending the Average Common Submatrix measure. This is accomplished by: (i) considering the frequency of matching patterns, (ii) restricting the pattern matching to a fixed-size neighborhood, and (iii) computing a distance-based approximate matching. This will achieve better performances with low execution time and larger information retrieval. |
| Tasks | Information Retrieval |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.06026v1 |
| http://arxiv.org/pdf/1706.06026v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-mathcale-average-common-submatrix |
| Repo | |
| Framework | |
SKOS Concepts and Natural Language Concepts: an Analysis of Latent Relationships in KOSs
| Title | SKOS Concepts and Natural Language Concepts: an Analysis of Latent Relationships in KOSs |
| Authors | Anna Mastora, Manolis Peponakis, Sarantos Kapidakis |
| Abstract | The vehicle to represent Knowledge Organization Systems (KOSs) in the environment of the Semantic Web and linked data is the Simple Knowledge Organization System (SKOS). SKOS provides a way to assign a URI to each concept, and this URI functions as a surrogate for the concept. This fact makes of main concern the need to clarify the URIs’ ontological meaning. The aim of this study is to investigate the relation between the ontological substance of KOS concepts and concepts revealed through the grammatical and syntactic formalisms of natural language. For this purpose, we examined the dividableness of concepts in specific KOSs (i.e. a thesaurus, a subject headings system and a classification scheme) by applying Natural Language Processing (NLP) techniques (i.e. morphosyntactic analysis) to the lexical representations (i.e. RDF literals) of SKOS concepts. The results of the comparative analysis reveal that, despite the use of multi-word units, thesauri tend to represent concepts in a way that can hardly be further divided conceptually, while Subject Headings and Classification Schemes - to a certain extent - comprise terms that can be decomposed into more conceptual constituents. Consequently, SKOS concepts deriving from thesauri are more likely to represent atomic conceptual units and thus be more appropriate tools for inference and reasoning. Since identifiers represent the meaning of a concept, complex concepts are neither the most appropriate nor the most efficient way of modelling a KOS for the Semantic Web. |
| Tasks | |
| Published | 2017-09-16 |
| URL | http://arxiv.org/abs/1709.05576v1 |
| http://arxiv.org/pdf/1709.05576v1.pdf | |
| PWC | https://paperswithcode.com/paper/skos-concepts-and-natural-language-concepts |
| Repo | |
| Framework | |
Riemann-Theta Boltzmann Machine
| Title | Riemann-Theta Boltzmann Machine |
| Authors | Daniel Krefl, Stefano Carrazza, Babak Haghighat, Jens Kahlen |
| Abstract | A general Boltzmann machine with continuous visible and discrete integer valued hidden states is introduced. Under mild assumptions about the connection matrices, the probability density function of the visible units can be solved for analytically, yielding a novel parametric density function involving a ratio of Riemann-Theta functions. The conditional expectation of a hidden state for given visible states can also be calculated analytically, yielding a derivative of the logarithmic Riemann-Theta function. The conditional expectation can be used as activation function in a feedforward neural network, thereby increasing the modelling capacity of the network. Both the Boltzmann machine and the derived feedforward neural network can be successfully trained via standard gradient- and non-gradient-based optimization techniques. |
| Tasks | |
| Published | 2017-12-20 |
| URL | https://arxiv.org/abs/1712.07581v3 |
| https://arxiv.org/pdf/1712.07581v3.pdf | |
| PWC | https://paperswithcode.com/paper/riemann-theta-boltzmann-machine |
| Repo | |
| Framework | |
