Paper Group ANR 132
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding. Visible Light-Based Human Visual System Conceptual Model. Image-based Vehicle Analysis using Deep Neural Network: A Systematic Study. Non-Parametric Cluster Significance Testing with Reference to a Unimodal Null Distribution. Convolutional Neural Fabrics. Mapping c …
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding
| Title | Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding |
| Authors | Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei, Philip N. Garner |
| Abstract | Most current very low bit rate (VLBR) speech coding systems use hidden Markov model (HMM) based speech recognition/synthesis techniques. This allows transmission of information (such as phonemes) segment by segment that decreases the bit rate. However, the encoder based on a phoneme speech recognition may create bursts of segmental errors. Segmental errors are further propagated to optional suprasegmental (such as syllable) information coding. Together with the errors of voicing detection in pitch parametrization, HMM-based speech coding creates speech discontinuities and unnatural speech sound artefacts. In this paper, we propose a novel VLBR speech coding framework based on neural networks (NNs) for end-to-end speech analysis and synthesis without HMMs. The speech coding framework relies on phonological (sub-phonetic) representation of speech, and it is designed as a composition of deep and spiking NNs: a bank of phonological analysers at the transmitter, and a phonological synthesizer at the receiver, both realised as deep NNs, and a spiking NN as an incremental and robust encoder of syllable boundaries for coding of continuous fundamental frequency (F0). A combination of phonological features defines much more sound patterns than phonetic features defined by HMM-based speech coders, and the finer analysis/synthesis code contributes into smoother encoded speech. Listeners significantly prefer the NN-based approach due to fewer discontinuities and speech artefacts of the encoded speech. A single forward pass is required during the speech encoding and decoding. The proposed VLBR speech coding operates at a bit rate of approximately 360 bits/s. |
| Tasks | Speech Recognition |
| Published | 2016-04-15 |
| URL | http://arxiv.org/abs/1604.04383v3 |
| http://arxiv.org/pdf/1604.04383v3.pdf | |
| PWC | https://paperswithcode.com/paper/composition-of-deep-and-spiking-neural |
| Repo | |
| Framework | |
Visible Light-Based Human Visual System Conceptual Model
| Title | Visible Light-Based Human Visual System Conceptual Model |
| Authors | Lee Prangnell |
| Abstract | There exists a widely accepted set of assertions in the digital image and video coding literature, which are as follows: the Human Visual System (HVS) is more sensitive to luminance (often confused with brightness) than photon energies (often confused with chromaticity and chrominance). Passages similar to the following occur with high frequency in the peer reviewed literature and academic text books: “the HVS is much more sensitive to brightness than colour” and/or “the HVS is much more sensitive to luma than chroma”. In this discussion paper, a Visible Light-Based Human Visual System (VL-HVS) conceptual model is discussed. The objectives of VL-HVS are as follows: 1. To provide a deeper theoretical reflection of the fundamental relationship between visible light, the manifestation of colour perception derived from visible light and the physiology of the perception of colour. That is, in terms of the physics of visible light, photobiology and the human subjective interpretation of visible light, it is appropriate to provide comprehensive background information in relation to the natural interactions between visible light, the retinal photoreceptors and the subsequent cortical processing of such. 2. To provide a more wholesome account with respect to colour information in digital image and video processing applications. 3. To recontextualise colour data in the RGB and YCbCr colour spaces, such that novel techniques in digital image and video processing, including quantisation and artifact reduction techniques, may be developed based on both luma and chroma information (not luma data only). |
| Tasks | |
| Published | 2016-09-15 |
| URL | https://arxiv.org/abs/1609.04830v5 |
| https://arxiv.org/pdf/1609.04830v5.pdf | |
| PWC | https://paperswithcode.com/paper/visible-light-based-human-visual-system |
| Repo | |
| Framework | |
Image-based Vehicle Analysis using Deep Neural Network: A Systematic Study
| Title | Image-based Vehicle Analysis using Deep Neural Network: A Systematic Study |
| Authors | Yiren Zhou, Hossein Nejati, Thanh-Toan Do, Ngai-Man Cheung, Lynette Cheah |
| Abstract | We address the vehicle detection and classification problems using Deep Neural Networks (DNNs) approaches. Here we answer to questions that are specific to our application including how to utilize DNN for vehicle detection, what features are useful for vehicle classification, and how to extend a model trained on a limited size dataset, to the cases of extreme lighting condition. Answering these questions we propose our approach that outperforms state-of-the-art methods, and achieves promising results on image with extreme lighting conditions. |
| Tasks | |
| Published | 2016-01-06 |
| URL | http://arxiv.org/abs/1601.01145v2 |
| http://arxiv.org/pdf/1601.01145v2.pdf | |
| PWC | https://paperswithcode.com/paper/image-based-vehicle-analysis-using-deep |
| Repo | |
| Framework | |
Non-Parametric Cluster Significance Testing with Reference to a Unimodal Null Distribution
| Title | Non-Parametric Cluster Significance Testing with Reference to a Unimodal Null Distribution |
| Authors | Erika S. Helgeson, Eric Bair |
| Abstract | Cluster analysis is an unsupervised learning strategy that can be employed to identify subgroups of observations in data sets of unknown structure. This strategy is particularly useful for analyzing high-dimensional data such as microarray gene expression data. Many clustering methods are available, but it is challenging to determine if the identified clusters represent distinct subgroups. We propose a novel strategy to investigate the significance of identified clusters by comparing the within- cluster sum of squares from the original data to that produced by clustering an appropriate unimodal null distribution. The null distribution we present for this problem uses kernel density estimation and thus does not require that the data follow any particular distribution. We find that our method can accurately test for the presence of clustering even when the number of features is high. |
| Tasks | Density Estimation |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01424v2 |
| http://arxiv.org/pdf/1610.01424v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-parametric-cluster-significance-testing |
| Repo | |
| Framework | |
Convolutional Neural Fabrics
| Title | Convolutional Neural Fabrics |
| Authors | Shreyas Saxena, Jakob Verbeek |
| Abstract | Despite the success of CNNs, selecting the optimal architecture for a given task remains an open problem. Instead of aiming to select a single optimal architecture, we propose a “fabric” that embeds an exponentially large number of architectures. The fabric consists of a 3D trellis that connects response maps at different layers, scales, and channels with a sparse homogeneous local connectivity pattern. The only hyper-parameters of a fabric are the number of channels and layers. While individual architectures can be recovered as paths, the fabric can in addition ensemble all embedded architectures together, sharing their weights where their paths overlap. Parameters can be learned using standard methods based on back-propagation, at a cost that scales linearly in the fabric size. We present benchmark results competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2016-06-08 |
| URL | http://arxiv.org/abs/1606.02492v4 |
| http://arxiv.org/pdf/1606.02492v4.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-fabrics |
| Repo | |
| Framework | |
Mapping chemical performance on molecular structures using locally interpretable explanations
| Title | Mapping chemical performance on molecular structures using locally interpretable explanations |
| Authors | Leanne S. Whitmore, Anthe George, Corey M. Hudson |
| Abstract | In this work, we present an application of Locally Interpretable Machine-Agnostic Explanations to 2-D chemical structures. Using this framework we are able to provide a structural interpretation for an existing black-box model for classifying biologically produced fuel compounds with regard to Research Octane Number. This method of “painting” locally interpretable explanations onto 2-D chemical structures replicates the chemical intuition of synthetic chemists, allowing researchers in the field to directly accept, reject, inform and evaluate decisions underlying inscrutably complex quantitative structure-activity relationship models. |
| Tasks | |
| Published | 2016-11-22 |
| URL | http://arxiv.org/abs/1611.07443v1 |
| http://arxiv.org/pdf/1611.07443v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-chemical-performance-on-molecular |
| Repo | |
| Framework | |
A temporal model for multiple sclerosis course evolution
| Title | A temporal model for multiple sclerosis course evolution |
| Authors | Samuele Fiorini, Andrea Tacchino, Giampaolo Brichetto, Alessandro Verri, Annalisa Barla |
| Abstract | Multiple Sclerosis is a degenerative condition of the central nervous system that affects nearly 2.5 million of individuals in terms of their physical, cognitive, psychological and social capabilities. Researchers are currently investigating on the use of patient reported outcome measures for the assessment of impact and evolution of the disease on the life of the patients. To date, a clear understanding on the use of such measures to predict the evolution of the disease is still lacking. In this work we resort to regularized machine learning methods for binary classification and multiple output regression. We propose a pipeline that can be used to predict the disease progression from patient reported measures. The obtained model is tested on a data set collected from an ongoing clinical research project. |
| Tasks | |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00615v1 |
| http://arxiv.org/pdf/1612.00615v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-temporal-model-for-multiple-sclerosis |
| Repo | |
| Framework | |
Automatic LQR Tuning Based on Gaussian Process Global Optimization
| Title | Automatic LQR Tuning Based on Gaussian Process Global Optimization |
| Authors | Alonso Marco, Philipp Hennig, Jeannette Bohg, Stefan Schaal, Sebastian Trimpe |
| Abstract | This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree-of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Results of a two- and four-dimensional tuning problems highlight the method’s potential for automatic controller tuning on robotic platforms. |
| Tasks | |
| Published | 2016-05-06 |
| URL | http://arxiv.org/abs/1605.01950v1 |
| http://arxiv.org/pdf/1605.01950v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-lqr-tuning-based-on-gaussian |
| Repo | |
| Framework | |
Noisy Inductive Matrix Completion Under Sparse Factor Models
| Title | Noisy Inductive Matrix Completion Under Sparse Factor Models |
| Authors | Akshay Soni, Troy Chevalier, Swayambhoo Jain |
| Abstract | Inductive Matrix Completion (IMC) is an important class of matrix completion problems that allows direct inclusion of available features to enhance estimation capabilities. These models have found applications in personalized recommendation systems, multilabel learning, dictionary learning, etc. This paper examines a general class of noisy matrix completion tasks where the underlying matrix is following an IMC model i.e., it is formed by a mixing matrix (a priori unknown) sandwiched between two known feature matrices. The mixing matrix here is assumed to be well approximated by the product of two sparse matrices—referred here to as “sparse factor models.” We leverage the main theorem of Soni:2016:NMC and extend it to provide theoretical error bounds for the sparsity-regularized maximum likelihood estimators for the class of problems discussed in this paper. The main result is general in the sense that it can be used to derive error bounds for various noise models. In this paper, we instantiate our main result for the case of Gaussian noise and provide corresponding error bounds in terms of squared loss. |
| Tasks | Dictionary Learning, Matrix Completion, Recommendation Systems |
| Published | 2016-09-13 |
| URL | http://arxiv.org/abs/1609.03958v1 |
| http://arxiv.org/pdf/1609.03958v1.pdf | |
| PWC | https://paperswithcode.com/paper/noisy-inductive-matrix-completion-under |
| Repo | |
| Framework | |
Revisiting Role Discovery in Networks: From Node to Edge Roles
| Title | Revisiting Role Discovery in Networks: From Node to Edge Roles |
| Authors | Nesreen K. Ahmed, Ryan A. Rossi, Theodore L. Willke, Rong Zhou |
| Abstract | Previous work in network analysis has focused on modeling the mixed-memberships of node roles in the graph, but not the roles of edges. We introduce the edge role discovery problem and present a generalizable framework for learning and extracting edge roles from arbitrary graphs automatically. Furthermore, while existing node-centric role models have mainly focused on simple degree and egonet features, this work also explores graphlet features for role discovery. In addition, we also develop an approach for automatically learning and extracting important and useful edge features from an arbitrary graph. The experimental results demonstrate the utility of edge roles for network analysis tasks on a variety of graphs from various problem domains. |
| Tasks | |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.00844v2 |
| http://arxiv.org/pdf/1610.00844v2.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-role-discovery-in-networks-from |
| Repo | |
| Framework | |
A Physical Metaphor to Study Semantic Drift
| Title | A Physical Metaphor to Study Semantic Drift |
| Authors | Sándor Darányi, Peter Wittek, Konstantinos Konstantinidis, Symeon Papadopoulos, Efstratios Kontopoulos |
| Abstract | In accessibility tests for digital preservation, over time we experience drifts of localized and labelled content in statistical models of evolving semantics represented as a vector field. This articulates the need to detect, measure, interpret and model outcomes of knowledge dynamics. To this end we employ a high-performance machine learning algorithm for the training of extremely large emergent self-organizing maps for exploratory data analysis. The working hypothesis we present here is that the dynamics of semantic drifts can be modeled on a relaxed version of Newtonian mechanics called social mechanics. By using term distances as a measure of semantic relatedness vs. their PageRank values indicating social importance and applied as variable term mass', gravitation as a metaphor to express changes in the semantic content of a vector field lends a new perspective for experimentation. From term gravitation’ over time, one can compute its generating potential whose fluctuations manifest modifications in pairwise term similarity vs. social importance, thereby updating Osgood’s semantic differential. The dataset examined is the public catalog metadata of Tate Galleries, London. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01298v1 |
| http://arxiv.org/pdf/1608.01298v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-physical-metaphor-to-study-semantic-drift |
| Repo | |
| Framework | |
In narrative texts punctuation marks obey the same statistics as words
| Title | In narrative texts punctuation marks obey the same statistics as words |
| Authors | Andrzej Kulig, Jaroslaw Kwapien, Tomasz Stanisz, Stanislaw Drozdz |
| Abstract | From a grammar point of view, the role of punctuation marks in a sentence is formally defined and well understood. In semantic analysis punctuation plays also a crucial role as a method of avoiding ambiguity of the meaning. A different situation can be observed in the statistical analyses of language samples, where the decision on whether the punctuation marks should be considered or should be neglected is seen rather as arbitrary and at present it belongs to a researcher’s preference. An objective of this work is to shed some light onto this problem by providing us with an answer to the question whether the punctuation marks may be treated as ordinary words and whether they should be included in any analysis of the word co-occurences. We already know from our previous study (S.~Dro.zd.z {\it et al.}, Inf. Sci. 331 (2016) 32-44) that full stops that determine the length of sentences are the main carrier of long-range correlations. Now we extend that study and analyze statistical properties of the most common punctuation marks in a few Indo-European languages, investigate their frequencies, and locate them accordingly in the Zipf rank-frequency plots as well as study their role in the word-adjacency networks. We show that, from a statistical viewpoint, the punctuation marks reveal properties that are qualitatively similar to the properties of the most frequent words like articles, conjunctions, pronouns, and prepositions. This refers to both the Zipfian analysis and the network analysis. By adding the punctuation marks to the Zipf plots, we also show that these plots that are normally described by the Zipf-Mandelbrot distribution largely restore the power-law Zipfian behaviour for the most frequent items. |
| Tasks | |
| Published | 2016-04-04 |
| URL | http://arxiv.org/abs/1604.00834v2 |
| http://arxiv.org/pdf/1604.00834v2.pdf | |
| PWC | https://paperswithcode.com/paper/in-narrative-texts-punctuation-marks-obey-the |
| Repo | |
| Framework | |
Comparing the hierarchy of keywords in on-line news portals
| Title | Comparing the hierarchy of keywords in on-line news portals |
| Authors | Gergely Tibély, David Sousa-Rodrigues, Péter Pollner, Gergely Palla |
| Abstract | The tagging of on-line content with informative keywords is a widespread phenomenon from scientific article repositories through blogs to on-line news portals. In most of the cases, the tags on a given item are free words chosen by the authors independently. Therefore, relations among keywords in a collection of news items is unknown. However, in most cases the topics and concepts described by these keywords are forming a latent hierarchy, with the more general topics and categories at the top, and more specialised ones at the bottom. Here we apply a recent, cooccurrence-based tag hierarchy extraction method to sets of keywords obtained from four different on-line news portals. The resulting hierarchies show substantial differences not just in the topics rendered as important (being at the top of the hierarchy) or of less interest (categorised low in the hierarchy), but also in the underlying network structure. This reveals discrepancies between the plausible keyword association frameworks in the studied news portals. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06142v1 |
| http://arxiv.org/pdf/1606.06142v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-the-hierarchy-of-keywords-in-on |
| Repo | |
| Framework | |
On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra
| Title | On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra |
| Authors | C. Dafonte, D. Fustes, M. Manteiga, D. Garabato, M. A. Alvarez, A. Ulla, C. Allende Prieto |
| Abstract | Aims. We present an innovative artificial neural network (ANN) architecture, called Generative ANN (GANN), that computes the forward model, that is it learns the function that relates the unknown outputs (stellar atmospheric parameters, in this case) to the given inputs (spectra). Such a model can be integrated in a Bayesian framework to estimate the posterior distribution of the outputs. Methods. The architecture of the GANN follows the same scheme as a normal ANN, but with the inputs and outputs inverted. We train the network with the set of atmospheric parameters (Teff, logg, [Fe/H] and [alpha/Fe]), obtaining the stellar spectra for such inputs. The residuals between the spectra in the grid and the estimated spectra are minimized using a validation dataset to keep solutions as general as possible. Results. The performance of both conventional ANNs and GANNs to estimate the stellar parameters as a function of the star brightness is presented and compared for different Galactic populations. GANNs provide significantly improved parameterizations for early and intermediate spectral types with rich and intermediate metallicities. The behaviour of both algorithms is very similar for our sample of late-type stars, obtaining residuals in the derivation of [Fe/H] and [alpha/Fe] below 0.1dex for stars with Gaia magnitude Grvs<12, which accounts for a number in the order of four million stars to be observed by the Radial Velocity Spectrograph of the Gaia satellite. Conclusions. Uncertainty estimation of computed astrophysical parameters is crucial for the validation of the parameterization itself and for the subsequent exploitation by the astronomical community. GANNs produce not only the parameters for a given spectrum, but a goodness-of-fit between the observed spectrum and the predicted one for a given set of parameters. Moreover, they allow us to obtain the full posterior distribution… |
| Tasks | |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05954v1 |
| http://arxiv.org/pdf/1607.05954v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-estimation-of-stellar-parameters-with |
| Repo | |
| Framework | |
Deep Deformable Registration: Enhancing Accuracy by Fully Convolutional Neural Net
| Title | Deep Deformable Registration: Enhancing Accuracy by Fully Convolutional Neural Net |
| Authors | Sayan Ghosal, Nilanjan Ray |
| Abstract | Deformable registration is ubiquitous in medical image analysis. Many deformable registration methods minimize sum of squared difference (SSD) as the registration cost with respect to deformable model parameters. In this work, we construct a tight upper bound of the SSD registration cost by using a fully convolutional neural network (FCNN) in the registration pipeline. The upper bound SSD (UB-SSD) enhances the original deformable model parameter space by adding a heatmap output from FCNN. Next, we minimize this UB-SSD by adjusting both the parameters of the FCNN and the parameters of the deformable model in coordinate descent. Our coordinate descent framework is end-to-end and can work with any deformable registration method that uses SSD. We demonstrate experimentally that our method enhances the accuracy of deformable registration algorithms significantly on two publicly available 3D brain MRI data sets. |
| Tasks | |
| Published | 2016-11-27 |
| URL | http://arxiv.org/abs/1611.08796v1 |
| http://arxiv.org/pdf/1611.08796v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-deformable-registration-enhancing |
| Repo | |
| Framework | |
