Paper Group ANR 138
Neural networks for the prediction organic chemistry reactions. And the Winner is …: Bayesian Twitter-based Prediction on 2016 U.S. Presidential Election. Detecting Breast Cancer using a Compressive Sensing Unmixing Algorithm. Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks. Lensless Imaging with Compressive Ultrafa …
Neural networks for the prediction organic chemistry reactions
| Title | Neural networks for the prediction organic chemistry reactions |
| Authors | Jennifer N. Wei, David Duvenaud, Alán Aspuru-Guzik |
| Abstract | Reaction prediction remains one of the major challenges for organic chemistry, and is a pre-requisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, “learn” from being exposed to examples of the application of the rules of organic chemistry. We explore the use of neural networks for predicting reaction types, using a new reaction fingerprinting method. We combine this predictor with SMARTS transformations to build a system which, given a set of reagents and re- actants, predicts the likely products. We test this method on problems from a popular organic chemistry textbook. |
| Tasks | |
| Published | 2016-08-22 |
| URL | http://arxiv.org/abs/1608.06296v2 |
| http://arxiv.org/pdf/1608.06296v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-for-the-prediction-organic |
| Repo | |
| Framework | |
And the Winner is …: Bayesian Twitter-based Prediction on 2016 U.S. Presidential Election
| Title | And the Winner is …: Bayesian Twitter-based Prediction on 2016 U.S. Presidential Election |
| Authors | Elvyna Tunggawan, Yustinus Eko Soelistio |
| Abstract | This paper describes a Naive-Bayesian predictive model for 2016 U.S. Presidential Election based on Twitter data. We use 33,708 tweets gathered since December 16, 2015 until February 29, 2016. We introduce a simpler data preprocessing method to label the data and train the model. The model achieves 95.8% accuracy on 10-fold cross validation and predicts Ted Cruz and Bernie Sanders as Republican and Democratic nominee respectively. It achieves a comparable result to those in its competitor methods. |
| Tasks | |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00440v1 |
| http://arxiv.org/pdf/1611.00440v1.pdf | |
| PWC | https://paperswithcode.com/paper/and-the-winner-is-bayesian-twitter-based |
| Repo | |
| Framework | |
Detecting Breast Cancer using a Compressive Sensing Unmixing Algorithm
| Title | Detecting Breast Cancer using a Compressive Sensing Unmixing Algorithm |
| Authors | Richard Obermeier, Jose Angel Martinez-Lorenzo |
| Abstract | Traditional breast cancer imaging methods using microwave Nearfield Radar Imaging (NRI) seek to recover the complex permittivity of the tissues at each voxel in the imaging region. This approach is suboptimal, in that it does not directly consider the permittivity values that healthy and cancerous breast tissues typically have. In this paper, we describe a novel unmixing algorithm for detecting breast cancer. In this approach, the breast tissue is separated into three components, low water content (LWC), high water content (HWC), and cancerous tissues, and the goal of the optimization procedure is to recover the mixture proportions for each component. By utilizing this approach in a hybrid DBT / NRI system, the unmixing reconstruction process can be posed as a sparse recovery problem, such that compressive sensing (CS) techniques can be employed. A numerical analysis is performed, which demonstrates that cancerous lesions can be detected from their mixture proportion under the appropriate conditions. |
| Tasks | Compressive Sensing |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09386v1 |
| http://arxiv.org/pdf/1610.09386v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-breast-cancer-using-a-compressive |
| Repo | |
| Framework | |
Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks
| Title | Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks |
| Authors | Masoud Abdi, Saeid Nahavandi |
| Abstract | In this article, we take one step toward understanding the learning behavior of deep residual networks, and supporting the observation that deep residual networks behave like ensembles. We propose a new convolutional neural network architecture which builds upon the success of residual networks by explicitly exploiting the interpretation of very deep networks as an ensemble. The proposed multi-residual network increases the number of residual functions in the residual blocks. Our architecture generates models that are wider, rather than deeper, which significantly improves accuracy. We show that our model achieves an error rate of 3.73% and 19.45% on CIFAR-10 and CIFAR-100 respectively, that outperforms almost all of the existing models. We also demonstrate that our model outperforms very deep residual networks by 0.22% (top-1 error) on the full ImageNet 2012 classification dataset. Additionally, inspired by the parallel structure of multi-residual networks, a model parallelism technique has been investigated. The model parallelism method distributes the computation of residual blocks among the processors, yielding up to 15% computational complexity improvement. |
| Tasks | |
| Published | 2016-09-19 |
| URL | http://arxiv.org/abs/1609.05672v4 |
| http://arxiv.org/pdf/1609.05672v4.pdf | |
| PWC | https://paperswithcode.com/paper/multi-residual-networks-improving-the-speed |
| Repo | |
| Framework | |
Lensless Imaging with Compressive Ultrafast Sensing
| Title | Lensless Imaging with Compressive Ultrafast Sensing |
| Authors | Guy Satat, Matthew Tancik, Ramesh Raskar |
| Abstract | Lensless imaging is an important and challenging problem. One notable solution to lensless imaging is a single pixel camera which benefits from ideas central to compressive sampling. However, traditional single pixel cameras require many illumination patterns which result in a long acquisition process. Here we present a method for lensless imaging based on compressive ultrafast sensing. Each sensor acquisition is encoded with a different illumination pattern and produces a time series where time is a function of the photon’s origin in the scene. Currently available hardware with picosecond time resolution enables time tagging photons as they arrive to an omnidirectional sensor. This allows lensless imaging with significantly fewer patterns compared to regular single pixel imaging. To that end, we develop a framework for designing lensless imaging systems that use ultrafast detectors. We provide an algorithm for ideal sensor placement and an algorithm for optimized active illumination patterns. We show that efficient lensless imaging is possible with ultrafast measurement and compressive sensing. This paves the way for novel imaging architectures and remote sensing in extreme situations where imaging with a lens is not possible. |
| Tasks | Compressive Sensing, Time Series |
| Published | 2016-10-19 |
| URL | http://arxiv.org/abs/1610.05834v2 |
| http://arxiv.org/pdf/1610.05834v2.pdf | |
| PWC | https://paperswithcode.com/paper/lensless-imaging-with-compressive-ultrafast |
| Repo | |
| Framework | |
Understanding Deep Neural Networks with Rectified Linear Units
| Title | Understanding Deep Neural Networks with Rectified Linear Units |
| Authors | Raman Arora, Amitabh Basu, Poorya Mianjy, Anirbit Mukherjee |
| Abstract | In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to global optimality with runtime polynomial in the data size albeit exponential in the input dimension. Further, we improve on the known lower bounds on size (from exponential to super exponential) for approximating a ReLU deep net function by a shallower ReLU net. Our gap theorems hold for smoothly parametrized families of “hard” functions, contrary to countable, discrete families known in the literature. An example consequence of our gap theorems is the following: for every natural number $k$ there exists a function representable by a ReLU DNN with $k^2$ hidden layers and total size $k^3$, such that any ReLU DNN with at most $k$ hidden layers will require at least $\frac{1}{2}k^{k+1}-1$ total nodes. Finally, for the family of $\mathbb{R}^n\to \mathbb{R}$ DNNs with ReLU activations, we show a new lowerbound on the number of affine pieces, which is larger than previous constructions in certain regimes of the network architecture and most distinctively our lowerbound is demonstrated by an explicit construction of a smoothly parameterized family of functions attaining this scaling. Our construction utilizes the theory of zonotopes from polyhedral theory. |
| Tasks | |
| Published | 2016-11-04 |
| URL | http://arxiv.org/abs/1611.01491v6 |
| http://arxiv.org/pdf/1611.01491v6.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-deep-neural-networks-with |
| Repo | |
| Framework | |
Statistical Guarantees for Estimating the Centers of a Two-component Gaussian Mixture by EM
| Title | Statistical Guarantees for Estimating the Centers of a Two-component Gaussian Mixture by EM |
| Authors | Jason M. Klusowski, W. D. Brinda |
| Abstract | Recently, a general method for analyzing the statistical accuracy of the EM algorithm has been developed and applied to some simple latent variable models [Balakrishnan et al. 2016]. In that method, the basin of attraction for valid initialization is required to be a ball around the truth. Using Stein’s Lemma, we extend these results in the case of estimating the centers of a two-component Gaussian mixture in $d$ dimensions. In particular, we significantly expand the basin of attraction to be the intersection of a half space and a ball around the origin. If the signal-to-noise ratio is at least a constant multiple of $ \sqrt{d\log d} $, we show that a random initialization strategy is feasible. |
| Tasks | Latent Variable Models |
| Published | 2016-08-07 |
| URL | http://arxiv.org/abs/1608.02280v1 |
| http://arxiv.org/pdf/1608.02280v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-guarantees-for-estimating-the |
| Repo | |
| Framework | |
Mixtures of Bivariate von Mises Distributions with Applications to Modelling of Protein Dihedral Angles
| Title | Mixtures of Bivariate von Mises Distributions with Applications to Modelling of Protein Dihedral Angles |
| Authors | Parthan Kasarapu |
| Abstract | The modelling of empirically observed data is commonly done using mixtures of probability distributions. In order to model angular data, directional probability distributions such as the bivariate von Mises (BVM) is typically used. The critical task involved in mixture modelling is to determine the optimal number of component probability distributions. We employ the Bayesian information-theoretic principle of minimum message length (MML) to distinguish mixture models by balancing the trade-off between the model’s complexity and its goodness-of-fit to the data. We consider the problem of modelling angular data resulting from the spatial arrangement of protein structures using BVM distributions. The main contributions of the paper include the development of the mixture modelling apparatus along with the MML estimation of the parameters of the BVM distribution. We demonstrate that statistical inference using the MML framework supersedes the traditional methods and offers a mechanism to objectively determine models that are of practical significance. |
| Tasks | |
| Published | 2016-07-05 |
| URL | http://arxiv.org/abs/1607.01312v2 |
| http://arxiv.org/pdf/1607.01312v2.pdf | |
| PWC | https://paperswithcode.com/paper/mixtures-of-bivariate-von-mises-distributions |
| Repo | |
| Framework | |
CNN based texture synthesize with Semantic segment
| Title | CNN based texture synthesize with Semantic segment |
| Authors | Xianye Liang, Bocheng Zhuo, Peijie Li, Liangju He |
| Abstract | Deep learning algorithm display powerful ability in Computer Vision area, in recent year, the CNN has been applied to solve problems in the subarea of Image-generating, which has been widely applied in areas such as photo editing, image design, computer animation, real-time rendering for large scale of scenes and for visual effects in movies. However in the texture synthesize procedure. The state-of-art CNN can not capture the spatial location of texture in image, lead to significant distortion after texture synthesize, we propose a new way to generating-image by adding the semantic segment step with deep learning algorithm as Pre-Processing and analyze the outcome. |
| Tasks | |
| Published | 2016-05-16 |
| URL | http://arxiv.org/abs/1605.04731v1 |
| http://arxiv.org/pdf/1605.04731v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnn-based-texture-synthesize-with-semantic |
| Repo | |
| Framework | |
Adaptive foveated single-pixel imaging with dynamic super-sampling
| Title | Adaptive foveated single-pixel imaging with dynamic super-sampling |
| Authors | David B. Phillips, Ming-Jie Sun, Jonathan M. Taylor, Matthew P. Edgar, Stephen M. Barnett, Graham G. Gibson, Miles J. Padgett |
| Abstract | As an alternative to conventional multi-pixel cameras, single-pixel cameras enable images to be recorded using a single detector that measures the correlations between the scene and a set of patterns. However, to fully sample a scene in this way requires at least the same number of correlation measurements as there are pixels in the reconstructed image. Therefore single-pixel imaging systems typically exhibit low frame-rates. To mitigate this, a range of compressive sensing techniques have been developed which rely on a priori knowledge of the scene to reconstruct images from an under-sampled set of measurements. In this work we take a different approach and adopt a strategy inspired by the foveated vision systems found in the animal kingdom - a framework that exploits the spatio-temporal redundancy present in many dynamic scenes. In our single-pixel imaging system a high-resolution foveal region follows motion within the scene, but unlike a simple zoom, every frame delivers new spatial information from across the entire field-of-view. Using this approach we demonstrate a four-fold reduction in the time taken to record the detail of rapidly evolving features, whilst simultaneously accumulating detail of more slowly evolving regions over several consecutive frames. This tiered super-sampling technique enables the reconstruction of video streams in which both the resolution and the effective exposure-time spatially vary and adapt dynamically in response to the evolution of the scene. The methods described here can complement existing compressive sensing approaches and may be applied to enhance a variety of computational imagers that rely on sequential correlation measurements. |
| Tasks | Compressive Sensing |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08236v1 |
| http://arxiv.org/pdf/1607.08236v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-foveated-single-pixel-imaging-with |
| Repo | |
| Framework | |
Data Clustering and Graph Partitioning via Simulated Mixing
| Title | Data Clustering and Graph Partitioning via Simulated Mixing |
| Authors | Shahzad Bhatti, Carolyn Beck, Angelia Nedic |
| Abstract | Spectral clustering approaches have led to well-accepted algorithms for finding accurate clusters in a given dataset. However, their application to large-scale datasets has been hindered by computational complexity of eigenvalue decompositions. Several algorithms have been proposed in the recent past to accelerate spectral clustering, however they compromise on the accuracy of the spectral clustering to achieve faster speed. In this paper, we propose a novel spectral clustering algorithm based on a mixing process on a graph. Unlike the existing spectral clustering algorithms, our algorithm does not require computing eigenvectors. Specifically, it finds the equivalent of a linear combination of eigenvectors of the normalized similarity matrix weighted with corresponding eigenvalues. This linear combination is then used to partition the dataset into meaningful clusters. Simulations on real datasets show that partitioning datasets based on such linear combinations of eigenvectors achieves better accuracy than standard spectral clustering methods as the number of clusters increase. Our algorithm can easily be implemented in a distributed setting. |
| Tasks | graph partitioning |
| Published | 2016-03-15 |
| URL | http://arxiv.org/abs/1603.04918v1 |
| http://arxiv.org/pdf/1603.04918v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-clustering-and-graph-partitioning-via |
| Repo | |
| Framework | |
Phase Unmixing : Multichannel Source Separation with Magnitude Constraints
| Title | Phase Unmixing : Multichannel Source Separation with Magnitude Constraints |
| Authors | Antoine Deleforge, Yann Traonmilin |
| Abstract | We consider the problem of estimating the phases of K mixed complex signals from a multichannel observation, when the mixing matrix and signal magnitudes are known. This problem can be cast as a non-convex quadratically constrained quadratic program which is known to be NP-hard in general. We propose three approaches to tackle it: a heuristic method, an alternate minimization method, and a convex relaxation into a semi-definite program. The last two approaches are showed to outperform the oracle multichannel Wiener filter in under-determined informed source separation tasks, using simulated and speech signals. The convex relaxation approach yields best results, including the potential for exact source separation in under-determined settings. |
| Tasks | |
| Published | 2016-09-30 |
| URL | http://arxiv.org/abs/1609.09744v2 |
| http://arxiv.org/pdf/1609.09744v2.pdf | |
| PWC | https://paperswithcode.com/paper/phase-unmixing-multichannel-source-separation |
| Repo | |
| Framework | |
Sequential Low-Rank Change Detection
| Title | Sequential Low-Rank Change Detection |
| Authors | Yao Xie, Lee Seversky |
| Abstract | Detecting emergence of a low-rank signal from high-dimensional data is an important problem arising from many applications such as camera surveillance and swarm monitoring using sensors. We consider a procedure based on the largest eigenvalue of the sample covariance matrix over a sliding window to detect the change. To achieve dimensionality reduction, we present a sketching-based approach for rank change detection using the low-dimensional linear sketches of the original high-dimensional observations. The premise is that when the sketching matrix is a random Gaussian matrix, and the dimension of the sketching vector is sufficiently large, the rank of sample covariance matrix for these sketches equals the rank of the original sample covariance matrix with high probability. Hence, we may be able to detect the low-rank change using sample covariance matrices of the sketches without having to recover the original covariance matrix. We character the performance of the largest eigenvalue statistic in terms of the false-alarm-rate and the expected detection delay, and present an efficient online implementation via subspace tracking. |
| Tasks | Dimensionality Reduction |
| Published | 2016-10-03 |
| URL | http://arxiv.org/abs/1610.00732v2 |
| http://arxiv.org/pdf/1610.00732v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-low-rank-change-detection |
| Repo | |
| Framework | |
Anomaly Detection in XML-Structured SOAP Messages Using Tree-Based Association Rule Mining
| Title | Anomaly Detection in XML-Structured SOAP Messages Using Tree-Based Association Rule Mining |
| Authors | Reyhaneh Ghassem Esfahani, Mohammad Abadollahi Azgomi, Reza Fathi |
| Abstract | Web services are software systems designed for supporting interoperable dynamic cross-enterprise interactions. The result of attacks to Web services can be catastrophic and causing the disclosure of enterprises’ confidential data. As new approaches of attacking arise every day, anomaly detection systems seem to be invaluable tools in this context. The aim of this work has been to target the attacks that reside in the Web service layer and the extensible markup language (XML)-structured simple object access protocol (SOAP) messages. After studying the shortcomings of the existing solutions, a new approach for detecting anomalies in Web services is outlined. More specifically, the proposed technique illustrates how to identify anomalies by employing mining methods on XML-structured SOAP messages. This technique also takes the advantages of tree-based association rule mining to extract knowledge in the training phase, which is used in the test phase to detect anomalies. In addition, this novel composition of techniques brings nearly low false alarm rate while maintaining the detection rate reasonably high, which is shown by a case study. |
| Tasks | Anomaly Detection |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06466v1 |
| http://arxiv.org/pdf/1605.06466v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-xml-structured-soap |
| Repo | |
| Framework | |
High Dimensional Human Guided Machine Learning
| Title | High Dimensional Human Guided Machine Learning |
| Authors | Eric Holloway, Robert Marks II |
| Abstract | Have you ever looked at a machine learning classification model and thought, I could have made that? Well, that is what we test in this project, comparing XGBoost trained on human engineered features to training directly on data. The human engineered features do not outperform XGBoost trained di- rectly on the data, but they are comparable. This project con- tributes a novel method for utilizing human created classifi- cation models on high dimensional datasets. |
| Tasks | |
| Published | 2016-09-04 |
| URL | http://arxiv.org/abs/1609.00904v1 |
| http://arxiv.org/pdf/1609.00904v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-human-guided-machine |
| Repo | |
| Framework | |
