Paper Group ANR 339
Semiparametric energy-based probabilistic models. VLSI Extreme Learning Machine: A Design Space Exploration. Permutation-equivariant neural networks applied to dynamics prediction. Time Series Structure Discovery via Probabilistic Program Synthesis. Supervised Term Weighting Metrics for Sentiment Analysis in Short Text. Phase-Mapper: An AI Platform …
Semiparametric energy-based probabilistic models
| Title | Semiparametric energy-based probabilistic models |
| Authors | Jan Humplik, Gašper Tkačik |
| Abstract | Probabilistic models can be defined by an energy function, where the probability of each state is proportional to the exponential of the state’s negative energy. This paper considers a generalization of energy-based models in which the probability of a state is proportional to an arbitrary positive, strictly decreasing, and twice differentiable function of the state’s energy. The precise shape of the nonlinear map from energies to unnormalized probabilities has to be learned from data together with the parameters of the energy function. As a case study we show that the above generalization of a fully visible Boltzmann machine yields an accurate model of neural activity of retinal ganglion cells. We attribute this success to the model’s ability to easily capture distributions whose probabilities span a large dynamic range, a possible consequence of latent variables that globally couple the system. Similar features have recently been observed in many datasets, suggesting that our new method has wide applicability. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07371v1 |
| http://arxiv.org/pdf/1605.07371v1.pdf | |
| PWC | https://paperswithcode.com/paper/semiparametric-energy-based-probabilistic |
| Repo | |
| Framework | |
VLSI Extreme Learning Machine: A Design Space Exploration
| Title | VLSI Extreme Learning Machine: A Design Space Exploration |
| Authors | Enyi Yao, Arindam Basu |
| Abstract | In this paper, we describe a compact low-power, high performance hardware implementation of the extreme learning machine (ELM) for machine learning applications. Mismatch in current mirrors are used to perform the vector-matrix multiplication that forms the first stage of this classifier and is the most computationally intensive. Both regression and classification (on UCI data sets) are demonstrated and a design space trade-off between speed, power and accuracy is explored. Our results indicate that for a wide set of problems, $\sigma V_T$ in the range of $15-25$mV gives optimal results. An input weight matrix rotation method to extend the input dimension and hidden layer size beyond the physical limits imposed by the chip is also described. This allows us to overcome a major limit imposed on most hardware machine learners. The chip is implemented in a $0.35 \mu$m CMOS process and occupies a die area of around 5 mm $\times$ 5 mm. Operating from a $1$ V power supply, it achieves an energy efficiency of $0.47$ pJ/MAC at a classification rate of $31.6$ kHz. |
| Tasks | |
| Published | 2016-05-03 |
| URL | http://arxiv.org/abs/1605.00740v1 |
| http://arxiv.org/pdf/1605.00740v1.pdf | |
| PWC | https://paperswithcode.com/paper/vlsi-extreme-learning-machine-a-design-space |
| Repo | |
| Framework | |
Permutation-equivariant neural networks applied to dynamics prediction
| Title | Permutation-equivariant neural networks applied to dynamics prediction |
| Authors | Nicholas Guttenberg, Nathaniel Virgo, Olaf Witkowski, Hidetoshi Aoki, Ryota Kanai |
| Abstract | The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain. In comparison, there are a number of problems in which there are a number of different inputs which are all ‘of the same type’ — multiple particles, multiple agents, multiple stock prices, etc. The corresponding symmetry to this is permutation symmetry, in that the algorithm should not depend on the specific ordering of the input data. We discuss a permutation-invariant neural network layer in analogy to convolutional layers, and show the ability of this architecture to learn to predict the motion of a variable number of interacting hard discs in 2D. In the same way that convolutional layers can generalize to different image sizes, the permutation layer we describe generalizes to different numbers of objects. |
| Tasks | |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04530v1 |
| http://arxiv.org/pdf/1612.04530v1.pdf | |
| PWC | https://paperswithcode.com/paper/permutation-equivariant-neural-networks |
| Repo | |
| Framework | |
Time Series Structure Discovery via Probabilistic Program Synthesis
| Title | Time Series Structure Discovery via Probabilistic Program Synthesis |
| Authors | Ulrich Schaechtle, Feras Saad, Alexey Radul, Vikash Mansinghka |
| Abstract | There is a widespread need for techniques that can discover structure from time series data. Recently introduced techniques such as Automatic Bayesian Covariance Discovery (ABCD) provide a way to find structure within a single time series by searching through a space of covariance kernels that is generated using a simple grammar. While ABCD can identify a broad class of temporal patterns, it is difficult to extend and can be brittle in practice. This paper shows how to extend ABCD by formulating it in terms of probabilistic program synthesis. The key technical ideas are to (i) represent models using abstract syntax trees for a domain-specific probabilistic language, and (ii) represent the time series model prior, likelihood, and search strategy using probabilistic programs in a sufficiently expressive language. The final probabilistic program is written in under 70 lines of probabilistic code in Venture. The paper demonstrates an application to time series clustering that involves a non-parametric extension to ABCD, experiments for interpolation and extrapolation on real-world econometric data, and improvements in accuracy over both non-parametric and standard regression baselines. |
| Tasks | Program Synthesis, Time Series, Time Series Clustering |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.07051v3 |
| http://arxiv.org/pdf/1611.07051v3.pdf | |
| PWC | https://paperswithcode.com/paper/time-series-structure-discovery-via |
| Repo | |
| Framework | |
Supervised Term Weighting Metrics for Sentiment Analysis in Short Text
| Title | Supervised Term Weighting Metrics for Sentiment Analysis in Short Text |
| Authors | Hussam Hamdan, Patrice Bellot, Frederic Bechet |
| Abstract | Term weighting metrics assign weights to terms in order to discriminate the important terms from the less crucial ones. Due to this characteristic, these metrics have attracted growing attention in text classification and recently in sentiment analysis. Using the weights given by such metrics could lead to more accurate document representation which may improve the performance of the classification. While previous studies have focused on proposing or comparing different weighting metrics at two-classes document level sentiment analysis, this study propose to analyse the results given by each metric in order to find out the characteristics of good and bad weighting metrics. Therefore we present an empirical study of fifteen global supervised weighting metrics with four local weighting metrics adopted from information retrieval, we also give an analysis to understand the behavior of each metric by observing and analysing how each metric distributes the terms and deduce some characteristics which may distinguish the good and bad metrics. The evaluation has been done using Support Vector Machine on three different datasets: Twitter, restaurant and laptop reviews. |
| Tasks | Information Retrieval, Sentiment Analysis, Text Classification |
| Published | 2016-10-10 |
| URL | http://arxiv.org/abs/1610.03106v1 |
| http://arxiv.org/pdf/1610.03106v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-term-weighting-metrics-for |
| Repo | |
| Framework | |
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
| Title | Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery |
| Authors | Yexiang Xue, Junwen Bai, Ronan Le Bras, Brendan Rappazzo, Richard Bernstein, Johan Bjorck, Liane Longpre, Santosh K. Suram, Robert B. van Dover, John Gregoire, Carla P. Gomes |
| Abstract | High-Throughput materials discovery involves the rapid synthesis, measurement, and characterization of many different but structurally-related materials. A key problem in materials discovery, the phase map identification problem, involves the determination of the crystal phase diagram from the materials’ composition and structural characterization data. We present Phase-Mapper, a novel AI platform to solve the phase map identification problem that allows humans to interact with both the data and products of AI algorithms, including the incorporation of human feedback to constrain or initialize solutions. Phase-Mapper affords incorporation of any spectral demixing algorithm, including our novel solver, AgileFD, which is based on a convolutive non-negative matrix factorization algorithm. AgileFD can incorporate constraints to capture the physics of the materials as well as human feedback. We compare three solver variants with previously proposed methods in a large-scale experiment involving 20 synthetic systems, demonstrating the efficacy of imposing physical constrains using AgileFD. Phase-Mapper has also been used by materials scientists to solve a wide variety of phase diagrams, including the previously unsolved Nb-Mn-V oxide system, which is provided here as an illustrative example. |
| Tasks | |
| Published | 2016-10-03 |
| URL | http://arxiv.org/abs/1610.00689v2 |
| http://arxiv.org/pdf/1610.00689v2.pdf | |
| PWC | https://paperswithcode.com/paper/phase-mapper-an-ai-platform-to-accelerate |
| Repo | |
| Framework | |
Structured illumination microscopy with unknown patterns and a statistical prior
| Title | Structured illumination microscopy with unknown patterns and a statistical prior |
| Authors | Li-Hao Yeh, Lei Tian, Laura Waller |
| Abstract | Structured illumination microscopy (SIM) improves resolution by down-modulating high-frequency information of an object to fit within the passband of the optical system. Generally, the reconstruction process requires prior knowledge of the illumination patterns, which implies a well-calibrated and aberration-free system. Here, we propose a new \textit{algorithmic self-calibration} strategy for SIM that does not need to know the exact patterns {\it a priori}, but only their covariance. The algorithm, termed PE-SIMS, includes a Pattern-Estimation (PE) step requiring the uniformity of the sum of the illumination patterns and a SIM reconstruction procedure using a Statistical prior (SIMS). Additionally, we perform a pixel reassignment process (SIMS-PR) to enhance the reconstruction quality. We achieve 2$\times$ better resolution than a conventional widefield microscope, while remaining insensitive to aberration-induced pattern distortion and robust against parameter tuning. |
| Tasks | Calibration |
| Published | 2016-10-26 |
| URL | http://arxiv.org/abs/1611.00287v2 |
| http://arxiv.org/pdf/1611.00287v2.pdf | |
| PWC | https://paperswithcode.com/paper/structured-illumination-microscopy-with |
| Repo | |
| Framework | |
Color Homography
| Title | Color Homography |
| Authors | Graham D. Finlayson, Han Gong, Robert B. Fisher |
| Abstract | We show the surprising result that colors across a change in viewing condition (changing light color, shading and camera) are related by a homography. Our homography color correction application delivers improved color fidelity compared with the linear least-square. |
| Tasks | |
| Published | 2016-05-13 |
| URL | http://arxiv.org/abs/1605.04250v2 |
| http://arxiv.org/pdf/1605.04250v2.pdf | |
| PWC | https://paperswithcode.com/paper/color-homography |
| Repo | |
| Framework | |
A novel and effective scoring scheme for structure classification and pairwise similarity measurement
| Title | A novel and effective scoring scheme for structure classification and pairwise similarity measurement |
| Authors | Rezaul Karim, Md. Momin Al Aziz, Swakkhar Shatabda, M. Sohel Rahman |
| Abstract | Protein tertiary structure defines its functions, classification and binding sites. Similar structural characteristics between two proteins often lead to the similar characteristics thereof. Determining structural similarity accurately in real time is a crucial research issue. In this paper, we present a novel and effective scoring scheme that is dependent on novel features extracted from protein alpha carbon distance matrices. Our scoring scheme is inspired from pattern recognition and computer vision. Our method is significantly better than the current state of the art methods in terms of family match of pairs of protein structures and other statistical measurements. The effectiveness of our method is tested on standard benchmark structures. A web service is available at http://research.buet.ac.bd:8080/Comograd/score.html where you can get the similarity measurement score between two protein structures based on our method. |
| Tasks | |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.01052v1 |
| http://arxiv.org/pdf/1610.01052v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-and-effective-scoring-scheme-for |
| Repo | |
| Framework | |
Entity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning
| Title | Entity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning |
| Authors | Shoaib Jameel, Steven Schockaert |
| Abstract | Conceptual spaces are geometric representations of conceptual knowledge, in which entities correspond to points, natural properties correspond to convex regions, and the dimensions of the space correspond to salient features. While conceptual spaces enable elegant models of various cognitive phenomena, the lack of automated methods for constructing such representations have so far limited their application in artificial intelligence. To address this issue, we propose a method which learns a vector-space embedding of entities from Wikipedia and constrains this embedding such that entities of the same semantic type are located in some lower-dimensional subspace. We experimentally demonstrate the usefulness of these subspaces as (approximate) conceptual space representations by showing, among others, that important features can be modelled as directions and that natural properties tend to correspond to convex regions. |
| Tasks | Entity Embeddings |
| Published | 2016-02-18 |
| URL | http://arxiv.org/abs/1602.05765v2 |
| http://arxiv.org/pdf/1602.05765v2.pdf | |
| PWC | https://paperswithcode.com/paper/entity-embeddings-with-conceptual-subspaces |
| Repo | |
| Framework | |
Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks
| Title | Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks |
| Authors | Matthew Francis-Landau, Greg Durrett, Dan Klein |
| Abstract | A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention’s context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to achieve state-of-the-art performance on multiple entity linking datasets, outperforming the prior systems of Durrett and Klein (2014) and Nguyen et al. (2014). |
| Tasks | Entity Linking, Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-04-04 |
| URL | http://arxiv.org/abs/1604.00734v1 |
| http://arxiv.org/pdf/1604.00734v1.pdf | |
| PWC | https://paperswithcode.com/paper/capturing-semantic-similarity-for-entity |
| Repo | |
| Framework | |
Online Active Linear Regression via Thresholding
| Title | Online Active Linear Regression via Thresholding |
| Authors | Carlos Riquelme, Ramesh Johari, Baosen Zhang |
| Abstract | We consider the problem of online active learning to collect data for regression modeling. Specifically, we consider a decision maker with a limited experimentation budget who must efficiently learn an underlying linear population model. Our main contribution is a novel threshold-based algorithm for selection of most informative observations; we characterize its performance and fundamental lower bounds. We extend the algorithm and its guarantees to sparse linear regression in high-dimensional settings. Simulations suggest the algorithm is remarkably robust: it provides significant benefits over passive random sampling in real-world datasets that exhibit high nonlinearity and high dimensionality — significantly reducing both the mean and variance of the squared error. |
| Tasks | Active Learning |
| Published | 2016-02-09 |
| URL | http://arxiv.org/abs/1602.02845v4 |
| http://arxiv.org/pdf/1602.02845v4.pdf | |
| PWC | https://paperswithcode.com/paper/online-active-linear-regression-via |
| Repo | |
| Framework | |
An Argument-based Creative Assistant for Harmonic Blending
| Title | An Argument-based Creative Assistant for Harmonic Blending |
| Authors | Maximos Kaliakatsos-Papakostas, Roberto Confalonieri, Joseph Corneli, Asterios Zacharakis, Emilios Cambouropoulos |
| Abstract | Conceptual blending is a powerful tool for computational creativity where, for example, the properties of two harmonic spaces may be combined in a consistent manner to produce a novel harmonic space. However, deciding about the importance of property features in the input spaces and evaluating the results of conceptual blending is a nontrivial task. In the specific case of musical harmony, defining the salient features of chord transitions and evaluating invented harmonic spaces requires deep musicological background knowledge. In this paper, we propose a creative tool that helps musicologists to evaluate and to enhance harmonic innovation. This tool allows a music expert to specify arguments over given transition properties. These arguments are then considered by the system when defining combinations of features in an idiom-blending process. A music expert can assess whether the new harmonic idiom makes musicological sense and re-adjust the arguments (selection of features) to explore alternative blends that can potentially produce better harmonic spaces. We conclude with a discussion of future work that would further automate the harmonisation process. |
| Tasks | |
| Published | 2016-03-06 |
| URL | http://arxiv.org/abs/1603.01770v1 |
| http://arxiv.org/pdf/1603.01770v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-argument-based-creative-assistant-for |
| Repo | |
| Framework | |
Incremental Parsing with Minimal Features Using Bi-Directional LSTM
| Title | Incremental Parsing with Minimal Features Using Bi-Directional LSTM |
| Authors | James Cross, Liang Huang |
| Abstract | Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting important global context. To further reduce feature engineering to the bare minimum, we use bi-directional LSTM sentence representations to model a parser state with only three sentence positions, which automatically identifies important aspects of the entire sentence. This model achieves state-of-the-art results among greedy dependency parsers for English. We also introduce a novel transition system for constituency parsing which does not require binarization, and together with the above architecture, achieves state-of-the-art results among greedy parsers for both English and Chinese. |
| Tasks | Constituency Parsing, Feature Engineering |
| Published | 2016-06-21 |
| URL | http://arxiv.org/abs/1606.06406v1 |
| http://arxiv.org/pdf/1606.06406v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-parsing-with-minimal-features |
| Repo | |
| Framework | |
Fusion of Range and Thermal Images for Person Detection
| Title | Fusion of Range and Thermal Images for Person Detection |
| Authors | Wim Abbeloos, Toon Goedemé |
| Abstract | Detecting people in images is a challenging problem. Differences in pose, clothing and lighting, along with other factors, cause a lot of variation in their appearance. To overcome these issues, we propose a system based on fused range and thermal infrared images. These measurements show considerably less variation and provide more meaningful information. We provide a brief introduction to the sensor technology used and propose a calibration method. Several data fusion algorithms are compared and their performance is assessed on a simulated data set. The results of initial experiments on real data are analyzed and the measurement errors and the challenges they present are discussed. The resulting fused data are used to efficiently detect people in a fixed camera set-up. The system is extended to include person tracking. |
| Tasks | Calibration, Human Detection |
| Published | 2016-12-07 |
| URL | http://arxiv.org/abs/1612.02183v1 |
| http://arxiv.org/pdf/1612.02183v1.pdf | |
| PWC | https://paperswithcode.com/paper/fusion-of-range-and-thermal-images-for-person |
| Repo | |
| Framework | |
