May 5, 2019

2865 words 14 mins read

Paper Group ANR 532

Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning. Log-Normal Matrix Completion for Large Scale Link Prediction. Simple Question Answering by Attentive Convolutional Neural Network. Siamese convolutional networks based on phonetic features for cognate identification. Near-Infrared Coloring via a Cont …

Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning


Title	Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
Authors	Amirhossein Tavanaei, Anthony S. Maida
Abstract	Hierarchical feature discovery using non-spiking convolutional neural networks (CNNs) has attracted much recent interest in machine learning and computer vision. However, it is still not well understood how to create a biologically plausible network of brain-like, spiking neurons with multi-layer, unsupervised learning. This paper explores a novel bio-inspired spiking CNN that is trained in a greedy, layer-wise fashion. The proposed network consists of a spiking convolutional-pooling layer followed by a feature discovery layer extracting independent visual features. Kernels for the convolutional layer are trained using local learning. The learning is implemented using a sparse, spiking auto-encoder representing primary visual features. The feature discovery layer extracts independent features by probabilistic, leaky integrate-and-fire (LIF) neurons that are sparsely active in response to stimuli. The layer of the probabilistic, LIF neurons implicitly provides lateral inhibitions to extract sparse and independent features. Experimental results show that the convolutional layer is stack-admissible, enabling it to support a multi-layer learning. The visual features obtained from the proposed probabilistic LIF neurons in the feature discovery layer are utilized for training a classifier. Classification results contribute to the independent and informative visual features extracted in a hierarchy of convolutional and feature discovery layers. The proposed model is evaluated on the MNIST digit dataset using clean and noisy images. The recognition performance for clean images is above 98%. The performance loss for recognizing the noisy images is in the range 0.1% to 8.5% depending on noise types and densities. This level of performance loss indicates that the network is robust to additive noise.
Tasks
Published	2016-11-09
URL	http://arxiv.org/abs/1611.03000v4
PDF	http://arxiv.org/pdf/1611.03000v4.pdf
PWC	https://paperswithcode.com/paper/bio-inspired-spiking-convolutional-neural
Repo
Framework

Log-Normal Matrix Completion for Large Scale Link Prediction


Title	Log-Normal Matrix Completion for Large Scale Link Prediction
Authors	Brian Mohtashemi, Thomas Ketseoglou
Abstract	The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node friendship information, and the availability of parallel computer architectures for rapid matrix processing. Current Link Prediction literature has demonstrated vast performance improvement through the utilization of sparsity in addition to the low rank matrix assumption. However, the majority of research has introduced sparsity through the limited L1 or Frobenius norms, instead of considering the more detailed distributions which led to the graph formation and relationship evolution. In particular, social networks have been found to express either Pareto, or more recently discovered, Log Normal distributions. Employing the convexity-inducing Lovasz Extension, we demonstrate how incorporating specific degree distribution information can lead to large scale improvements in Matrix Completion based Link prediction. We introduce Log-Normal Matrix Completion (LNMC), and solve the complex optimization problem by employing Alternating Direction Method of Multipliers. Using data from three popular social networks, our experiments yield up to 5% AUC increase over top-performing non-structured sparsity based methods.
Tasks	Link Prediction, Matrix Completion
Published	2016-01-28
URL	http://arxiv.org/abs/1601.07714v1
PDF	http://arxiv.org/pdf/1601.07714v1.pdf
PWC	https://paperswithcode.com/paper/log-normal-matrix-completion-for-large-scale
Repo
Framework

Simple Question Answering by Attentive Convolutional Neural Network


Title	Simple Question Answering by Attentive Convolutional Neural Network
Authors	Wenpeng Yin, Mo Yu, Bing Xiang, Bowen Zhou, Hinrich Schütze
Abstract	This work focuses on answering single-relation factoid questions over Freebase. Each question can acquire the answer from a single fact of form (subject, predicate, object) in Freebase. This task, simple question answering (SimpleQA), can be addressed via a two-step pipeline: entity linking and fact selection. In fact selection, we match the subject entity in a fact candidate with the entity mention in the question by a character-level convolutional neural network (char-CNN), and match the predicate in that fact with the question by a word-level CNN (word-CNN). This work makes two main contributions. (i) A simple and effective entity linker over Freebase is proposed. Our entity linker outperforms the state-of-the-art entity linker over SimpleQA task. (ii) A novel attentive maxpooling is stacked over word-CNN, so that the predicate representation can be matched with the predicate-focused question representation more effectively. Experiments show that our system sets new state-of-the-art in this task.
Tasks	Entity Linking, Question Answering
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03391v2
PDF	http://arxiv.org/pdf/1606.03391v2.pdf
PWC	https://paperswithcode.com/paper/simple-question-answering-by-attentive
Repo
Framework

Siamese convolutional networks based on phonetic features for cognate identification


Title	Siamese convolutional networks based on phonetic features for cognate identification
Authors	Taraka Rama
Abstract	In this paper, we explore the use of convolutional networks (ConvNets) for the purpose of cognate identification. We compare our architecture with binary classifiers based on string similarity measures on different language families. Our experiments show that convolutional networks achieve competitive results across concepts and across language families at the task of cognate identification.
Tasks
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05172v2
PDF	http://arxiv.org/pdf/1605.05172v2.pdf
PWC	https://paperswithcode.com/paper/siamese-convolutional-networks-based-on
Repo
Framework

Near-Infrared Coloring via a Contrast-Preserving Mapping Model


Title	Near-Infrared Coloring via a Contrast-Preserving Mapping Model
Authors	Chang-Hwan Son, Xiao-Ping Zhang
Abstract	Near-infrared gray images captured together with corresponding visible color images have recently proven useful for image restoration and classification. This paper introduces a new coloring method to add colors to near-infrared gray images based on a contrast-preserving mapping model. A naive coloring method directly adds the colors from the visible color image to the near-infrared gray image; however, this method results in an unrealistic image because of the discrepancies in brightness and image structure between the captured near-infrared gray image and the visible color image. To solve the discrepancy problem, first we present a new contrast-preserving mapping model to create a new near-infrared gray image with a similar appearance in the luminance plane to the visible color image, while preserving the contrast and details of the captured near-infrared gray image. Then based on the proposed contrast-preserving mapping model, we develop a method to derive realistic colors that can be added to the newly created near-infrared gray image. Experimental results show that the proposed method can not only preserve the local contrasts and details of the captured near-infrared gray image, but transfers the realistic colors from the visible color image to the newly created near-infrared gray image. Experimental results also show that the proposed approach can be applied to near-infrared denoising.
Tasks	Denoising, Image Restoration
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00382v1
PDF	http://arxiv.org/pdf/1610.00382v1.pdf
PWC	https://paperswithcode.com/paper/near-infrared-coloring-via-a-contrast
Repo
Framework

Pathway Lasso: Estimate and Select Sparse Mediation Pathways with High Dimensional Mediators


Title	Pathway Lasso: Estimate and Select Sparse Mediation Pathways with High Dimensional Mediators
Authors	Yi Zhao, Xi Luo
Abstract	In many scientific studies, it becomes increasingly important to delineate the causal pathways through a large number of mediators, such as genetic and brain mediators. Structural equation modeling (SEM) is a popular technique to estimate the pathway effects, commonly expressed as products of coefficients. However, it becomes unstable to fit such models with high dimensional mediators, especially for a general setting where all the mediators are causally dependent but the exact causal relationships between them are unknown. This paper proposes a sparse mediation model using a regularized SEM approach, where sparsity here means that a small number of mediators have nonzero mediation effects between a treatment and an outcome. To address the model selection challenge, we innovate by introducing a new penalty called Pathway Lasso. This penalty function is a convex relaxation of the non-convex product function, and it enables a computationally tractable optimization criterion to estimate and select many pathway effects simultaneously. We develop a fast ADMM-type algorithm to compute the model parameters, and we show that the iterative updates can be expressed in closed form. On both simulated data and a real fMRI dataset, the proposed approach yields higher pathway selection accuracy and lower estimation bias than other competing methods.
Tasks	Model Selection
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07749v1
PDF	http://arxiv.org/pdf/1603.07749v1.pdf
PWC	https://paperswithcode.com/paper/pathway-lasso-estimate-and-select-sparse
Repo
Framework

Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach


Title	Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach
Authors	Jianbo Yuan, Walid Shalaby, Mohammed Korayem, David Lin, Khalifeh AlJadda, Jiebo Luo
Abstract	Collaborative Filtering (CF) is widely used in large-scale recommendation engines because of its efficiency, accuracy and scalability. However, in practice, the fact that recommendation engines based on CF require interactions between users and items before making recommendations, make it inappropriate for new items which haven’t been exposed to the end users to interact with. This is known as the cold-start problem. In this paper we introduce a novel approach which employs deep learning to tackle this problem in any CF based recommendation engine. One of the most important features of the proposed technique is the fact that it can be applied on top of any existing CF based recommendation engine without changing the CF core. We successfully applied this technique to overcome the item cold-start problem in Careerbuilder’s CF based recommendation engine. Our experiments show that the proposed technique is very efficient to resolve the cold-start problem while maintaining high accuracy of the CF recommendations.
Tasks
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05480v1
PDF	http://arxiv.org/pdf/1611.05480v1.pdf
PWC	https://paperswithcode.com/paper/solving-cold-start-problem-in-large-scale
Repo
Framework

As Cool as a Cucumber: Towards a Corpus of Contemporary Similes in Serbian


Title	As Cool as a Cucumber: Towards a Corpus of Contemporary Similes in Serbian
Authors	Nikola Milosevic, Goran Nenadic
Abstract	Similes are natural language expressions used to compare unlikely things, where the comparison is not taken literally. They are often used in everyday communication and are an important part of cultural heritage. Having an up-to-date corpus of similes is challenging, as they are constantly coined and/or adapted to the contemporary times. In this paper we present a methodology for semi-automated collection of similes from the world wide web using text mining techniques. We expanded an existing corpus of traditional similes (containing 333 similes) by collecting 446 additional expressions. We, also, explore how crowdsourcing can be used to extract and curate new similes.
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06319v1
PDF	http://arxiv.org/pdf/1605.06319v1.pdf
PWC	https://paperswithcode.com/paper/as-cool-as-a-cucumber-towards-a-corpus-of
Repo
Framework

DPPred: An Effective Prediction Framework with Concise Discriminative Patterns


Title	DPPred: An Effective Prediction Framework with Concise Discriminative Patterns
Authors	Jingbo Shang, Meng Jiang, Wenzhu Tong, Jinfeng Xiao, Jian Peng, Jiawei Han
Abstract	In the literature, two series of models have been proposed to address prediction problems including classification and regression. Simple models, such as generalized linear models, have ordinary performance but strong interpretability on a set of simple features. The other series, including tree-based models, organize numerical, categorical and high dimensional features into a comprehensive structure with rich interpretable information in the data. In this paper, we propose a novel Discriminative Pattern-based Prediction framework (DPPred) to accomplish the prediction tasks by taking their advantages of both effectiveness and interpretability. Specifically, DPPred adopts the concise discriminative patterns that are on the prefix paths from the root to leaf nodes in the tree-based models. DPPred selects a limited number of the useful discriminative patterns by searching for the most effective pattern combination to fit generalized linear models. Extensive experiments show that in many scenarios, DPPred provides competitive accuracy with the state-of-the-art as well as the valuable interpretability for developers and experts. In particular, taking a clinical application dataset as a case study, our DPPred outperforms the baselines by using only 40 concise discriminative patterns out of a potentially exponentially large set of patterns.
Tasks
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09778v1
PDF	http://arxiv.org/pdf/1610.09778v1.pdf
PWC	https://paperswithcode.com/paper/dppred-an-effective-prediction-framework-with
Repo
Framework

Latent Contextual Bandits and their Application to Personalized Recommendations for New Users


Title	Latent Contextual Bandits and their Application to Personalized Recommendations for New Users
Authors	Li Zhou, Emma Brunskill
Abstract	Personalized recommendations for new users, also known as the cold-start problem, can be formulated as a contextual bandit problem. Existing contextual bandit algorithms generally rely on features alone to capture user variability. Such methods are inefficient in learning new users’ interests. In this paper we propose Latent Contextual Bandits. We consider both the benefit of leveraging a set of learned latent user classes for new users, and how we can learn such latent classes from prior users. We show that our approach achieves a better regret bound than existing algorithms. We also demonstrate the benefit of our approach using a large real world dataset and a preliminary user study.
Tasks	Multi-Armed Bandits
Published	2016-04-22
URL	http://arxiv.org/abs/1604.06743v1
PDF	http://arxiv.org/pdf/1604.06743v1.pdf
PWC	https://paperswithcode.com/paper/latent-contextual-bandits-and-their
Repo
Framework

Evolving Boolean Regulatory Networks with Variable Gene Expression Times


Title	Evolving Boolean Regulatory Networks with Variable Gene Expression Times
Authors	Larry Bull
Abstract	The time taken for gene expression varies not least because proteins vary in length considerably. This paper uses an abstract, tuneable Boolean regulatory network model to explore gene expression time variation. In particular, it is shown how non-uniform expression times can emerge under certain conditions through simulated evolution. That is, gene expression time variance appears beneficial in the shaping of the dynamical behaviour of the regulatory network without explicit consideration of protein function.
Tasks
Published	2016-03-02
URL	http://arxiv.org/abs/1603.01185v2
PDF	http://arxiv.org/pdf/1603.01185v2.pdf
PWC	https://paperswithcode.com/paper/evolving-boolean-regulatory-networks-with-1
Repo
Framework

A Compositional Object-Based Approach to Learning Physical Dynamics


Title	A Compositional Object-Based Approach to Learning Physical Dynamics
Authors	Michael B. Chang, Tomer Ullman, Antonio Torralba, Joshua B. Tenenbaum
Abstract	We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt to specific object properties and dynamics of different worlds. We evaluate the efficacy of our approach on simple rigid body dynamics in two-dimensional worlds. By comparing to less structured architectures, we show that the NPE’s compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00341v2
PDF	http://arxiv.org/pdf/1612.00341v2.pdf
PWC	https://paperswithcode.com/paper/a-compositional-object-based-approach-to
Repo
Framework

Automatic Quality Assessment for Speech Translation Using Joint ASR and MT Features


Title	Automatic Quality Assessment for Speech Translation Using Joint ASR and MT Features
Authors	Ngoc-Tien Le, Benjamin Lecouteux, Laurent Besacier
Abstract	This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad according to a large feature set. We propose several word confidence estimators (WCE) based on our automatic evaluation of transcription (ASR) quality, translation (MT) quality, or both (combined ASR+MT). This research work is possible because we built a specific corpus which contains 6.7k utterances for which a quintuplet containing: ASR output, verbatim transcript, text translation, speech translation and post-edition of translation is built. The conclusion of our multiple experiments using joint ASR and MT features for WCE is that MT features remain the most influent while ASR feature can bring interesting complementary information. Our robust quality estimators for SLT can be used for re-scoring speech translation graphs or for providing feedback to the user in interactive speech translation or computer-assisted speech-to-text scenarios.
Tasks
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06049v1
PDF	http://arxiv.org/pdf/1609.06049v1.pdf
PWC	https://paperswithcode.com/paper/automatic-quality-assessment-for-speech
Repo
Framework

Intrinsic Subspace Evaluation of Word Embedding Representations


Title	Intrinsic Subspace Evaluation of Word Embedding Representations
Authors	Yadollah Yaghoobzadeh, Hinrich Schütze
Abstract	We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose difficulties to NLP systems; and develop tests that directly show whether or not representations contain the subspaces necessary to satisfy these criteria. Current intrinsic evaluations are mostly based on the overall similarity or full-space similarity of words and thus view vector representations as points. We show the limits of these point-based intrinsic evaluations. We apply our evaluation methodology to the comparison of a count vector model and several neural network models and demonstrate important properties of these models.
Tasks
Published	2016-06-25
URL	http://arxiv.org/abs/1606.07902v1
PDF	http://arxiv.org/pdf/1606.07902v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-subspace-evaluation-of-word
Repo
Framework

A Vector Space for Distributional Semantics for Entailment


Title	A Vector Space for Distributional Semantics for Entailment
Authors	James Henderson, Diana Nicoleta Popa
Abstract	Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation for a distributional semantics of entailment. Using a mean-field approximation, we develop approximate inference procedures and entailment operators over vectors of probabilities of features being known (versus unknown). We use this framework to reinterpret an existing distributional-semantic model (Word2Vec) as approximating an entailment-based model of the distributions of words in contexts, thereby predicting lexical entailment relations. In both unsupervised and semi-supervised experiments on hyponymy detection, we get substantial improvements over previous results.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03780v1
PDF	http://arxiv.org/pdf/1607.03780v1.pdf
PWC	https://paperswithcode.com/paper/a-vector-space-for-distributional-semantics
Repo
Framework