May 7, 2019

2762 words 13 mins read

Paper Group ANR 39

Bayesian Nonparametric Models for Synchronous Brain-Computer Interfaces. Regularization for Unsupervised Deep Neural Nets. Recurrent Exponential-Family Harmoniums without Backprop-Through-Time. Unsupervised Clustering of Commercial Domains for Adaptive Machine Translation. Reliable Attribute-Based Object Recognition Using High Predictive Value Clas …

Bayesian Nonparametric Models for Synchronous Brain-Computer Interfaces


Title	Bayesian Nonparametric Models for Synchronous Brain-Computer Interfaces
Authors	Jaime Fernando Delgado Saa, Mujdat Cetin
Abstract	A brain-computer interface (BCI) is a system that aims for establishing a non-muscular communication path for subjects who had suffer from a neurodegenerative disease. Many BCI systems make use of the phenomena of event-related synchronization and de-synchronization of brain waves as a main feature for classification of different cognitive tasks. However, the temporal dynamics of the electroencephalographic (EEG) signals contain additional information that can be incorporated into the inference engine in order to improve the performance of the BCIs. This information about the dynamics of the signals have been exploited previously in BCIs by means of generative and discriminative methods. In particular, hidden Markov models (HMMs) have been used in previous works. These methods have the disadvantage that the model parameters such as the number of hidden states and the number of Gaussian mixtures need to be fix “a priori”. In this work, we propose a Bayesian nonparametric model for brain signal classification that does not require “a priori” selection of the number of hidden states and the number of Gaussian mixtures of a HMM. The results show that the proposed model outperform other methods based on HMM as well as the winner algorithm of the BCI competition IV.
Tasks	EEG
Published	2016-12-27
URL	http://arxiv.org/abs/1612.08642v1
PDF	http://arxiv.org/pdf/1612.08642v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-nonparametric-models-for-synchronous
Repo
Framework

Regularization for Unsupervised Deep Neural Nets


Title	Regularization for Unsupervised Deep Neural Nets
Authors	Baiyang Wang, Diego Klabjan
Abstract	Unsupervised neural networks, such as restricted Boltzmann machines (RBMs) and deep belief networks (DBNs), are powerful tools for feature selection and pattern recognition tasks. We demonstrate that overfitting occurs in such models just as in deep feedforward neural networks, and discuss possible regularization methods to reduce overfitting. We also propose a “partial” approach to improve the efficiency of Dropout/DropConnect in this scenario, and discuss the theoretical justification of these methods from model convergence and likelihood bounds. Finally, we compare the performance of these methods based on their likelihood and classification error rates for various pattern recognition data sets.
Tasks	Feature Selection
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04426v4
PDF	http://arxiv.org/pdf/1608.04426v4.pdf
PWC	https://paperswithcode.com/paper/regularization-for-unsupervised-deep-neural
Repo
Framework

Recurrent Exponential-Family Harmoniums without Backprop-Through-Time


Title	Recurrent Exponential-Family Harmoniums without Backprop-Through-Time
Authors	Joseph G. Makin, Benjamin K. Dichter, Philip N. Sabes
Abstract	Exponential-family harmoniums (EFHs), which extend restricted Boltzmann machines (RBMs) from Bernoulli random variables to other exponential families (Welling et al., 2005), are generative models that can be trained with unsupervised-learning techniques, like contrastive divergence (Hinton et al. 2006; Hinton, 2002), as density estimators for static data. Methods for extending RBMs–and likewise EFHs–to data with temporal dependencies have been proposed previously (Sutskever and Hinton, 2007; Sutskever et al., 2009), the learning procedure being validated by qualitative assessment of the generative model. Here we propose and justify, from a very different perspective, an alternative training procedure, proving sufficient conditions for optimal inference under that procedure. The resulting algorithm can be learned with only forward passes through the data–backprop-through-time is not required, as in previous approaches. The proof exploits a recent result about information retention in density estimators (Makin and Sabes, 2015), and applies it to a “recurrent EFH” (rEFH) by induction. Finally, we demonstrate optimality by simulation, testing the rEFH: (1) as a filter on training data generated with a linear dynamical system, the position of which is noisily reported by a population of “neurons” with Poisson-distributed spike counts; and (2) with the qualitative experiments proposed by Sutskever et al. (2009).
Tasks
Published	2016-05-19
URL	http://arxiv.org/abs/1605.05799v1
PDF	http://arxiv.org/pdf/1605.05799v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-exponential-family-harmoniums
Repo
Framework

Unsupervised Clustering of Commercial Domains for Adaptive Machine Translation


Title	Unsupervised Clustering of Commercial Domains for Adaptive Machine Translation
Authors	Mauro Cettolo, Mara Chinea Rios, Roldano Cattoni
Abstract	In this paper, we report on domain clustering in the ambit of an adaptive MT architecture. A standard bottom-up hierarchical clustering algorithm has been instantiated with five different distances, which have been compared, on an MT benchmark built on 40 commercial domains, in terms of dendrograms, intrinsic and extrinsic evaluations. The main outcome is that the most expensive distance is also the only one able to allow the MT engine to guarantee good performance even with few, but highly populated clusters of domains.
Tasks	Machine Translation
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04683v1
PDF	http://arxiv.org/pdf/1612.04683v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-clustering-of-commercial-domains
Repo
Framework

Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers


Title	Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers
Authors	Wentao Luan, Yezhou Yang, Cornelia Fermuller, John Baras
Abstract	We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented for recognition from point-cloud data. First, the viewing conditions can have a strong influence on classification performance. We study the impact of the distance between the camera and the object and propose an approach to fuse multiple attribute classifiers, which incorporates distance into the decision making. Second, lack of representative training samples often makes it difficult to learn the optimal threshold value for best positive and negative detection rate. We address this issue, by setting in our attribute classifiers instead of just one threshold value, two threshold values to distinguish a positive, a negative and an uncertainty class, and we prove the theoretical correctness of this approach. Empirical studies demonstrate the effectiveness and feasibility of the proposed concepts.
Tasks	Decision Making, Object Recognition
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03619v2
PDF	http://arxiv.org/pdf/1609.03619v2.pdf
PWC	https://paperswithcode.com/paper/reliable-attribute-based-object-recognition
Repo
Framework

Term-Class-Max-Support (TCMS): A Simple Text Document Categorization Approach Using Term-Class Relevance Measure


Title	Term-Class-Max-Support (TCMS): A Simple Text Document Categorization Approach Using Term-Class Relevance Measure
Authors	D S Guru, Mahamad Suhil
Abstract	In this paper, a simple text categorization method using term-class relevance measures is proposed. Initially, text documents are processed to extract significant terms present in them. For every term extracted from a document, we compute its importance in preserving the content of a class through a novel term-weighting scheme known as Term_Class Relevance (TCR) measure proposed by Guru and Suhil (2015) [1]. In this way, for every term, its relevance for all the classes present in the corpus is computed and stored in the knowledgebase. During testing, the terms present in the test document are extracted and the term-class relevance of each term is obtained from the stored knowledgebase. To achieve quick search of term weights, Btree indexing data structure has been adapted. Finally, the class which receives maximum support in terms of term-class relevance is decided to be the class of the given test document. The proposed method works in logarithmic complexity in testing time and simple to implement when compared to any other text categorization techniques available in literature. The experiments conducted on various benchmarking datasets have revealed that the performance of the proposed method is satisfactory and encouraging.
Tasks	Text Categorization
Published	2016-10-16
URL	http://arxiv.org/abs/1610.04814v1
PDF	http://arxiv.org/pdf/1610.04814v1.pdf
PWC	https://paperswithcode.com/paper/term-class-max-support-tcms-a-simple-text
Repo
Framework

Content Based Image Retrieval (CBIR) in Remote Clinical Diagnosis and Healthcare


Title	Content Based Image Retrieval (CBIR) in Remote Clinical Diagnosis and Healthcare
Authors	Albany E. Herrmann, Vania Vieira Estrela
Abstract	Content-Based Image Retrieval (CBIR) locates, retrieves and displays images alike to one given as a query, using a set of features. It demands accessible data in medical archives and from medical equipment, to infer meaning after some processing. A problem similar in some sense to the target image can aid clinicians. CBIR complements text-based retrieval and improves evidence-based diagnosis, administration, teaching, and research in healthcare. It facilitates visual/automatic diagnosis and decision-making in real-time remote consultation/screening, store-and-forward tests, home care assistance and overall patient surveillance. Metrics help comparing visual data and improve diagnostic. Specially designed architectures can benefit from the application scenario. CBIR use calls for file storage standardization, querying procedures, efficient image transmission, realistic databases, global availability, access simplicity, and Internet-based structures. This chapter recommends important and complex aspects required to handle visual content in healthcare.
Tasks	Content-Based Image Retrieval, Decision Making, Image Retrieval
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02902v1
PDF	http://arxiv.org/pdf/1610.02902v1.pdf
PWC	https://paperswithcode.com/paper/content-based-image-retrieval-cbir-in-remote
Repo
Framework


Title	Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
Authors	Hao Wang, Xingjian Shi, Dit-Yan Yeung
Abstract	Hybrid methods that utilize both content and rating information are commonly used in many recommender systems. However, most of them use either handcrafted features or the bag-of-words representation as a surrogate for the content information but they are neither effective nor natural enough. To address this problem, we develop a collaborative recurrent autoencoder (CRAE) which is a denoising recurrent autoencoder (DRAE) that models the generation of content sequences in the collaborative filtering (CF) setting. The model generalizes recent advances in recurrent deep learning from i.i.d. input to non-i.i.d. (CF-based) input and provides a new denoising scheme along with a novel learnable pooling scheme for the recurrent autoencoder. To do this, we first develop a hierarchical Bayesian model for the DRAE and then generalize it to the CF setting. The synergy between denoising and CF enables CRAE to make accurate recommendations while learning to fill in the blanks in sequences. Experiments on real-world datasets from different domains (CiteULike and Netflix) show that, by jointly modeling the order-aware generation of sequences for the content information and performing CF for the ratings, CRAE is able to significantly outperform the state of the art on both the recommendation task based on ratings and the sequence generation task based on content information.
Tasks	Denoising, Recommendation Systems
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00454v1
PDF	http://arxiv.org/pdf/1611.00454v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-recurrent-autoencoder-recommend
Repo
Framework

Transfer Learning via Latent Factor Modeling to Improve Prediction of Surgical Complications


Title	Transfer Learning via Latent Factor Modeling to Improve Prediction of Surgical Complications
Authors	Elizabeth C Lorenzi, Zhifei Sun, Erich Huang, Ricardo Henao, Katherine A Heller
Abstract	We aim to create a framework for transfer learning using latent factor models to learn the dependence structure between a larger source dataset and a target dataset. The methodology is motivated by our goal of building a risk-assessment model for surgery patients, using both institutional and national surgical outcomes data. The national surgical outcomes data is collected through NSQIP (National Surgery Quality Improvement Program), a database housing almost 4 million patients from over 700 different hospitals. We build a latent factor model with a hierarchical prior on the loadings matrix to appropriately account for the different covariance structure in our data. We extend this model to handle more complex relationships between the populations by deriving a scale mixture formulation using stick-breaking properties. Our model provides a transfer learning framework that utilizes all information from both the source and target data, while modeling the underlying inherent differences between them.
Tasks	Transfer Learning
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00555v1
PDF	http://arxiv.org/pdf/1612.00555v1.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-via-latent-factor-modeling
Repo
Framework

Embedding Projector: Interactive Visualization and Interpretation of Embeddings


Title	Embedding Projector: Interactive Visualization and Interpretation of Embeddings
Authors	Daniel Smilkov, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda B. Viégas, Martin Wattenberg
Abstract	Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive visualization and interpretation of embeddings.
Tasks	Recommendation Systems
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05469v1
PDF	http://arxiv.org/pdf/1611.05469v1.pdf
PWC	https://paperswithcode.com/paper/embedding-projector-interactive-visualization
Repo
Framework

Parallelizable sparse inverse formulation Gaussian processes (SpInGP)


Title	Parallelizable sparse inverse formulation Gaussian processes (SpInGP)
Authors	Alexander Grigorievskiy, Neil Lawrence, Simo Särkkä
Abstract	We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and because all the computations are parallelizable, the parallel form of the algorithm is sublinear in the number of data points. We provide example algorithms to implement the sparse matrix routines and experimentally test the method using both simulated and real data.
Tasks	Gaussian Processes
Published	2016-10-25
URL	http://arxiv.org/abs/1610.08035v4
PDF	http://arxiv.org/pdf/1610.08035v4.pdf
PWC	https://paperswithcode.com/paper/parallelizable-sparse-inverse-formulation
Repo
Framework

The Player Kernel: Learning Team Strengths Based on Implicit Player Contributions


Title	The Player Kernel: Learning Team Strengths Based on Implicit Player Contributions
Authors	Lucas Maystre, Victor Kristof, Antonio J. González Ferrer, Matthias Grossglauser
Abstract	In this work, we draw attention to a connection between skill-based models of game outcomes and Gaussian process classification models. The Gaussian process perspective enables a) a principled way of dealing with uncertainty and b) rich models, specified through kernel functions. Using this connection, we tackle the problem of predicting outcomes of football matches between national teams. We develop a player kernel that relates any two football matches through the players lined up on the field. This makes it possible to share knowledge gained from observing matches between clubs (available in large quantities) and matches between national teams (available only in limited quantities). We evaluate our approach on the Euro 2008, 2012 and 2016 final tournaments.
Tasks
Published	2016-09-05
URL	http://arxiv.org/abs/1609.01176v1
PDF	http://arxiv.org/pdf/1609.01176v1.pdf
PWC	https://paperswithcode.com/paper/the-player-kernel-learning-team-strengths
Repo
Framework

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation


Title	View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
Authors	Joel Z. Leibo, Qianli Liao, Winrich Freiwald, Fabio Anselmi, Tomaso Poggio
Abstract	The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and relatively robust against identity-preserving transformations like depth-rotations. Current computational models of object recognition, including recent deep learning networks, generate these properties through a hierarchy of alternating selectivity-increasing filtering and tolerance-increasing pooling operations, similar to simple-complex cells operations. While simulations of these models recapitulate the ventral stream’s progression from early view-specific to late view-tolerant representations, they fail to generate the most salient property of the intermediate representation for faces found in the brain: mirror-symmetric tuning of the neural population to head orientation. Here we prove that a class of hierarchical architectures and a broad set of biologically plausible learning rules can provide approximate invariance at the top level of the network. While most of the learning rules do not yield mirror-symmetry in the mid-level representations, we characterize a specific biologically-plausible Hebb-type learning rule that is guaranteed to generate mirror-symmetric tuning to faces tuning at intermediate levels of the architecture.
Tasks	Face Recognition, Object Recognition
Published	2016-06-05
URL	http://arxiv.org/abs/1606.01552v1
PDF	http://arxiv.org/pdf/1606.01552v1.pdf
PWC	https://paperswithcode.com/paper/view-tolerant-face-recognition-and-hebbian
Repo
Framework

Detecting Rainfall Onset Using Sky Images


Title	Detecting Rainfall Onset Using Sky Images
Authors	Soumyabrata Dev, Shilpa Manandhar, Yee Hui Lee, Stefan Winkler
Abstract	Ground-based sky cameras (popularly known as Whole Sky Imagers) are increasingly used now-a-days for continuous monitoring of the atmosphere. These imagers have higher temporal and spatial resolutions compared to conventional satellite images. In this paper, we use ground-based sky cameras to detect the onset of rainfall. These images contain additional information about cloud coverage and movement and are therefore useful for accurate rainfall nowcast. We validate our results using rain gauge measurement recordings and achieve an accuracy of 89% for correct detection of rainfall onset.
Tasks
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06667v1
PDF	http://arxiv.org/pdf/1610.06667v1.pdf
PWC	https://paperswithcode.com/paper/detecting-rainfall-onset-using-sky-images
Repo
Framework

Leveraging Union of Subspace Structure to Improve Constrained Clustering


Title	Leveraging Union of Subspace Structure to Improve Constrained Clustering
Authors	John Lipor, Laura Balzano
Abstract	Many clustering problems in computer vision and other contexts are also classification problems, where each cluster shares a meaningful label. Subspace clustering algorithms in particular are often applied to problems that fit this description, for example with face images or handwritten digits. While it is straightforward to request human input on these datasets, our goal is to reduce this input as much as possible. We present a pairwise-constrained clustering algorithm that actively selects queries based on the union-of-subspaces model. The central step of the algorithm is in querying points of minimum margin between estimated subspaces; analogous to classifier margin, these lie near the decision boundary. We prove that points lying near the intersection of subspaces are points with low margin. Our procedure can be used after any subspace clustering algorithm that outputs an affinity matrix. We demonstrate on several datasets that our algorithm drives the clustering error down considerably faster than the state-of-the-art active query algorithms on datasets with subspace structure and is competitive on other datasets.
Tasks
Published	2016-08-06
URL	http://arxiv.org/abs/1608.02146v2
PDF	http://arxiv.org/pdf/1608.02146v2.pdf
PWC	https://paperswithcode.com/paper/leveraging-union-of-subspace-structure-to
Repo
Framework