May 5, 2019

2651 words 13 mins read

Paper Group ANR 557

On the Semantic Relationship between Probabilistic Soft Logic and Markov Logic. Sampling Method for Fast Training of Support Vector Data Description. A Model of Virtual Carrier Immigration in Digital Images for Region Segmentation. The Symmetry of a Simple Optimization Problem in Lasso Screening. Kernel-based Generative Learning in Distortion Featu …

On the Semantic Relationship between Probabilistic Soft Logic and Markov Logic


Title	On the Semantic Relationship between Probabilistic Soft Logic and Markov Logic
Authors	Joohyung Lee, Yi Wang
Abstract	Markov Logic Networks (MLN) and Probabilistic Soft Logic (PSL) are widely applied formalisms in Statistical Relational Learning, an emerging area in Artificial Intelligence that is concerned with combining logical and statistical AI. Despite their resemblance, the relationship has not been formally stated. In this paper, we describe the precise semantic relationship between them from a logical perspective. This is facilitated by first extending fuzzy logic to allow weights, which can be also viewed as a generalization of PSL, and then relate that generalization to MLN. We observe that the relationship between PSL and MLN is analogous to the known relationship between fuzzy logic and Boolean logic, and furthermore the weight scheme of PSL is essentially a generalization of the weight scheme of MLN for the many-valued setting.
Tasks	Relational Reasoning
Published	2016-06-28
URL	http://arxiv.org/abs/1606.08896v1
PDF	http://arxiv.org/pdf/1606.08896v1.pdf
PWC	https://paperswithcode.com/paper/on-the-semantic-relationship-between
Repo
Framework

Sampling Method for Fast Training of Support Vector Data Description


Title	Sampling Method for Fast Training of Support Vector Data Description
Authors	Arin Chaudhuri, Deovrat Kakde, Maria Jahja, Wei Xiao, Hansi Jiang, Seunghyun Kong, Sergiy Peredriy
Abstract	Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD training. The method incrementally learns the training data description at each iteration by computing SVDD on an independent random sample selected with replacement from the training data set. The experimental results indicate that the proposed method is extremely fast and provides a good data description .
Tasks	Outlier Detection
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05382v3
PDF	http://arxiv.org/pdf/1606.05382v3.pdf
PWC	https://paperswithcode.com/paper/sampling-method-for-fast-training-of-support
Repo
Framework

A Model of Virtual Carrier Immigration in Digital Images for Region Segmentation


Title	A Model of Virtual Carrier Immigration in Digital Images for Region Segmentation
Authors	Xiaodong Zhuang, N. E. Mastorakis
Abstract	A novel model for image segmentation is proposed, which is inspired by the carrier immigration mechanism in physical P-N junction. The carrier diffusing and drifting are simulated in the proposed model, which imitates the physical self-balancing mechanism in P-N junction. The effect of virtual carrier immigration in digital images is analyzed and studied by experiments on test images and real world images. The sign distribution of net carrier at the model’s balance state is exploited for region segmentation. The experimental results for both test images and real-world images demonstrate self-adaptive and meaningful gathering of pixels to suitable regions, which prove the effectiveness of the proposed method for image region segmentation.
Tasks	Semantic Segmentation
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03614v1
PDF	http://arxiv.org/pdf/1610.03614v1.pdf
PWC	https://paperswithcode.com/paper/a-model-of-virtual-carrier-immigration-in
Repo
Framework

The Symmetry of a Simple Optimization Problem in Lasso Screening


Title	The Symmetry of a Simple Optimization Problem in Lasso Screening
Authors	Yun Wang, Peter J. Ramadge
Abstract	Recently dictionary screening has been proposed as an effective way to improve the computational efficiency of solving the lasso problem, which is one of the most commonly used method for learning sparse representations. To address today’s ever increasing large dataset, effective screening relies on a tight region bound on the solution to the dual lasso. Typical region bounds are in the form of an intersection of a sphere and multiple half spaces. One way to tighten the region bound is using more half spaces, which however, adds to the overhead of solving the high dimensional optimization problem in lasso screening. This paper reveals the interesting property that the optimization problem only depends on the projection of features onto the subspace spanned by the normals of the half spaces. This property converts an optimization problem in high dimension to much lower dimension, and thus sheds light on reducing the computation overhead of lasso screening based on tighter region bounds.
Tasks
Published	2016-08-21
URL	http://arxiv.org/abs/1608.06014v2
PDF	http://arxiv.org/pdf/1608.06014v2.pdf
PWC	https://paperswithcode.com/paper/the-symmetry-of-a-simple-optimization-problem
Repo
Framework

Kernel-based Generative Learning in Distortion Feature Space


Title	Kernel-based Generative Learning in Distortion Feature Space
Authors	Bo Tang, Paul M. Baggenstoss, Haibo He
Abstract	This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier. An iterative kernel selection algorithm is developed to steadily improve classification performance by repeatedly removing and adding kernels. The experimental results on character recognition application not only show that the proposed generative classifier performs better than many existing classifiers, but also illustrate that it has different recognition capability compared to the state-of-the-art discriminative classifier - deep belief network. The recognition diversity indicates that a hybrid combination of the proposed generative classifier and the discriminative classifier could further improve the classification performance. Two hybrid combination methods, cascading and stacking, have been implemented to verify the diversity and the improvement of the proposed classifier.
Tasks
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06377v1
PDF	http://arxiv.org/pdf/1606.06377v1.pdf
PWC	https://paperswithcode.com/paper/kernel-based-generative-learning-in
Repo
Framework

Diversity encouraged learning of unsupervised LSTM ensemble for neural activity video prediction


Title	Diversity encouraged learning of unsupervised LSTM ensemble for neural activity video prediction
Authors	Yilin Song, Jonathan Viventi, Yao Wang
Abstract	Being able to predict the neural signal in the near future from the current and previous observations has the potential to enable real-time responsive brain stimulation to suppress seizures. We have investigated how to use an auto-encoder model consisting of LSTM cells for such prediction. Recog- nizing that there exist multiple activity pattern clusters, we have further explored to train an ensemble of LSTM mod- els so that each model can specialize in modeling certain neural activities, without explicitly clustering the training data. We train the ensemble using an ensemble-awareness loss, which jointly solves the model assignment problem and the error minimization problem. During training, for each training sequence, only the model that has the lowest recon- struction and prediction error is updated. Intrinsically such a loss function enables each LTSM model to be adapted to a subset of the training sequences that share similar dynamic behavior. We demonstrate this can be trained in an end- to-end manner and achieve significant accuracy in neural activity prediction.
Tasks	Activity Prediction, Video Prediction
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04899v2
PDF	http://arxiv.org/pdf/1611.04899v2.pdf
PWC	https://paperswithcode.com/paper/diversity-encouraged-learning-of-unsupervised
Repo
Framework

Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States


Title	Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States
Authors	William Montgomery, Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine
Abstract	Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human-provided demonstrations, instrumentation of the training environment, or extremely long training times. In this paper, we propose a new reinforcement learning algorithm for learning manipulation skills that can train general-purpose neural network policies with minimal human engineering, while still allowing for fast, efficient learning in stochastic environments. Our approach builds on the guided policy search (GPS) algorithm, which transforms the reinforcement learning problem into supervised learning from a computational teacher (without human demonstrations). In contrast to prior GPS methods, which require a consistent set of initial states to which the system must be reset after each episode, our approach can handle randomized initial states, allowing it to be used in environments where deterministic resets are impossible. We compare our method to existing policy search techniques in simulation, showing that it can train high-dimensional neural network policies with the same sample efficiency as prior GPS methods, and present real-world results on a PR2 robotic manipulator.
Tasks
Published	2016-10-04
URL	http://arxiv.org/abs/1610.01112v2
PDF	http://arxiv.org/pdf/1610.01112v2.pdf
PWC	https://paperswithcode.com/paper/reset-free-guided-policy-search-efficient
Repo
Framework

A simple squared-error reformulation for ordinal classification


Title	A simple squared-error reformulation for ordinal classification
Authors	Christopher Beckham, Christopher Pal
Abstract	In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes. Our formulation is based on the use of a softmax hidden layer, which has received relatively little attention in the literature. We empirically evaluate its performance on the Kaggle diabetic retinopathy dataset, an ordinal and high-resolution dataset and show that it outperforms all of the baselines employed.
Tasks
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00775v2
PDF	http://arxiv.org/pdf/1612.00775v2.pdf
PWC	https://paperswithcode.com/paper/a-simple-squared-error-reformulation-for
Repo
Framework

S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking


Title	S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
Authors	Yi Yang, Ming-Wei Chang
Abstract	Non-linear models recently receive a lot of attention as people are starting to discover the power of statistical and embedding features. However, tree-based models are seldom studied in the context of structured learning despite their recent success on various classification and ranking tasks. In this paper, we propose S-MART, a tree-based structured learning framework based on multiple additive regression trees. S-MART is especially suitable for handling tasks with dense features, and can be used to learn many different structures under various loss functions. We apply S-MART to the task of tweet entity linking — a core component of tweet information extraction, which aims to identify and link name mentions to entities in a knowledge base. A novel inference algorithm is proposed to handle the special structure of the task. The experimental results show that S-MART significantly outperforms state-of-the-art tweet entity linking systems.
Tasks	Entity Linking
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08075v1
PDF	http://arxiv.org/pdf/1609.08075v1.pdf
PWC	https://paperswithcode.com/paper/s-mart-novel-tree-based-structured-learning
Repo
Framework

Towards semi-episodic learning for robot damage recovery


Title	Towards semi-episodic learning for robot damage recovery
Authors	Konstantinos Chatzilygeroudis, Antoine Cully, Jean-Baptiste Mouret
Abstract	The recently introduced Intelligent Trial and Error algorithm (IT&E) enables robots to creatively adapt to damage in a matter of minutes by combining an off-line evolutionary algorithm and an on-line learning algorithm based on Bayesian Optimization. We extend the IT&E algorithm to allow for robots to learn to compensate for damages while executing their task(s). This leads to a semi-episodic learning scheme that increases the robot’s lifetime autonomy and adaptivity. Preliminary experiments on a toy simulation and a 6-legged robot locomotion task show promising results.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01407v1
PDF	http://arxiv.org/pdf/1610.01407v1.pdf
PWC	https://paperswithcode.com/paper/towards-semi-episodic-learning-for-robot
Repo
Framework

Towards Multi-Agent Communication-Based Language Learning


Title	Towards Multi-Agent Communication-Based Language Learning
Authors	Angeliki Lazaridou, Nghia The Pham, Marco Baroni
Abstract	We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Preliminary experiments provide promising results, but also suggest that it is important to ensure that agents trained in this way do not develop an adhoc communication code only effective for the game they are playing
Tasks
Published	2016-05-23
URL	http://arxiv.org/abs/1605.07133v1
PDF	http://arxiv.org/pdf/1605.07133v1.pdf
PWC	https://paperswithcode.com/paper/towards-multi-agent-communication-based
Repo
Framework

Adversarial Training For Sketch Retrieval


Title	Adversarial Training For Sketch Retrieval
Authors	Antonia Creswell, Anil Anthony Bharath
Abstract	Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification. Representations learned by GANs have not yet been applied to retrieval. In this paper, we show that the representations learned by GANs can indeed be used for retrieval. We consider heritage documents that contain unlabelled Merchant Marks, sketch-like symbols that are similar to hieroglyphs. We introduce a novel GAN architecture with design features that make it suitable for sketch retrieval. The performance of this sketch-GAN is compared to a modified version of the original GAN architecture with respect to simple invariance properties. Experiments suggest that sketch-GANs learn representations that are suitable for retrieval and which also have increased stability to rotation, scale and translation compared to the standard GAN architecture.
Tasks	Image Generation, Scene Classification
Published	2016-07-10
URL	http://arxiv.org/abs/1607.02748v2
PDF	http://arxiv.org/pdf/1607.02748v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-training-for-sketch-retrieval
Repo
Framework

Scene Labeling Through Knowledge-Based Rules Employing Constrained Integer Linear Programing


Title	Scene Labeling Through Knowledge-Based Rules Employing Constrained Integer Linear Programing
Authors	Nasim Souly, Mubarak Shah
Abstract	Scene labeling task is to segment the image into meaningful regions and categorize them into classes of objects which comprised the image. Commonly used methods typically find the local features for each segment and label them using classifiers. Afterward, labeling is smoothed in order to make sure that neighboring regions receive similar labels. However, they ignore expressive and non-local dependencies among regions due to expensive training and inference. In this paper, we propose to use high-level knowledge regarding rules in the inference to incorporate dependencies among regions in the image to improve scores of classification. Towards this aim, we extract these rules from data and transform them into constraints for Integer Programming to optimize the structured problem of assigning labels to super-pixels (consequently pixels) of an image. In addition, we propose to use soft-constraints in some scenarios, allowing violating the constraint by imposing a penalty, to make the model more flexible. We assessed our approach on three datasets and obtained promising results.
Tasks	Scene Labeling
Published	2016-08-17
URL	http://arxiv.org/abs/1608.05104v1
PDF	http://arxiv.org/pdf/1608.05104v1.pdf
PWC	https://paperswithcode.com/paper/scene-labeling-through-knowledge-based-rules
Repo
Framework

Learning Dynamic Hierarchical Models for Anytime Scene Labeling


Title	Learning Dynamic Hierarchical Models for Anytime Scene Labeling
Authors	Buyu Liu, Xuming He
Abstract	With increasing demand for efficient image and video analysis, test-time cost of scene parsing becomes critical for many large-scale or time-sensitive vision applications. We propose a dynamic hierarchical model for anytime scene labeling that allows us to achieve flexible trade-offs between efficiency and accuracy in pixel-level prediction. In particular, our approach incorporates the cost of feature computation and model inference, and optimizes the model performance for any given test-time budget by learning a sequence of image-adaptive hierarchical models. We formulate this anytime representation learning as a Markov Decision Process with a discrete-continuous state-action space. A high-quality policy of feature and model selection is learned based on an approximate policy iteration method with action proposal mechanism. We demonstrate the advantages of our dynamic non-myopic anytime scene parsing on three semantic segmentation datasets, which achieves $90%$ of the state-of-the-art performances by using $15%$ of their overall costs.
Tasks	Model Selection, Representation Learning, Scene Labeling, Scene Parsing, Semantic Segmentation
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03474v1
PDF	http://arxiv.org/pdf/1608.03474v1.pdf
PWC	https://paperswithcode.com/paper/learning-dynamic-hierarchical-models-for
Repo
Framework

A Score-level Fusion Method for Eye Movement Biometrics


Title	A Score-level Fusion Method for Eye Movement Biometrics
Authors	Anjith George, Aurobinda Routray
Abstract	This paper proposes a novel framework for the use of eye movement patterns for biometric applications. Eye movements contain abundant information about cognitive brain functions, neural pathways, etc. In the proposed method, eye movement data is classified into fixations and saccades. Features extracted from fixations and saccades are used by a Gaussian Radial Basis Function Network (GRBFN) based method for biometric authentication. A score fusion approach is adopted to classify the data in the output layer. In the evaluation stage, the algorithm has been tested using two types of stimuli: random dot following on a screen and text reading. The results indicate the strength of eye movement pattern as a biometric modality. The algorithm has been evaluated on BioEye 2015 database and found to outperform all the other methods. Eye movements are generated by a complex oculomotor plant which is very hard to spoof by mechanical replicas. Use of eye movement dynamics along with iris recognition technology may lead to a robust counterfeit-resistant person identification system.
Tasks	Iris Recognition, Person Identification
Published	2016-01-13
URL	http://arxiv.org/abs/1601.03333v1
PDF	http://arxiv.org/pdf/1601.03333v1.pdf
PWC	https://paperswithcode.com/paper/a-score-level-fusion-method-for-eye-movement
Repo
Framework