May 5, 2019

3250 words 16 mins read

Paper Group ANR 522

3D Shape Induction from 2D Views of Multiple Objects. Generalizing Skills with Semi-Supervised Reinforcement Learning. Vocabulary Selection Strategies for Neural Machine Translation. Random Forest for Label Ranking. Predictive modelling of football injuries. Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an …

3D Shape Induction from 2D Views of Multiple Objects


Title	3D Shape Induction from 2D Views of Multiple Objects
Authors	Matheus Gadelha, Subhransu Maji, Rui Wang
Abstract	In this paper we investigate the problem of inducing a distribution over three-dimensional structures given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called “projective generative adversarial networks” (PrGANs) trains a deep generative model of 3D shapes whose projections match the distributions of the input 2D views. The addition of a projection module allows us to infer the underlying 3D shape distribution without using any 3D, viewpoint information, or annotation during the learning phase. We show that our approach produces 3D shapes of comparable quality to GANs trained on 3D data for a number of shape categories including chairs, airplanes, and cars. Experiments also show that the disentangled representation of 2D shapes into geometry and viewpoint leads to a good generative model of 2D shapes. The key advantage is that our model allows us to predict 3D, viewpoint, and generate novel views from an input image in a completely unsupervised manner.
Tasks
Published	2016-12-18
URL	http://arxiv.org/abs/1612.05872v1
PDF	http://arxiv.org/pdf/1612.05872v1.pdf
PWC	https://paperswithcode.com/paper/3d-shape-induction-from-2d-views-of-multiple
Repo
Framework

Generalizing Skills with Semi-Supervised Reinforcement Learning


Title	Generalizing Skills with Semi-Supervised Reinforcement Learning
Authors	Chelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine
Abstract	Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known to achieve remarkable generalization when provided with massive amounts of labeled data, but can we provide this breadth of experience to an RL agent, such as a robot? The robot might continuously learn as it explores the world around it, even while deployed. However, this learning requires access to a reward function, which is often hard to measure in real-world domains, where the reward could depend on, for example, unknown positions of objects or the emotional state of the user. Conversely, it is often quite practical to provide the agent with reward functions in a limited set of situations, such as when a human supervisor is present or in a controlled setting. Can we make use of this limited supervision, and still benefit from the breadth of experience an agent might collect on its own? In this paper, we formalize this problem as semisupervised reinforcement learning, where the reward function can only be evaluated in a set of “labeled” MDPs, and the agent must generalize its behavior to the wide range of states it might encounter in a set of “unlabeled” MDPs, by using experience from both settings. Our proposed method infers the task objective in the unlabeled MDPs through an algorithm that resembles inverse RL, using the agent’s own prior experience in the labeled MDPs as a kind of demonstration of optimal behavior. We evaluate our method on challenging tasks that require control directly from images, and show that our approach can improve the generalization of a learned deep neural network policy by using experience for which no reward function is available. We also show that our method outperforms direct supervised learning of the reward.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00429v2
PDF	http://arxiv.org/pdf/1612.00429v2.pdf
PWC	https://paperswithcode.com/paper/generalizing-skills-with-semi-supervised
Repo
Framework

Vocabulary Selection Strategies for Neural Machine Translation


Title	Vocabulary Selection Strategies for Neural Machine Translation
Authors	Gurvan L’Hostis, David Grangier, Michael Auli
Abstract	Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by restricting the output vocabulary to a subset of likely candidates given the source. In this paper we experiment with context and embedding-based selection methods and extend previous work by examining speed and accuracy trade-offs in more detail. We show that decoding time on CPUs can be reduced by up to 90% and training time by 25% on the WMT15 English-German and WMT16 English-Romanian tasks at the same or only negligible change in accuracy. This brings the time to decode with a state of the art neural translation system to just over 140 msec per sentence on a single CPU core for English-German.
Tasks	Machine Translation
Published	2016-10-01
URL	http://arxiv.org/abs/1610.00072v1
PDF	http://arxiv.org/pdf/1610.00072v1.pdf
PWC	https://paperswithcode.com/paper/vocabulary-selection-strategies-for-neural
Repo
Framework

Random Forest for Label Ranking


Title	Random Forest for Label Ranking
Authors	Yangming Zhou, Guoping Qiu
Abstract	Label ranking aims to learn a mapping from instances to rankings over a finite number of predefined labels. Random forest is a powerful and one of the most successful general-purpose machine learning algorithms of modern times. In this paper, we present a powerful random forest label ranking method which uses random decision trees to retrieve nearest neighbors. We have developed a novel two-step rank aggregation strategy to effectively aggregate neighboring rankings discovered by the random forest into a final predicted ranking. Compared with existing methods, the new random forest method has many advantages including its intrinsically scalable tree data structure, highly parallel-able computational architecture and much superior performance. We present extensive experimental results to demonstrate that our new method achieves the highly competitive performance compared with state-of-the-art methods for datasets with complete ranking and datasets with only partial ranking information.
Tasks
Published	2016-08-27
URL	http://arxiv.org/abs/1608.07710v3
PDF	http://arxiv.org/pdf/1608.07710v3.pdf
PWC	https://paperswithcode.com/paper/random-forest-for-label-ranking
Repo
Framework

Predictive modelling of football injuries


Title	Predictive modelling of football injuries
Authors	Stylianos Kampakis
Abstract	The goal of this thesis is to investigate the potential of predictive modelling for football injuries. This work was conducted in close collaboration with Tottenham Hotspurs FC (THFC), the PGA European tour and the participation of Wolverhampton Wanderers (WW). Three investigations were conducted: 1. Predicting the recovery time of football injuries using the UEFA injury recordings: The UEFA recordings is a common standard for recording injuries in professional football. For this investigation, three datasets of UEFA injury recordings were available. Different machine learning algorithms were used in order to build a predictive model. The performance of the machine learning models is then improved by using feature selection conducted through correlation-based subset feature selection and random forests. 2. Predicting injuries in professional football using exposure records: The relationship between exposure (in training hours and match hours) in professional football athletes and injury incidence was studied. A common problem in football is understanding how the training schedule of an athlete can affect the chance of him getting injured. The task was to predict the number of days a player can train before he gets injured. 3. Predicting intrinsic injury incidence using in-training GPS measurements: A significant percentage of football injuries can be attributed to overtraining and fatigue. GPS data collected during training sessions might provide indicators of fatigue, or might be used to detect very intense training sessions which can lead to overtraining. This research used GPS data gathered during training sessions of the first team of THFC, in order to predict whether an injury would take place during a week.
Tasks	Feature Selection, Game of Football, Injury Prediction
Published	2016-09-20
URL	http://arxiv.org/abs/1609.07480v1
PDF	http://arxiv.org/pdf/1609.07480v1.pdf
PWC	https://paperswithcode.com/paper/predictive-modelling-of-football-injuries
Repo
Framework

Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model


Title	Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model
Authors	Pavel Filonov, Andrey Lavrentyev, Artem Vorontsov
Abstract	We adopted an approach based on an LSTM neural network to monitor and detect faults in industrial multivariate time series data. To validate the approach we created a Modelica model of part of a real gasoil plant. By introducing hacks into the logic of the Modelica model, we were able to generate both the roots and causes of fault behavior in the plant. Having a self-consistent data set with labeled faults, we used an LSTM architecture with a forecasting error threshold to obtain precision and recall quality metrics. The dependency of the quality metric on the threshold level is considered. An appropriate mechanism such as “one handle” was introduced for filtering faults that are outside of the plant operator field of interest.
Tasks	Fault Detection, Time Series
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06676v2
PDF	http://arxiv.org/pdf/1612.06676v2.pdf
PWC	https://paperswithcode.com/paper/multivariate-industrial-time-series-with
Repo
Framework

Whole-brain substitute CT generation using Markov random field mixture models


Title	Whole-brain substitute CT generation using Markov random field mixture models
Authors	Anders Hildeman, David Bolin, Jonas Wallin, Adam Johansson, Tufve Nyholm, Thomas Asklund, Jun Yu
Abstract	Computed tomography (CT) equivalent information is needed for attenuation correction in PET imaging and for dose planning in radiotherapy. Prior work has shown that Gaussian mixture models can be used to generate a substitute CT (s-CT) image from a specific set of MRI modalities. This work introduces a more flexible class of mixture models for s-CT generation, that incorporates spatial dependency in the data through a Markov random field prior on the latent field of class memberships associated with a mixture model. Furthermore, the mixture distributions are extended from Gaussian to normal inverse Gaussian (NIG), allowing heavier tails and skewness. The amount of data needed to train a model for s-CT generation is of the order of 100 million voxels. The computational efficiency of the parameter estimation and prediction methods are hence paramount, especially when spatial dependency is included in the models. A stochastic Expectation Maximization (EM) gradient algorithm is proposed in order to tackle this challenge. The advantages of the spatial model and NIG distributions are evaluated with a cross-validation study based on data from 14 patients. The study show that the proposed model enhances the predictive quality of the s-CT images by reducing the mean absolute error with 17.9%. Also, the distribution of CT values conditioned on the MR images are better explained by the proposed model as evaluated using continuous ranked probability scores.
Tasks	Computed Tomography (CT)
Published	2016-07-07
URL	http://arxiv.org/abs/1607.02188v2
PDF	http://arxiv.org/pdf/1607.02188v2.pdf
PWC	https://paperswithcode.com/paper/whole-brain-substitute-ct-generation-using
Repo
Framework

Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networks


Title	Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networks
Authors	Alexander Gomez, Augusto Salazar, Francisco Vargas
Abstract	Non intrusive monitoring of animals in the wild is possible using camera trapping framework, which uses cameras triggered by sensors to take a burst of images of animals in their habitat. However camera trapping framework produces a high volume of data (in the order on thousands or millions of images), which must be analyzed by a human expert. In this work, a method for animal species identification in the wild using very deep convolutional neural networks is presented. Multiple versions of the Snapshot Serengeti dataset were used in order to probe the ability of the method to cope with different challenges that camera-trap images demand. The method reached 88.9% of accuracy in Top-1 and 98.1% in Top-5 in the evaluation set using a residual network topology. Also, the results show that the proposed method outperforms previous approximations and proves that recognition in camera-trap images can be automated.
Tasks
Published	2016-03-20
URL	http://arxiv.org/abs/1603.06169v2
PDF	http://arxiv.org/pdf/1603.06169v2.pdf
PWC	https://paperswithcode.com/paper/towards-automatic-wild-animal-monitoring
Repo
Framework

Infomax strategies for an optimal balance between exploration and exploitation


Title	Infomax strategies for an optimal balance between exploration and exploitation
Authors	Gautam Reddy, Antonio Celani, Massimo Vergassola
Abstract	Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates that maximization of information directs the function of diverse systems, from living systems to artificial neural networks. While specific applications are successful, the validity of information as a proxy for reward remains unclear. Here, we consider the multi-armed bandit decision problem, which features arms (slot-machines) of unknown probabilities of success and a player trying to maximize cumulative payoff by choosing the sequence of arms to play. We show that an Infomax strategy (Info-p) which optimally gathers information on the highest mean reward among the arms saturates known optimal bounds and compares favorably to existing policies. The highest mean reward considered by Info-p is not the quantity actually needed for the choice of the arm to play, yet it allows for optimal tradeoffs between exploration and exploitation.
Tasks
Published	2016-01-12
URL	http://arxiv.org/abs/1601.03073v1
PDF	http://arxiv.org/pdf/1601.03073v1.pdf
PWC	https://paperswithcode.com/paper/infomax-strategies-for-an-optimal-balance
Repo
Framework

FOCA: A Methodology for Ontology Evaluation


Title	FOCA: A Methodology for Ontology Evaluation
Authors	Judson Bandeira, Ig Ibert Bittencourt, Patricia Espinheira, Seiji Isotani
Abstract	Modeling an ontology is a hard and time-consuming task. Although methodologies are useful for ontologists to create good ontologies, they do not help with the task of evaluating the quality of the ontology to be reused. For these reasons, it is imperative to evaluate the quality of the ontology after constructing it or before reusing it. Few studies usually present only a set of criteria and questions, but no guidelines to evaluate the ontology. The effort to evaluate an ontology is very high as there is a huge dependence on the evaluator’s expertise to understand the criteria and questions in depth. Moreover, the evaluation is still very subjective. This study presents a novel methodology for ontology evaluation, taking into account three fundamental principles: i) it is based on the Goal, Question, Metric approach for empirical evaluation; ii) the goals of the methodologies are based on the roles of knowledge representations combined with specific evaluation criteria; iii) each ontology is evaluated according to the type of ontology. The methodology was empirically evaluated using different ontologists and ontologies of the same domain. The main contributions of this study are: i) defining a step-by-step approach to evaluate the quality of an ontology; ii) proposing an evaluation based on the roles of knowledge representations; iii) the explicit difference of the evaluation according to the type of the ontology iii) a questionnaire to evaluate the ontologies; iv) a statistical model that automatically calculates the quality of the ontologies.
Tasks
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03353v2
PDF	http://arxiv.org/pdf/1612.03353v2.pdf
PWC	https://paperswithcode.com/paper/foca-a-methodology-for-ontology-evaluation
Repo
Framework

InterActive: Inter-Layer Activeness Propagation


Title	InterActive: Inter-Layer Activeness Propagation
Authors	Lingxi Xie, Liang Zheng, Jingdong Wang, Alan Yuille, Qi Tian
Abstract	An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network. Despite the astonishing performance, deep features extracted from low-level neurons are still below satisfaction, arguably because they cannot access the spatial context contained in the higher layers. In this paper, we present InterActive, a novel algorithm which computes the activeness of neurons and network connections. Activeness is propagated through a neural network in a top-down manner, carrying high-level context and improving the descriptive power of low-level and mid-level neurons. Visualization indicates that neuron activeness can be interpreted as spatial-weighted neuron responses. We achieve state-of-the-art classification performance on a wide range of image datasets.
Tasks
Published	2016-04-30
URL	http://arxiv.org/abs/1605.00052v1
PDF	http://arxiv.org/pdf/1605.00052v1.pdf
PWC	https://paperswithcode.com/paper/interactive-inter-layer-activeness
Repo
Framework

A Theoretical Analysis of the BDeu Scores in Bayesian Network Structure Learning


Title	A Theoretical Analysis of the BDeu Scores in Bayesian Network Structure Learning
Authors	Joe Suzuki
Abstract	In Bayesian network structure learning (BNSL), we need the prior probability over structures and parameters. If the former is the uniform distribution, the latter determines the correctness of BNSL. In this paper, we compare BDeu (Bayesian Dirichlet equivalent uniform) and Jeffreys’ prior w.r.t. their consistency. When we seek a parent set $U$ of a variable $X$, we require regularity that if $H(XU)\leq H(XU’)$ and $U\subsetneq U'$, then $U$ should be chosen rather than $U'$. We prove that the BDeu scores violate the property and cause fatal situations in BNSL. This is because for the BDeu scores, for any sample size $n$,there exists a probability in the form $P(X,Y,Z)={P(XZ)P(YZ)}/{P(Z)}$ such that the probability of deciding that $X$ and $Y$ are not conditionally independent given $Z$ is more than a half. For Jeffreys’ prior, the false-positive probability uniformly converges to zero without depending on any parameter values, and no such an inconvenience occurs.
Tasks
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04427v3
PDF	http://arxiv.org/pdf/1607.04427v3.pdf
PWC	https://paperswithcode.com/paper/a-theoretical-analysis-of-the-bdeu-scores-in
Repo
Framework

Molecular Graph Convolutions: Moving Beyond Fingerprints


Title	Molecular Graph Convolutions: Moving Beyond Fingerprints
Authors	Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley
Abstract	Molecular “fingerprints” encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular “graph convolutions”, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph—atoms, bonds, distances, etc.—which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.
Tasks	Drug Discovery, Graph Regression
Published	2016-03-02
URL	http://arxiv.org/abs/1603.00856v3
PDF	http://arxiv.org/pdf/1603.00856v3.pdf
PWC	https://paperswithcode.com/paper/molecular-graph-convolutions-moving-beyond
Repo
Framework

Dictionary Learning with Equiprobable Matching Pursuit


Title	Dictionary Learning with Equiprobable Matching Pursuit
Authors	Fredrik Sandin, Sergio Martin-del-Campo
Abstract	Sparse signal representations based on linear combinations of learned atoms have been used to obtain state-of-the-art results in several practical signal processing applications. Approximation methods are needed to process high-dimensional signals in this way because the problem to calculate optimal atoms for sparse coding is NP-hard. Here we study greedy algorithms for unsupervised learning of dictionaries of shift-invariant atoms and propose a new method where each atom is selected with the same probability on average, which corresponds to the homeostatic regulation of a recurrent convolutional neural network. Equiprobable selection can be used with several greedy algorithms for dictionary learning to ensure that all atoms adapt during training and that no particular atom is more likely to take part in the linear combination on average. We demonstrate via simulation experiments that dictionary learning with equiprobable selection results in higher entropy of the sparse representation and lower reconstruction and denoising errors, both in the case of ordinary matching pursuit and orthogonal matching pursuit with shift-invariant dictionaries. Furthermore, we show that the computational costs of the matching pursuits are lower with equiprobable selection, leading to faster and more accurate dictionary learning algorithms.
Tasks	Denoising, Dictionary Learning
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09333v1
PDF	http://arxiv.org/pdf/1611.09333v1.pdf
PWC	https://paperswithcode.com/paper/dictionary-learning-with-equiprobable
Repo
Framework

Refining adverse drug reaction signals by incorporating interaction variables identified using emergent pattern mining


Title	Refining adverse drug reaction signals by incorporating interaction variables identified using emergent pattern mining
Authors	Jenna M. Reps, Uwe Aickelin, Richard B. Hubbard
Abstract	Purpose: To develop a framework for identifying and incorporating candidate confounding interaction terms into a regularised cox regression analysis to refine adverse drug reaction signals obtained via longitudinal observational data. Methods: We considered six drug families that are commonly associated with myocardial infarction in observational healthcare data, but where the causal relationship ground truth is known (adverse drug reaction or not). We applied emergent pattern mining to find itemsets of drugs and medical events that are associated with the development of myocardial infarction. These are the candidate confounding interaction terms. We then implemented a cohort study design using regularised cox regression that incorporated and accounted for the candidate confounding interaction terms. Results The methodology was able to account for signals generated due to confounding and a cox regression with elastic net regularisation correctly ranked the drug families known to be true adverse drug reactions above those.
Tasks
Published	2016-07-20
URL	http://arxiv.org/abs/1607.05906v1
PDF	http://arxiv.org/pdf/1607.05906v1.pdf
PWC	https://paperswithcode.com/paper/refining-adverse-drug-reaction-signals-by
Repo
Framework