May 7, 2019

3456 words 17 mins read

Paper Group ANR 48

A New Approach for Revising Logic Programs. Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration. Conditional Generative Moment-Matching Networks. Coarse-to-fine Surgical Instrument Detection for Cataract Surgery Monitoring. TerpreT: A Probabilistic Programming Language for Program Induction. Recurrent Mixture Density Network for Sp …

A New Approach for Revising Logic Programs


Title	A New Approach for Revising Logic Programs
Authors	Zhiqiang Zhuang, James Delgrande, Abhaya Nayak, Abdul Sattar
Abstract	Belief revision has been studied mainly with respect to background logics that are monotonic in character. In this paper we study belief revision when the underlying logic is non-monotonic instead–an inherently interesting problem that is under explored. In particular, we will focus on the revision of a body of beliefs that is represented as a logic program under the answer set semantics, while the new information is also similarly represented as a logic program. Our approach is driven by the observation that unlike in a monotonic setting where, when necessary, consistency in a revised body of beliefs is maintained by jettisoning some old beliefs, in a non-monotonic setting consistency can be restored by adding new beliefs as well. We will define a syntactic revision function and subsequently provide representation theorem for characterising it.
Tasks
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09465v1
PDF	http://arxiv.org/pdf/1603.09465v1.pdf
PWC	https://paperswithcode.com/paper/a-new-approach-for-revising-logic-programs
Repo
Framework

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration


Title	Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
Authors	Jiaolong Yang, Hongdong Li, Dylan Campbell, Yunde Jia
Abstract	The Iterative Closest Point (ICP) algorithm is one of the most widely used methods for point-set registration. However, being based on local iterative optimization, ICP is known to be susceptible to local minima. Its performance critically relies on the quality of the initialization and only local optimality is guaranteed. This paper presents the first globally optimal algorithm, named Go-ICP, for Euclidean (rigid) registration of two 3D point-sets under the L2 error metric defined in ICP. The Go-ICP method is based on a branch-and-bound (BnB) scheme that searches the entire 3D motion space SE(3). By exploiting the special structure of SE(3) geometry, we derive novel upper and lower bounds for the registration error function. Local ICP is integrated into the BnB scheme, which speeds up the new method while guaranteeing global optimality. We also discuss extensions, addressing the issue of outlier robustness. The evaluation demonstrates that the proposed method is able to produce reliable registration results regardless of the initialization. Go-ICP can be applied in scenarios where an optimal solution is desirable or where a good initialization is not always available.
Tasks
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03344v1
PDF	http://arxiv.org/pdf/1605.03344v1.pdf
PWC	https://paperswithcode.com/paper/go-icp-a-globally-optimal-solution-to-3d-icp
Repo
Framework

Conditional Generative Moment-Matching Networks


Title	Conditional Generative Moment-Matching Networks
Authors	Yong Ren, Jialian Li, Yucen Luo, Jun Zhu
Abstract	Maximum mean discrepancy (MMD) has been successfully applied to learn deep generative models for characterizing a joint distribution of variables via kernel mean embedding. In this paper, we present conditional generative moment- matching networks (CGMMN), which learn a conditional distribution given some input variables based on a conditional maximum mean discrepancy (CMMD) criterion. The learning is performed by stochastic gradient descent with the gradient calculated by back-propagation. We evaluate CGMMN on a wide range of tasks, including predictive modeling, contextual generation, and Bayesian dark knowledge, which distills knowledge from a Bayesian model by learning a relatively small CGMMN student network. Our results demonstrate competitive performance in all the tasks.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04218v1
PDF	http://arxiv.org/pdf/1606.04218v1.pdf
PWC	https://paperswithcode.com/paper/conditional-generative-moment-matching
Repo
Framework

Coarse-to-fine Surgical Instrument Detection for Cataract Surgery Monitoring


Title	Coarse-to-fine Surgical Instrument Detection for Cataract Surgery Monitoring
Authors	Hassan Al Hajj, Gwenolé Quellec, Mathieu Lamard, Guy Cazuguel, Béatrice Cochener
Abstract	The amount of surgical data, recorded during video-monitored surgeries, has extremely increased. This paper aims at improving existing solutions for the automated analysis of cataract surgeries in real time. Through the analysis of a video recording the operating table, it is possible to know which instruments exit or enter the operating table, and therefore which ones are likely being used by the surgeon. Combining these observations with observations from the microscope video should enhance the overall performance of the systems. To this end, the proposed solution is divided into two main parts: one to detect the instruments at the beginning of the surgery and one to update the list of instruments every time a change is detected in the scene. In the first part, the goal is to separate the instruments from the background and from irrelevant objects. For the second, we are interested in detecting the instruments that appear and disappear whenever the surgeon interacts with the table. Experiments on a dataset of 36 cataract surgeries validate the good performance of the proposed solution.
Tasks
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05619v1
PDF	http://arxiv.org/pdf/1609.05619v1.pdf
PWC	https://paperswithcode.com/paper/coarse-to-fine-surgical-instrument-detection
Repo
Framework

TerpreT: A Probabilistic Programming Language for Program Induction


Title	TerpreT: A Probabilistic Programming Language for Program Induction
Authors	Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, Daniel Tarlow
Abstract	We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our aims are to develop new machine learning approaches based on neural networks and graphical models, and to understand the capabilities of machine learning techniques relative to traditional alternatives, such as those based on constraint solving from the programming languages community. Our key contribution is the proposal of TerpreT, a domain-specific language for expressing program synthesis problems. TerpreT is similar to a probabilistic programming language: a model is composed of a specification of a program representation (declarations of random variables) and an interpreter describing how programs map inputs to outputs (a model connecting unknowns to observations). The inference task is to observe a set of input-output examples and infer the underlying program. TerpreT has two main benefits. First, it enables rapid exploration of a range of domains, program representations, and interpreter models. Second, it separates the model specification from the inference algorithm, allowing like-to-like comparisons between different approaches to inference. From a single TerpreT specification we automatically perform inference using four different back-ends. These are based on gradient descent, linear program (LP) relaxations for graphical models, discrete satisfiability solving, and the Sketch program synthesis system. We illustrate the value of TerpreT by developing several interpreter models and performing an empirical comparison between alternative inference algorithms. Our key empirical finding is that constraint solvers dominate the gradient descent and LP-based formulations. We conclude with suggestions for the machine learning community to make progress on program synthesis.
Tasks	Probabilistic Programming, Program Synthesis
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04428v1
PDF	http://arxiv.org/pdf/1608.04428v1.pdf
PWC	https://paperswithcode.com/paper/terpret-a-probabilistic-programming-language
Repo
Framework

Recurrent Mixture Density Network for Spatiotemporal Visual Attention


Title	Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Authors	Loris Bazzani, Hugo Larochelle, Lorenzo Torresani
Abstract	In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images or videos that are salient, e.g., by down-weighting irrelevant pixels. In this work, we propose a spatiotemporal attentional model that learns where to look in a video directly from human fixation data. We model visual attention with a mixture of Gaussians at each frame. This distribution is used to express the probability of saliency for each pixel. Time consistency in videos is modeled hierarchically by: 1) deep 3D convolutional features to represent spatial and short-term time relations and 2) a long short-term memory network on top that aggregates the clip-level representation of sequential clips and therefore expands the temporal domain from few frames to seconds. The parameters of the proposed model are optimized via maximum likelihood estimation using human fixations as training data, without knowledge of the action in each video. Our experiments on Hollywood2 show state-of-the-art performance on saliency prediction for video. We also show that our attentional model trained on Hollywood2 generalizes well to UCF101 and it can be leveraged to improve action classification accuracy on both datasets.
Tasks	Action Classification, Saliency Prediction
Published	2016-03-27
URL	http://arxiv.org/abs/1603.08199v4
PDF	http://arxiv.org/pdf/1603.08199v4.pdf
PWC	https://paperswithcode.com/paper/recurrent-mixture-density-network-for
Repo
Framework

Phase 2: DCL System Using Deep Learning Approaches for Land-based or Ship-based Real-Time Recognition and Localization of Marine Mammals - Machine Learning Detection Algorithms


Title	Phase 2: DCL System Using Deep Learning Approaches for Land-based or Ship-based Real-Time Recognition and Localization of Marine Mammals - Machine Learning Detection Algorithms
Authors	Peter J. Dugan, Christopher W. Clark, Yann André LeCun, Sofie M. Van Parijs
Abstract	Overarching goals for this work aim to advance the state of the art for detection, classification and localization (DCL) in the field of bioacoustics. This goal is primarily achieved by building a generic framework for detection-classification (DC) using a fast, efficient and scalable architecture, demonstrating the capabilities of this system using on a variety of low-frequency mid-frequency cetacean sounds. Two primary goals are to develop transferable technologies for detection and classification in, one: the area of advanced algorithms, such as deep learning and other methods; and two: advanced systems, capable of real-time and archival processing. For each key area, we will focus on producing publications from this work and providing tools and software to the community where/when possible. Currently massive amounts of acoustic data are being collected by various institutions, corporations and national defense agencies. The long-term goal is to provide technical capability to analyze the data using automatic algorithms for (DC) based on machine intelligence. The goal of the automation is to provide effective and efficient mechanisms by which to process large acoustic datasets for understanding the bioacoustic behaviors of marine mammals. This capability will provide insights into the potential ecological impacts and influences of anthropogenic ocean sounds. This work focuses on building technologies using a maturity model based on DARPA 6.1 and 6.2 processes, for basic and applied research, respectively.
Tasks
Published	2016-05-03
URL	http://arxiv.org/abs/1605.00972v2
PDF	http://arxiv.org/pdf/1605.00972v2.pdf
PWC	https://paperswithcode.com/paper/phase-2-dcl-system-using-deep-learning
Repo
Framework

Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers


Title	Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers
Authors	Dominik Fisch, Christian Gruhl, Edgar Kalkowski, Bernhard Sick, Seppo J. Ovaska
Abstract	After data selection, pre-processing, transformation, and feature extraction, knowledge extraction is not the final step in a data mining process. It is then necessary to understand this knowledge in order to apply it efficiently and effectively. Up to now, there is a lack of appropriate techniques that support this significant step. This is partly due to the fact that the assessment of knowledge is often highly subjective, e.g., regarding aspects such as novelty or usefulness. These aspects depend on the specific knowledge and requirements of the data miner. There are, however, a number of aspects that are objective and for which it is possible to provide appropriate measures. In this article we focus on classification problems and use probabilistic generative classifiers based on mixture density models that are quite common in data mining applications. We define objective measures to assess the informativeness, uniqueness, importance, discrimination, representativity, uncertainty, and distinguishability of rules contained in these classifiers numerically. These measures not only support a data miner in evaluating results of a data mining process based on such classifiers. As we will see in illustrative case studies, they may also be used to improve the data mining process itself or to support the later application of the extracted knowledge.
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06377v1
PDF	http://arxiv.org/pdf/1605.06377v1.pdf
PWC	https://paperswithcode.com/paper/towards-automation-of-knowledge-understanding
Repo
Framework

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition


Title	Pairwise Decomposition of Image Sequences for Active Multi-View Recognition
Authors	Edward Johns, Stefan Leutenegger, Andrew J. Davison
Abstract	A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.
Tasks	Object Recognition
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08359v1
PDF	http://arxiv.org/pdf/1605.08359v1.pdf
PWC	https://paperswithcode.com/paper/pairwise-decomposition-of-image-sequences-for
Repo
Framework

Sparse Representation of Multivariate Extremes with Applications to Anomaly Ranking


Title	Sparse Representation of Multivariate Extremes with Applications to Anomaly Ranking
Authors	Nicolas Goix, Anne Sabourin, Stéphan Clémençon
Abstract	Extremes play a special role in Anomaly Detection. Beyond inference and simulation purposes, probabilistic tools borrowed from Extreme Value Theory (EVT), such as the angular measure, can also be used to design novel statistical learning methods for Anomaly Detection/ranking. This paper proposes a new algorithm based on multivariate EVT to learn how to rank observations in a high dimensional space with respect to their degree of ‘abnormality’. The procedure relies on an original dimension-reduction technique in the extreme domain that possibly produces a sparse representation of multivariate extremes and allows to gain insight into the dependence structure thereof, escaping the curse of dimensionality. The representation output by the unsupervised methodology we propose here can be combined with any Anomaly Detection technique tailored to non-extreme data. As it performs linearly with the dimension and almost linearly in the data (in O(dn log n)), it fits to large scale problems. The approach in this paper is novel in that EVT has never been used in its multivariate version in the field of Anomaly Detection. Illustrative experimental results provide strong empirical evidence of the relevance of our approach.
Tasks	Anomaly Detection, Dimensionality Reduction
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09584v1
PDF	http://arxiv.org/pdf/1603.09584v1.pdf
PWC	https://paperswithcode.com/paper/sparse-representation-of-multivariate
Repo
Framework

A multi-task learning model for malware classification with useful file access pattern from API call sequence


Title	A multi-task learning model for malware classification with useful file access pattern from API call sequence
Authors	Xin Wang, Siu Ming Yiu
Abstract	Based on API call sequences, semantic-aware and machine learning (ML) based malware classifiers can be built for malware detection or classification. Previous works concentrate on crafting and extracting various features from malware binaries, disassembled binaries or API calls via static or dynamic analysis and resorting to ML to build classifiers. However, they tend to involve too much feature engineering and fail to provide interpretability. We solve these two problems with the recent advances in deep learning: 1) RNN-based autoencoders (RNN-AEs) can automatically learn low-dimensional representation of a malware from its raw API call sequence. 2) Multiple decoders can be trained under different supervisions to give more information, other than the class or family label of a malware. Inspired by the works of document classification and automatic sentence summarization, each API call sequence can be regarded as a sentence. In this paper, we make the first attempt to build a multi-task malware learning model based on API call sequences. The model consists of two decoders, one for malware classification and one for $\emph{file access pattern}$ (FAP) generation given the API call sequence of a malware. We base our model on the general seq2seq framework. Experiments show that our model can give competitive classification results as well as insightful FAP information.
Tasks	Document Classification, Feature Engineering, Malware Classification, Malware Detection, Multi-Task Learning
Published	2016-10-19
URL	http://arxiv.org/abs/1610.05945v1
PDF	http://arxiv.org/pdf/1610.05945v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-task-learning-model-for-malware
Repo
Framework

Artwork creation by a cognitive architecture integrating computational creativity and dual process approaches


Title	Artwork creation by a cognitive architecture integrating computational creativity and dual process approaches
Authors	Agnese Augello, Ignazio Infantino, Antonio Lieto, Giovanni Pilato, Riccardo Rizzo, Filippo Vella
Abstract	The paper proposes a novel cognitive architecture (CA) for computational creativity based on the Psi model and on the mechanisms inspired by dual process theories of reasoning and rationality. In recent years, many cognitive models have focused on dual process theories to better describe and implement complex cognitive skills in artificial agents, but creativity has been approached only at a descriptive level. In previous works we have described various modules of the cognitive architecture that allows a robot to execute creative paintings. By means of dual process theories we refine some relevant mechanisms to obtain artworks, and in particular we explain details about the resolution level of the CA dealing with different strategies of access to the Long Term Memory (LTM) and managing the interaction between S1 and S2 processes of the dual process theory. The creative process involves both divergent and convergent processes in either implicit or explicit manner. This leads to four activities (exploratory, reflective, tacit, and analytic) that, triggered by urges and motivations, generate creative acts. These creative acts exploit both the LTM and the WM in order to make novel substitutions to a perceived image by properly mixing parts of pictures coming from different domains. The paper highlights the role of the interaction between S1 and S2 processes, modulated by the resolution level, which focuses the attention of the creative agent by broadening or narrowing the exploration of novel solutions, or even drawing the solution from a set of already made associations. An example of artificial painter is described in some experimentations by using a robotic platform.
Tasks
Published	2016-01-04
URL	http://arxiv.org/abs/1601.00669v1
PDF	http://arxiv.org/pdf/1601.00669v1.pdf
PWC	https://paperswithcode.com/paper/artwork-creation-by-a-cognitive-architecture
Repo
Framework

Dependency Parsing as Head Selection


Title	Dependency Parsing as Head Selection
Authors	Xingxing Zhang, Jianpeng Cheng, Mirella Lapata
Abstract	Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model which we call \textsc{DeNSe} (as shorthand for {\bf De}pendency {\bf N}eural {\bf Se}lection) produces a distribution over possible heads for each word using features obtained from a bidirectional recurrent neural network. Without enforcing structural constraints during training, \textsc{DeNSe} generates (at inference time) trees for the overwhelming majority of sentences, while non-tree outputs can be adjusted with a maximum spanning tree algorithm. We evaluate \textsc{DeNSe} on four languages (English, Chinese, Czech, and German) with varying degrees of non-projectivity. Despite the simplicity of the approach, our parsers are on par with the state of the art.
Tasks	Dependency Parsing
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01280v4
PDF	http://arxiv.org/pdf/1606.01280v4.pdf
PWC	https://paperswithcode.com/paper/dependency-parsing-as-head-selection
Repo
Framework

On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products


Title	On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products
Authors	Kush R. Varshney, Homa Alemzadeh
Abstract	Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine learning. Heretofore, the definition of safety has not been formalized in a machine learning context. In this paper, we do so by defining machine learning safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. We then use this definition to examine safety in all sorts of applications in cyber-physical systems, decision sciences, and data products. We find that the foundational principle of modern statistical machine learning, empirical risk minimization, is not always a sufficient objective. Finally, we discuss how four different categories of strategies for achieving safety in engineering, including inherently safe design, safety reserves, safe fail, and procedural safeguards can be mapped to a machine learning context. We then discuss example techniques that can be adopted in each category, such as considering interpretability and causality of predictive models, objective functions beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software and open data.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01256v2
PDF	http://arxiv.org/pdf/1610.01256v2.pdf
PWC	https://paperswithcode.com/paper/on-the-safety-of-machine-learning-cyber
Repo
Framework

Random Forest for Malware Classification


Title	Random Forest for Malware Classification
Authors	Felan Carlo C. Garcia, Felix P. Muga II
Abstract	The challenge in engaging malware activities involves the correct identification and classification of different malware variants. Various malwares incorporate code obfuscation methods that alters their code signatures effectively countering antimalware detection techniques utilizing static methods and signature database. In this study, we utilized an approach of converting a malware binary into an image and use Random Forest to classify various malware families. The resulting accuracy of 0.9562 exhibits the effectivess of the method in detecting malware
Tasks	Malware Classification
Published	2016-09-25
URL	http://arxiv.org/abs/1609.07770v1
PDF	http://arxiv.org/pdf/1609.07770v1.pdf
PWC	https://paperswithcode.com/paper/random-forest-for-malware-classification
Repo
Framework