July 28, 2019

2804 words 14 mins read

Paper Group ANR 259

Horn-ICE Learning for Synthesizing Invariants and Contracts. Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding. A DIKW Paradigm to Cognitive Engineering. Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents. TripletGAN: Trai …

Horn-ICE Learning for Synthesizing Invariants and Contracts


Title	Horn-ICE Learning for Synthesizing Invariants and Contracts
Authors	Deepak D’Souza, P. Ezudheen, Pranav Garg, P. Madhusudan, Daniel Neider
Abstract	We design learning algorithms for synthesizing invariants using Horn implication counterexamples (Horn-ICE), extending the ICE-learning model. In particular, we describe a decision-tree learning algorithm that learns from Horn-ICE samples, works in polynomial time, and uses statistical heuristics to learn small trees that satisfy the samples. Since most verification proofs can be modeled using Horn clauses, Horn-ICE learning is a more robust technique to learn inductive annotations that prove programs correct. Our experiments show that an implementation of our algorithm is able to learn adequate inductive invariants and contracts efficiently for a variety of sequential and concurrent programs.
Tasks
Published	2017-12-26
URL	http://arxiv.org/abs/1712.09418v1
PDF	http://arxiv.org/pdf/1712.09418v1.pdf
PWC	https://paperswithcode.com/paper/horn-ice-learning-for-synthesizing-invariants
Repo
Framework

Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding


Title	Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
Authors	Anjishnu Kumar, Arpit Gupta, Julian Chan, Sam Tucker, Bjorn Hoffmeister, Markus Dreyer, Stanislav Peshterliev, Ankur Gandhe, Denis Filiminov, Ariya Rastrow, Christian Monson, Agnika Kumar
Abstract	This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon’s virtual assistant, Alexa. At Amazon, the infrastructure powers over 25,000 skills deployed through the ASK, as well as AWS’s Amazon Lex SLU Service. The ASK emphasizes flexibility, predictability and a rapid iteration cycle for third party developers. It imposes inductive biases that allow it to learn robust SLU models from extremely small and sparse datasets and, in doing so, removes significant barriers to entry for software developers and dialogue systems researchers.
Tasks	Spoken Language Understanding
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00549v4
PDF	http://arxiv.org/pdf/1711.00549v4.pdf
PWC	https://paperswithcode.com/paper/just-ask-building-an-architecture-for
Repo
Framework

A DIKW Paradigm to Cognitive Engineering


Title	A DIKW Paradigm to Cognitive Engineering
Authors	Amit Kumar Mishra
Abstract	Though the word cognitive has a wide range of meanings we define cognitive engineering as learning from brain to bolster engineering solutions. However, giving an achievable framework to the process towards this has been a difficult task. In this work we take the classic data information knowledge wisdom (DIKW) framework to set some achievable goals and sub-goals towards cognitive engineering. A layered framework like DIKW aligns nicely with the layered structure of pre-frontal cortex. And breaking the task into sub-tasks based on the layers also makes it easier to start developmental endeavours towards achieving the final goal of a brain-inspired system.
Tasks
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07168v1
PDF	http://arxiv.org/pdf/1702.07168v1.pdf
PWC	https://paperswithcode.com/paper/a-dikw-paradigm-to-cognitive-engineering
Repo
Framework

Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents


Title	Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents
Authors	Hardik Jain, Gaurav Gupta, Sharad Joshi, Nitin Khanna
Abstract	In this digital era, one thing that still holds the convention is a printed archive. Printed documents find their use in many critical domains such as contract papers, legal tenders and proof of identity documents. As more advanced printing, scanning and image editing techniques are becoming available, forgeries on these legal tenders pose a serious threat. Ability to easily and reliably identify source printer of a printed document can help a lot in reducing this menace. During printing procedure, printer hardware introduces certain distortions in printed characters’ locations and shapes which are invisible to naked eyes. These distortions are referred as geometric distortions, their profile (or signature) is generally unique for each printer and can be used for printer classification purpose. This paper proposes a set of features for characterizing text-line-level geometric distortions, referred as geometric distortion signatures and presents a novel system to use them for identification of the origin of a printed document. Detailed experiments performed on a set of thirteen printers demonstrate that the proposed system achieves state of the art performance and gives much higher accuracy under small training size constraint. For four training and six test pages of three different fonts, the proposed method gives 99% classification accuracy.
Tasks
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06651v1
PDF	http://arxiv.org/pdf/1706.06651v1.pdf
PWC	https://paperswithcode.com/paper/passive-classification-of-source-printer
Repo
Framework

TripletGAN: Training Generative Model with Triplet Loss


Title	TripletGAN: Training Generative Model with Triplet Loss
Authors	Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin, Yang Liu, Mingli Song
Abstract	As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map to replace softmax in the classification task. Inspired by this concept, we propose here a new adversarial modeling method by substituting the classification loss of discriminator with triplet loss. Theoretical proof based on IPM (Integral probability metric) demonstrates that such setting will help the generator converge to the given distribution theoretically under some conditions. Moreover, since triplet loss requires the generator to maximize distance within a class, we justify tripletGAN is also helpful to prevent mode collapse through both theory and experiment.
Tasks	Face Recognition, Metric Learning
Published	2017-11-14
URL	http://arxiv.org/abs/1711.05084v1
PDF	http://arxiv.org/pdf/1711.05084v1.pdf
PWC	https://paperswithcode.com/paper/tripletgan-training-generative-model-with
Repo
Framework

Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics


Title	Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics
Authors	Tomoki Nishi, Prashant Doshi, Michael R. James, Danil Prokhorov
Abstract	In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning (RL) method for continuous state and action spaces that learns with partial knowledge of the system and without active exploration. It solves linearly-solvable Markov decision processes (L-MDPs), which are well suited for continuous state and action spaces, based on an actor-critic architecture. Compared to previous RL methods for L-MDPs and path integral methods which are model based, the actor-critic learning does not need a model of the uncontrolled dynamics and, importantly, transition noise levels; however, it requires knowing the control dynamics for the problem. We evaluate our method on two synthetic test problems, and one real-world problem in simulation and using real traffic data. Our experiments demonstrate improved learning and policy performance.
Tasks
Published	2017-06-04
URL	http://arxiv.org/abs/1706.01077v1
PDF	http://arxiv.org/pdf/1706.01077v1.pdf
PWC	https://paperswithcode.com/paper/actor-critic-for-linearly-solvable-continuous
Repo
Framework

A Renewal Model of Intrusion


Title	A Renewal Model of Intrusion
Authors	David Tolpin
Abstract	We present a probabilistic model of an intrusion in a renewal process. Given a process and a sequence of events, an intrusion is a subsequence of events that is not produced by the process. Applications of the model are, for example, online payment fraud with the fraudster taking over a user’s account and performing payments on the user’s behalf, or unexpected equipment failures due to unintended use. We adopt Bayesian approach to infer the probability of an intrusion in a sequence of events, a MAP subsequence of events constituting the intrusion, and the marginal probability of each event in a sequence to belong to the intrusion. We evaluate the model for intrusion detection on synthetic data and on anonymized data from an online payment system.
Tasks	Intrusion Detection
Published	2017-09-24
URL	http://arxiv.org/abs/1709.08163v5
PDF	http://arxiv.org/pdf/1709.08163v5.pdf
PWC	https://paperswithcode.com/paper/a-renewal-model-of-intrusion
Repo
Framework

Identifying Spatial Relations in Images using Convolutional Neural Networks


Title	Identifying Spatial Relations in Images using Convolutional Neural Networks
Authors	Mandar Haldekar, Ashwinkumar Ganesan, Tim Oates
Abstract	Traditional approaches to building a large scale knowledge graph have usually relied on extracting information (entities, their properties, and relations between them) from unstructured text (e.g. Dbpedia). Recent advances in Convolutional Neural Networks (CNN) allow us to shift our focus to learning entities and relations from images, as they build robust models that require little or no pre-processing of the images. In this paper, we present an approach to identify and extract spatial relations (e.g., The girl is standing behind the table) from images using CNNs. Our research addresses two specific challenges: providing insight into how spatial relations are learned by the network and which parts of the image are used to predict these relations. We use the pre-trained network VGGNet to extract features from an image and train a Multi-layer Perceptron (MLP) on a set of synthetic images and the sun09 dataset to extract spatial relations. The MLP predicts spatial relations without a bounding box around the objects or the space in the image depicting the relation. To understand how the spatial relations are represented in the network, a heatmap is overlayed on the image to show the regions that are deemed important by the network. Also, we analyze the MLP to show the relationship between the activation of consistent groups of nodes and the prediction of a spatial relation. We show how the loss of these groups affects the networks ability to identify relations.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04215v1
PDF	http://arxiv.org/pdf/1706.04215v1.pdf
PWC	https://paperswithcode.com/paper/identifying-spatial-relations-in-images-using
Repo
Framework

Adaptive Generation-Based Evolution Control for Gaussian Process Surrogate Models


Title	Adaptive Generation-Based Evolution Control for Gaussian Process Surrogate Models
Authors	Jakub Repicky, Lukas Bajer, Zbynek Pitra, Martin Holena
Abstract	The interest in accelerating black-box optimizers has resulted in several surrogate model-assisted version of the Covariance Matrix Adaptation Evolution Strategy, a state-of-the-art continuous black-box optimizer. The version called Surrogate CMA-ES uses Gaussian processes or random forests surrogate models with a generation-based evolution control. This paper presents an adaptive improvement for S-CMA-ES based on a general procedure introduced with the s*ACM-ES algorithm, in which the number of generations using the surrogate model before retraining is adjusted depending on the performance of the last instance of the surrogate. Three algorithms that differ in the measure of the surrogate model’s performance are evaluated on the COCO/BBOB framework. The results show a minor improvement on S-CMA-ES with constant model lifelengths, especially when larger lifelengths are considered.
Tasks	Gaussian Processes
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10443v1
PDF	http://arxiv.org/pdf/1709.10443v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-generation-based-evolution-control
Repo
Framework

How to Learn a Model Checker


Title	How to Learn a Model Checker
Authors	Dung Phan, Radu Grosu, Nicola Paoletti, Scott A. Smolka, Scott D. Stoller
Abstract	We show how machine-learning techniques, particularly neural networks, offer a very effective and highly efficient solution to the approximate model-checking problem for continuous and hybrid systems, a solution where the general-purpose model checker is replaced by a model-specific classifier trained by sampling model trajectories. To the best of our knowledge, we are the first to establish this link from machine learning to model checking. Our method comprises a pipeline of analysis techniques for estimating and obtaining statistical guarantees on the classifier’s prediction performance, as well as tuning techniques to improve such performance. Our experimental evaluation considers the time-bounded reachability problem for three well-established benchmarks in the hybrid systems community. On these examples, we achieve an accuracy of 99.82% to 100% and a false-negative rate (incorrectly predicting that unsafe states are not reachable from a given state) of 0.0007 to 0. We believe that this level of accuracy is acceptable in many practical applications and we show how the approximate model checker can be made more conservative by tuning the classifier through further training and selection of the classification threshold.
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01935v1
PDF	http://arxiv.org/pdf/1712.01935v1.pdf
PWC	https://paperswithcode.com/paper/how-to-learn-a-model-checker
Repo
Framework

Region-Based Multiscale Spatiotemporal Saliency for Video


Title	Region-Based Multiscale Spatiotemporal Saliency for Video
Authors	Trung-Nghia Le, Akihiro Sugimoto
Abstract	Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and dynamic features computed from the low and middle levels are combined together. Our method utilizes such combined features spatially over each frame and, at the same time, temporally across frames using consistency between consecutive frames. Saliency cues in our method are analyzed through a multiscale segmentation model, and fused across scale levels, yielding to exploring regions efficiently. An adaptive temporal window using motion information is also developed to combine saliency values of consecutive frames in order to keep temporal consistency across frames. Performance evaluation on several popular benchmark datasets validates that our method outperforms existing state-of-the-arts.
Tasks	Saliency Detection
Published	2017-08-04
URL	http://arxiv.org/abs/1708.01589v1
PDF	http://arxiv.org/pdf/1708.01589v1.pdf
PWC	https://paperswithcode.com/paper/region-based-multiscale-spatiotemporal
Repo
Framework

Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-based Supervision


Title	Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-based Supervision
Authors	Baris Gecer, Vassileios Balntas, Tae-Kyun Kim
Abstract	In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization. We explain our framework that expands traditional learning with set-based supervision together with the strategies used to maintain set characteristics. We, then, briefly review the related set-based loss functions, and subsequently propose a novel Max-Margin Loss which maximizes maximum possible inter-class margin with assistance of Support Vector Machines (SVMs). It implicitly pushes all the samples towards correct side of the margin with a vector perpendicular to the hyperplane and a strength exponentially growing towards to negative side of the hyperplane. We show that the introduced loss outperform the previous sample-based and set-based ones in terms verification of faces on two commonly used benchmarks.
Tasks	Face Recognition
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00277v3
PDF	http://arxiv.org/pdf/1708.00277v3.pdf
PWC	https://paperswithcode.com/paper/learning-deep-convolutional-embeddings-for
Repo
Framework

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering


Title	Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering
Authors	Mengyao Zhai, Jiacheng Chen, Ruizhi Deng, Lei Chen, Ligeng Zhu, Greg Mori
Abstract	We propose an approach for forecasting video of complex human activity involving multiple people. Direct pixel-level prediction is too simple to handle the appearance variability in complex activities. Hence, we develop novel intermediate representations. An architecture combining a hierarchical temporal model for predicting human poses and encoder-decoder convolutional neural networks for rendering target appearances is proposed. Our hierarchical model captures interactions among people by adopting a dynamic group-based interaction mechanism. Next, our appearance rendering network encodes the targets’ appearances by learning adaptive appearance filters using a fully convolutional network. Finally, these filters are placed in encoder-decoder neural networks to complete the rendering. We demonstrate that our model can generate videos that are superior to state-of-the-art methods, and can handle complex human activity scenarios in video forecasting.
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01955v1
PDF	http://arxiv.org/pdf/1712.01955v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-forecast-videos-of-human-activity
Repo
Framework

Reinforcement Learning for Learning Rate Control


Title	Reinforcement Learning for Learning Rate Control
Authors	Chang Xu, Tao Qin, Gang Wang, Tie-Yan Liu
Abstract	Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks. It is observed that the models trained by SGD are sensitive to learning rates and good learning rates are problem specific. We propose an algorithm to automatically learn learning rates using neural network based actor-critic methods from deep reinforcement learning (RL).In particular, we train a policy network called actor to decide the learning rate at each step during training, and a value network called critic to give feedback about quality of the decision (e.g., the goodness of the learning rate outputted by the actor) that the actor made. The introduction of auxiliary actor and critic networks helps the main network achieve better performance. Experiments on different datasets and network architectures show that our approach leads to better convergence of SGD than human-designed competitors.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1705.11159v1
PDF	http://arxiv.org/pdf/1705.11159v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-for-learning-rate
Repo
Framework

Investigation on the use of Hidden-Markov Models in automatic transcription of music


Title	Investigation on the use of Hidden-Markov Models in automatic transcription of music
Authors	D. Cazau, G. Nuel
Abstract	Hidden Markov Models (HMMs) are a ubiquitous tool to model time series data, and have been widely used in two main tasks of Automatic Music Transcription (AMT): note segmentation, i.e. identifying the played notes after a multi-pitch estimation, and sequential post-processing, i.e. correcting note segmentation using training data. In this paper, we employ the multi-pitch estimation method called Probabilistic Latent Component Analysis (PLCA), and develop AMT systems by integrating different HMM-based modules in this framework. For note segmentation, we use two different twostate on/o? HMMs, including a higher-order one for duration modeling. For sequential post-processing, we focused on a musicological modeling of polyphonic harmonic transitions, using a first- and second-order HMMs whose states are defined through candidate note mixtures. These different PLCA plus HMM systems have been evaluated comparatively on two different instrument repertoires, namely the piano (using the MAPS database) and the marovany zither. Our results show that the use of HMMs could bring noticeable improvements to transcription results, depending on the instrument repertoire.
Tasks	Time Series
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03711v1
PDF	http://arxiv.org/pdf/1704.03711v1.pdf
PWC	https://paperswithcode.com/paper/investigation-on-the-use-of-hidden-markov
Repo
Framework