Paper Group ANR 723
A Polynomial Time Subsumption Algorithm for Nominal Safe $\mathcal{ELO}_\bot$ under Rational Closure. Regularized Fuzzy Neural Networks to Aid Effort Forecasting in the Construction and Software Development. SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection. Practical Bayesian Learning of Neural Networks via Adaptive …
A Polynomial Time Subsumption Algorithm for Nominal Safe $\mathcal{ELO}_\bot$ under Rational Closure
Title | A Polynomial Time Subsumption Algorithm for Nominal Safe $\mathcal{ELO}_\bot$ under Rational Closure |
Authors | Giovanni Casini, Umberto Straccia, Thomas Meyer |
Abstract | Description Logics (DLs) under Rational Closure (RC) is a well-known framework for non-monotonic reasoning in DLs. In this paper, we address the concept subsumption decision problem under RC for nominal safe $\mathcal{ELO}\bot$, a notable and practically important DL representative of the OWL 2 profile OWL 2 EL. Our contribution here is to define a polynomial time subsumption procedure for nominal safe $\mathcal{ELO}\bot$ under RC that relies entirely on a series of classical, monotonic $\mathcal{EL}\bot$ subsumption tests. Therefore, any existing classical monotonic $\mathcal{EL}\bot$ reasoner can be used as a black box to implement our method. We then also adapt the method to one of the known extensions of RC for DLs, namely Defeasible Inheritance-based DLs without losing the computational tractability. |
Tasks | |
Published | 2018-02-22 |
URL | http://arxiv.org/abs/1802.08201v2 |
http://arxiv.org/pdf/1802.08201v2.pdf | |
PWC | https://paperswithcode.com/paper/a-polynomial-time-subsumption-algorithm-for |
Repo | |
Framework | |
Regularized Fuzzy Neural Networks to Aid Effort Forecasting in the Construction and Software Development
Title | Regularized Fuzzy Neural Networks to Aid Effort Forecasting in the Construction and Software Development |
Authors | Paulo Vitor de Campos Souza, Augusto Junio Guimaraes, Vanessa Souza Araujo, Thiago Silva Rezende, Vinicius Jonathan Silva Araujo |
Abstract | Predicting the time to build software is a very complex task for software engineering managers. There are complex factors that can directly interfere with the productivity of the development team. Factors directly related to the complexity of the system to be developed drastically change the time necessary for the completion of the works with the software factories. This work proposes the use of a hybrid system based on artificial neural networks and fuzzy systems to assist in the construction of an expert system based on rules to support in the prediction of hours destined to the development of software according to the complexity of the elements present in the same. The set of fuzzy rules obtained by the system helps the management and control of software development by providing a base of interpretable estimates based on fuzzy rules. The model was submitted to tests on a real database, and its results were promissory in the construction of an aid mechanism in the predictability of the software construction. |
Tasks | |
Published | 2018-12-04 |
URL | http://arxiv.org/abs/1812.01351v1 |
http://arxiv.org/pdf/1812.01351v1.pdf | |
PWC | https://paperswithcode.com/paper/regularized-fuzzy-neural-networks-to-aid |
Repo | |
Framework | |
SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection
Title | SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection |
Authors | Mohsen Yavartanoo, Eu Young Kim, Kyoung Mu Lee |
Abstract | We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D convolutional neural network (CNN) to estimate the object category followed by view ensemble, which combines the responses from multiple views of the object to further enhance the predictions. Specifically, the proposed approach consists of four stages: (1) Stereographic projection of a 3D object, (2) view-specific feature learning, (3) view selection and (4) view ensemble. The proposed approach performs comparably to the state-of-the-art methods while having substantially lower GPU memory as well as network parameters. Despite its lightness, the experiments on 3D object classification and shape retrievals demonstrate the high performance of the proposed method. |
Tasks | 3D Object Classification, Object Classification |
Published | 2018-11-05 |
URL | http://arxiv.org/abs/1811.01571v2 |
http://arxiv.org/pdf/1811.01571v2.pdf | |
PWC | https://paperswithcode.com/paper/spnet-deep-3d-object-classification-and |
Repo | |
Framework | |
Practical Bayesian Learning of Neural Networks via Adaptive Subgradient Methods
Title | Practical Bayesian Learning of Neural Networks via Adaptive Subgradient Methods |
Authors | Arnold Salas, Samuel Kessler, Stefan Zohren, Stephen Roberts |
Abstract | We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive subgradient algorithms such as Adagrad and Adam. We demonstrate the effectiveness of our Bayesian Adam method, Badam, by experimentally showing that the learnt uncertainties correctly relate to the weights’ predictive capabilities by weight pruning. We also demonstrate the quality of the derived uncertainty measures by comparing the performance of Badam to standard methods in a Thompson sampling setting for multi-armed bandits, where good uncertainty measures are required for an agent to balance exploration and exploitation. |
Tasks | Multi-Armed Bandits |
Published | 2018-11-08 |
URL | https://arxiv.org/abs/1811.03679v2 |
https://arxiv.org/pdf/1811.03679v2.pdf | |
PWC | https://paperswithcode.com/paper/practical-bayesian-learning-of-neural |
Repo | |
Framework | |
Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks
Title | Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks |
Authors | Siddharth Mahendran, Ming Yang Lu, Haider Ali, René Vidal |
Abstract | We consider the task of estimating the 3D orientation of an object of known category given an image of the object and a bounding box around it. Recently, CNN-based regression and classification methods have shown significant performance improvements for this task. This paper proposes a new CNN-based approach to monocular orientation estimation that advances the state of the art in four different directions. First, we take into account the Riemannian structure of the orientation space when designing regression losses and nonlinear activation functions. Second, we propose a mixed Riemannian regression and classification framework that better handles the challenging case of nearly symmetric objects. Third, we propose a data augmentation strategy that is specifically designed to capture changes in 3D orientation. Fourth, our approach leads to state-of-the-art results on the PASCAL3D+ dataset. |
Tasks | Data Augmentation |
Published | 2018-07-19 |
URL | http://arxiv.org/abs/1807.07226v1 |
http://arxiv.org/pdf/1807.07226v1.pdf | |
PWC | https://paperswithcode.com/paper/monocular-object-orientation-estimation-using |
Repo | |
Framework | |
Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method
Title | Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method |
Authors | Ashkan Esmaeili, Kayhan Behdin, Sina Al-E-Mohammad, Farokh Marvasti |
Abstract | In this paper, we propose a novel approach in order to recover a quantized matrix with missing information. We propose a regularized convex cost function composed of a log-likelihood term and a Trace norm term. The Bi-factorization approach and the Augmented Lagrangian Method (ALM) are applied to find the global minimizer of the cost function in order to recover the genuine data. We provide mathematical convergence analysis for our proposed algorithm. In the Numerical Experiments Section, we show the superiority of our method in accuracy and also its robustness in computational complexity compared to the state-of-the-art literature methods. |
Tasks | |
Published | 2018-10-07 |
URL | http://arxiv.org/abs/1810.03222v1 |
http://arxiv.org/pdf/1810.03222v1.pdf | |
PWC | https://paperswithcode.com/paper/recovering-quantized-data-with-missing |
Repo | |
Framework | |
Testing Optimality of Sequential Decision-Making
Title | Testing Optimality of Sequential Decision-Making |
Authors | Meik Dörpinghaus, Izaak Neri, Édgar Roldán, Heinrich Meyr, Frank Jülicher |
Abstract | This paper provides a statistical method to test whether a system that performs a binary sequential hypothesis test is optimal in the sense of minimizing the average decision times while taking decisions with given reliabilities. The proposed method requires samples of the decision times, the decision outcomes, and the true hypotheses, but does not require knowledge on the statistics of the observations or the properties of the decision-making system. The method is based on fluctuation relations for decision time distributions which are proved for sequential probability ratio tests. These relations follow from the martingale property of probability ratios and hold under fairly general conditions. We illustrate these tests with numerical experiments and discuss potential applications. |
Tasks | Decision Making |
Published | 2018-01-04 |
URL | http://arxiv.org/abs/1801.01574v1 |
http://arxiv.org/pdf/1801.01574v1.pdf | |
PWC | https://paperswithcode.com/paper/testing-optimality-of-sequential-decision |
Repo | |
Framework | |
Implicit Language Model in LSTM for OCR
Title | Implicit Language Model in LSTM for OCR |
Authors | Ekraam Sabir, Stephen Rawls, Prem Natarajan |
Abstract | Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current neural network techniques using LSTMs and the previous state-of-the-art HMM systems is that HMM systems have a strong independence assumption. In comparison LSTMs have no explicit constraints on the amount of context that can be considered during decoding. In this paper we show that they learn an implicit LM and attempt to characterize the strength of the LM in terms of equivalent n-gram context. We show that this implicitly learned language model provides a 2.4% CER improvement on our synthetic test set when compared against a test set of random characters (i.e. not naturally occurring sequences), and that the LSTM learns to use up to 5 characters of context (which is roughly 88 frames in our configuration). We believe that this is the first ever attempt at characterizing the strength of the implicit LM in LSTM based OCR systems. |
Tasks | Language Modelling, Optical Character Recognition |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09441v1 |
http://arxiv.org/pdf/1805.09441v1.pdf | |
PWC | https://paperswithcode.com/paper/implicit-language-model-in-lstm-for-ocr |
Repo | |
Framework | |
Unsupervised Word Segmentation from Speech with Attention
Title | Unsupervised Word Segmentation from Speech with Attention |
Authors | Pierre Godard, Marcely Zanon-Boito, Lucas Ondel, Alexandre Berard, François Yvon, Aline Villavicencio, Laurent Besacier |
Abstract | We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illustrate the potential of attentional word segmentation for language documentation. |
Tasks | Machine Translation |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06734v1 |
http://arxiv.org/pdf/1806.06734v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-word-segmentation-from-speech |
Repo | |
Framework | |
IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
Title | IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection |
Authors | Qiangpeng Yang, Mengli Cheng, Wenmeng Zhou, Yan Chen, Minghui Qiu, Wei Lin, Wei Chu |
Abstract | Incidental scene text detection, especially for multi-oriented text regions, is one of the most challenging tasks in many computer vision applications. Different from the common object detection task, scene text often suffers from a large variance of aspect ratio, scale, and orientation. To solve this problem, we propose a novel end-to-end scene text detector IncepText from an instance-aware segmentation perspective. We design a novel Inception-Text module and introduce deformable PSROI pooling to deal with multi-oriented text detection. Extensive experiments on ICDAR2015, RCTW-17, and MSRA-TD500 datasets demonstrate our method’s superiority in terms of both effectiveness and efficiency. Our proposed method achieves 1st place result on ICDAR2015 challenge and the state-of-the-art performance on other datasets. Moreover, we have released our implementation as an OCR product which is available for public access. |
Tasks | Multi-Oriented Scene Text Detection, Object Detection, Optical Character Recognition, Scene Text Detection |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01167v2 |
http://arxiv.org/pdf/1805.01167v2.pdf | |
PWC | https://paperswithcode.com/paper/inceptext-a-new-inception-text-module-with |
Repo | |
Framework | |
Identification of physical processes via combined data-driven and data-assimilation methods
Title | Identification of physical processes via combined data-driven and data-assimilation methods |
Authors | Haibin Chang, Dongxiao Zhang |
Abstract | With the advent of modern data collection and storage technologies, data-driven approaches have been developed for discovering the governing partial differential equations (PDE) of physical problems. However, in the extant works the model parameters in the equations are either assumed to be known or have a linear dependency. Therefore, most of the realistic physical processes cannot be identified with the current data-driven PDE discovery approaches. In this study, an innovative framework is developed that combines data-driven and data-assimilation methods for simultaneously identifying physical processes and inferring model parameters. Spatiotemporal measurement data are first divided into a training data set and a testing data set. Using the training data set, a data-driven method is developed to learn the governing equation of the considered physical problem by identifying the occurred (or dominated) processes and selecting the proper empirical model. Through introducing a prediction error of the learned governing equation for the testing data set, a data-assimilation method is devised to estimate the uncertain model parameters of the selected empirical model. For the contaminant transport problem investigated, the results demonstrate that the proposed method can adequately identify the considered physical processes via concurrently discovering the corresponding governing equations and inferring uncertain parameters of nonlinear models, even in the presence of measurement errors. This work helps to broaden the applicable area of the research of data driven discovery of governing equations of physical problems. |
Tasks | |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.11977v1 |
http://arxiv.org/pdf/1810.11977v1.pdf | |
PWC | https://paperswithcode.com/paper/identification-of-physical-processes-via |
Repo | |
Framework | |
Encoding Motion Primitives for Autonomous Vehicles using Virtual Velocity Constraints and Neural Network Scheduling
Title | Encoding Motion Primitives for Autonomous Vehicles using Virtual Velocity Constraints and Neural Network Scheduling |
Authors | Mogens Graf Plessen |
Abstract | Within the context of trajectory planning for autonomous vehicles this paper proposes methods for efficient encoding of motion primitives in neural networks on top of model-based and gradient-free reinforcement learning. It is distinguished between 5 core aspects: system model, network architecture, training algorithm, training tasks selection and hardware/software implementation. For the system model, a kinematic (3-states-2-controls) and a dynamic (16-states-2-controls) vehicle model are compared. For the network architecture, 3 feedforward structures are compared including weighted skip connections. For the training algorithm, virtual velocity constraints and network scheduling are proposed. For the training tasks, different feature vector selections are discussed. For the implementation, aspects of gradient-free learning using 1 GPU and the handling of perturbation noise therefore are discussed. The effects of proposed methods are illustrated in experiments encoding up to 14625 motion primitives. The capabilities of tiny neural networks with as few as 10 scalar parameters when scheduled on vehicle velocity are emphasized. |
Tasks | Autonomous Vehicles |
Published | 2018-07-05 |
URL | http://arxiv.org/abs/1807.02187v2 |
http://arxiv.org/pdf/1807.02187v2.pdf | |
PWC | https://paperswithcode.com/paper/encoding-motion-primitives-for-autonomous |
Repo | |
Framework | |
Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples Only
Title | Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples Only |
Authors | Tianhang Zheng, Changyou Chen, Kui Ren |
Abstract | Recent work on adversarial attack and defense suggests that PGD is a universal $l_\infty$ first-order attack, and PGD adversarial training can significantly improve network robustness against a wide range of first-order $l_\infty$-bounded attacks, represented as the state-of-the-art defense method. However, an obvious weakness of PGD adversarial training is its highly-computational cost in generating adversarial samples, making it computationally infeasible for large and high-resolution real datasets such as the ImageNet dataset. In addition, recent work also has suggested a simple “close-form” solution to a robust model on MNIST. Therefore, a natural question raised is that is PGD adversarial training really necessary for robust defense? In this paper, we give a negative answer by proposing a training paradigm that is comparable to PGD adversarial training on several standard datasets, while only using noisy-natural samples. Specifically, we reformulate the min-max objective in PGD adversarial training by a problem to minimize the original network loss plus $l_1$ norms of its gradients w.r.t. the inputs. For the $l_1$-norm loss, we propose a computationally-feasible solution by embedding a differentiable soft-quantization layer after the network input layer. We show formally that the soft-quantization layer trained with noisy-natural samples is an alternative approach to minimizing the $l_1$-gradient norms as in PGD adversarial training. Extensive empirical evaluations on standard datasets show that our proposed models are comparable to PGD-adversarially-trained models under PGD and BPDA attacks. Remarkably, our method achieves a 24X speed-up on MNIST while maintaining a comparable defensive ability, and for the first time fine-tunes a robust Imagenet model within only two days. Code is provided on \url{https://github.com/tianzheng4/Noisy-Training-Soft-Quantization} |
Tasks | Adversarial Attack, Quantization |
Published | 2018-10-10 |
URL | http://arxiv.org/abs/1810.05665v2 |
http://arxiv.org/pdf/1810.05665v2.pdf | |
PWC | https://paperswithcode.com/paper/is-pgd-adversarial-training-necessary |
Repo | |
Framework | |
The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA
Title | The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA |
Authors | Shailza Jolly, Sandro Pezzelle, Tassilo Klein, Andreas Dengel, Moin Nabi |
Abstract | We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected by the Majority (MA) of annotators. Second, it does not account for the quantitative Subjectivity (S) of the answers in the sample (and dataset). Third, information about the Semantic Similarity (SES) of the responses is completely neglected. Based on such limitations, we propose a multi-component metric that accounts for all these issues. We show that our metric is effective in providing a more fine-grained evaluation both on the quantitative and qualitative level. |
Tasks | Question Answering, Semantic Similarity, Semantic Textual Similarity, Visual Question Answering |
Published | 2018-09-12 |
URL | http://arxiv.org/abs/1809.04344v1 |
http://arxiv.org/pdf/1809.04344v1.pdf | |
PWC | https://paperswithcode.com/paper/the-wisdom-of-masses-majority-subjectivity |
Repo | |
Framework | |
An Efficient Approach to Learning Chinese Judgment Document Similarity Based on Knowledge Summarization
Title | An Efficient Approach to Learning Chinese Judgment Document Similarity Based on Knowledge Summarization |
Authors | Yinglong Ma, Peng Zhang, Jiangang Ma |
Abstract | A previous similar case in common law systems can be used as a reference with respect to the current case such that identical situations can be treated similarly in every case. However, current approaches for judgment document similarity computation failed to capture the core semantics of judgment documents and therefore suffer from lower accuracy and higher computation complexity. In this paper, a knowledge block summarization based machine learning approach is proposed to compute the semantic similarity of Chinese judgment documents. By utilizing domain ontologies for judgment documents, the core semantics of Chinese judgment documents is summarized based on knowledge blocks. Then the WMD algorithm is used to calculate the similarity between knowledge blocks. At last, the related experiments were made to illustrate that our approach is very effective and efficient in achieving higher accuracy and faster computation speed in comparison with the traditional approaches. |
Tasks | Semantic Similarity, Semantic Textual Similarity |
Published | 2018-08-06 |
URL | http://arxiv.org/abs/1808.01843v1 |
http://arxiv.org/pdf/1808.01843v1.pdf | |
PWC | https://paperswithcode.com/paper/an-efficient-approach-to-learning-chinese |
Repo | |
Framework | |