Paper Group ANR 96
Incentivizing the Emergence of Grounded Discrete Communication Between General Agents. Text Similarity Using Word Embeddings to Classify Misinformation. Improved Binary Artificial Bee Colony Algorithm. Mathematical Formulae in Wikimedia Projects 2020. Analyzing Accuracy Loss in Randomized Smoothing Defenses. Will we ever have Conscious Machines?. O …
Incentivizing the Emergence of Grounded Discrete Communication Between General Agents
| Title | Incentivizing the Emergence of Grounded Discrete Communication Between General Agents |
| Authors | Thomas A. Unger, Elia Bruni |
| Abstract | We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques are sufficient to incentivize the emergence of a grounded discrete communication protocol between general agents. This is in contrast to previous experiments that employed straight-through estimation or tailored inductive biases. Our results show that these can indeed be avoided, by instead providing proper environmental incentives. Moreover, they show that a longer interval between communications incentivized more abstract semantics. In some cases, the communicating agents adapted to new environments more quickly than monolithic agents, showcasing the potential of emergent discrete communication for transfer learning. |
| Tasks | Transfer Learning |
| Published | 2020-01-06 |
| URL | https://arxiv.org/abs/2001.01772v1 |
| https://arxiv.org/pdf/2001.01772v1.pdf | |
| PWC | https://paperswithcode.com/paper/incentivizing-the-emergence-of-grounded |
| Repo | |
| Framework | |
Text Similarity Using Word Embeddings to Classify Misinformation
| Title | Text Similarity Using Word Embeddings to Classify Misinformation |
| Authors | Caio Almeida, Débora Santos |
| Abstract | Fake news is a growing problem in the last years, especially during elections. It’s hard work to identify what is true and what is false among all the user generated content that circulates every day. Technology can help with that work and optimize the fact-checking process. In this work, we address the challenge of finding similar content in order to be able to suggest to a fact-checker articles that could have been verified before and thus avoid that the same information is verified more than once. This is especially important in collaborative approaches to fact-checking where members of large teams will not know what content others have already fact-checked. |
| Tasks | Word Embeddings |
| Published | 2020-03-14 |
| URL | https://arxiv.org/abs/2003.06634v1 |
| https://arxiv.org/pdf/2003.06634v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-similarity-using-word-embeddings-to |
| Repo | |
| Framework | |
Improved Binary Artificial Bee Colony Algorithm
| Title | Improved Binary Artificial Bee Colony Algorithm |
| Authors | Rafet Durgut |
| Abstract | The Artificial Bee Colony (ABC) algorithm is an evolutionary optimization algorithm based on swarm intelligence and inspired by the honey bees’ food search behavior. Since the ABC algorithm has been developed to achieve optimal solutions by searching in the continuous search space, modification is required to apply this method to binary optimization problems. In this paper, we improve the ABC algorithm to solve binary optimization problems and call it the improved binary Artificial Bee Colony (ibinABC). The proposed method consists of an update mechanism based on fitness values and processing different number of decision variables. Thus, we aim to prevent the ABC algorithm from getting stuck in a local minimum by increasing its exploration ability. We compare the ibinABC algorithm with three variants of the ABC and other meta-heuristic algorithms in the literature. For comparison, we use the wellknown OR-Library dataset containing 15 problem instances prepared for the uncapacitated facility location problem. Computational results show that the proposed method is superior to other methods in terms of convergence speed and robustness. The source code of the algorithm will be available on GitHub after reviewing process |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.11641v1 |
| https://arxiv.org/pdf/2003.11641v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-binary-artificial-bee-colony |
| Repo | |
| Framework | |
Mathematical Formulae in Wikimedia Projects 2020
| Title | Mathematical Formulae in Wikimedia Projects 2020 |
| Authors | Moritz Schubotz, André Greiner-Petter, Norman Meuschke, Olaf Teschke, Bela Gipp |
| Abstract | This poster summarizes our contributions to Wikimedia’s processing pipeline for mathematical formulae. We describe how we have supported the transition from rendering formulae as course-grained PNG images in 2001 to providing modern semantically enriched language-independent MathML formulae in 2020. Additionally, we describe our plans to improve the accessibility and discoverability of mathematical knowledge in Wikimedia projects further. |
| Tasks | |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09417v1 |
| https://arxiv.org/pdf/2003.09417v1.pdf | |
| PWC | https://paperswithcode.com/paper/mathematical-formulae-in-wikimedia-projects |
| Repo | |
| Framework | |
Analyzing Accuracy Loss in Randomized Smoothing Defenses
| Title | Analyzing Accuracy Loss in Randomized Smoothing Defenses |
| Authors | Yue Gao, Harrison Rosenberg, Kassem Fawaz, Somesh Jha, Justin Hsu |
| Abstract | Recent advances in machine learning (ML) algorithms, especially deep neural networks (DNNs), have demonstrated remarkable success (sometimes exceeding human-level performance) on several tasks, including face and speech recognition. However, ML algorithms are vulnerable to \emph{adversarial attacks}, such test-time, training-time, and backdoor attacks. In test-time attacks an adversary crafts adversarial examples, which are specially crafted perturbations imperceptible to humans which, when added to an input example, force a machine learning model to misclassify the given input example. Adversarial examples are a concern when deploying ML algorithms in critical contexts, such as information security and autonomous driving. Researchers have responded with a plethora of defenses. One promising defense is \emph{randomized smoothing} in which a classifier’s prediction is smoothed by adding random noise to the input example we wish to classify. In this paper, we theoretically and empirically explore randomized smoothing. We investigate the effect of randomized smoothing on the feasible hypotheses space, and show that for some noise levels the set of hypotheses which are feasible shrinks due to smoothing, giving one reason why the natural accuracy drops after smoothing. To perform our analysis, we introduce a model for randomized smoothing which abstracts away specifics, such as the exact distribution of the noise. We complement our theoretical results with extensive experiments. |
| Tasks | Autonomous Driving, Speech Recognition |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01595v1 |
| https://arxiv.org/pdf/2003.01595v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-accuracy-loss-in-randomized |
| Repo | |
| Framework | |
Will we ever have Conscious Machines?
| Title | Will we ever have Conscious Machines? |
| Authors | Patrick Krauss, Andreas Maier |
| Abstract | The question of whether artificial beings or machines could become self-aware or consciousness has been a philosophical question for centuries. The main problem is that self-awareness cannot be observed from an outside perspective and the distinction of whether something is really self-aware or merely a clever program that pretends to do so cannot be answered without access to accurate knowledge about the mechanism’s inner workings. We review the current state-of-the-art regarding these developments and investigate common machine learning approaches with respect to their potential ability to become self-aware. We realise that many important algorithmic steps towards machines with a core consciousness have already been devised. For human-level intelligence, however, many additional techniques have to be discovered. |
| Tasks | |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2003.14132v1 |
| https://arxiv.org/pdf/2003.14132v1.pdf | |
| PWC | https://paperswithcode.com/paper/will-we-ever-have-conscious-machines |
| Repo | |
| Framework | |
On Calibration Neural Networks for extracting implied information from American options
| Title | On Calibration Neural Networks for extracting implied information from American options |
| Authors | Shuaiqiang Liu, Álvaro Leitao, Anastasia Borovykh, Cornelis W. Oosterlee |
| Abstract | Extracting implied information, like volatility and/or dividend, from observed option prices is a challenging task when dealing with American options, because of the computational costs needed to solve the corresponding mathematical problem many thousands of times. We will employ a data-driven machine learning approach to estimate the Black-Scholes implied volatility and the dividend yield for American options in a fast and robust way. To determine the implied volatility, the inverse function is approximated by an artificial neural network on the computational domain of interest, which decouples the offline (training) and online (prediction) phases and thus eliminates the need for an iterative process. For the implied dividend yield, we formulate the inverse problem as a calibration problem and determine simultaneously the implied volatility and dividend yield. For this, a generic and robust calibration framework, the Calibration Neural Network (CaNN), is introduced to estimate multiple parameters. It is shown that machine learning can be used as an efficient numerical technique to extract implied information from American options. |
| Tasks | Calibration |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2001.11786v1 |
| https://arxiv.org/pdf/2001.11786v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-calibration-neural-networks-for-extracting |
| Repo | |
| Framework | |
SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks
| Title | SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks |
| Authors | Sungho Shin, Yoonho Boo, Wonyong Sung |
| Abstract | Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generalization capability of DNNs, especially when the loss surface for training contains many sharp minima. We present a new quantized neural network optimization approach, stochastic quantized weight averaging (SQWA), to design low-precision DNNs with good generalization capability using model averaging. The proposed approach includes (1) floating-point model training, (2) direct quantization of weights, (3) capturing multiple low-precision models during retraining with cyclical learning rates, (4) averaging the captured models, and (5) re-quantizing the averaged model and fine-tuning it with low-learning rates. Additionally, we present a loss-visualization technique on the quantized weight domain to clearly elucidate the behavior of the proposed method. Visualization results indicate that a quantized DNN (QDNN) optimized with the proposed approach is located near the center of the flat minimum in the loss surface. With SQWA training, we achieved state-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets. Although we only employed a uniform quantization scheme for the sake of implementation in VLSI or low-precision neural processing units, the performance achieved exceeded those of previous studies employing non-uniform quantization. |
| Tasks | Quantization |
| Published | 2020-02-02 |
| URL | https://arxiv.org/abs/2002.00343v1 |
| https://arxiv.org/pdf/2002.00343v1.pdf | |
| PWC | https://paperswithcode.com/paper/sqwa-stochastic-quantized-weight-averaging |
| Repo | |
| Framework | |
Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention
| Title | Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention |
| Authors | Xuhua Ren, Jiayu Huo, Kai Xuan, Dongming Wei, Lichi Zhang, Qian Wang |
| Abstract | Brain magnetic resonance (MR) segmentation for hydrocephalus patients is considered as a challenging work. Encoding the variation of the brain anatomical structures from different individuals cannot be easily achieved. The task becomes even more difficult especially when the image data from hydrocephalus patients are considered, which often have large deformations and differ significantly from the normal subjects. Here, we propose a novel strategy with hard and soft attention modules to solve the segmentation problems for hydrocephalus MR images. Our main contributions are three-fold: 1) the hard-attention module generates coarse segmentation map using multi-atlas-based method and the VoxelMorph tool, which guides subsequent segmentation process and improves its robustness; 2) the soft-attention module incorporates position attention to capture precise context information, which further improves the segmentation accuracy; 3) we validate our method by segmenting insula, thalamus and many other regions-of-interests (ROIs) that are critical to quantify brain MR images of hydrocephalus patients in real clinical scenario. The proposed method achieves much improved robustness and accuracy when segmenting all 17 consciousness-related ROIs with high variations for different subjects. To the best of our knowledge, this is the first work to employ deep learning for solving the brain segmentation problems of hydrocephalus patients. |
| Tasks | Brain Segmentation, Semantic Segmentation |
| Published | 2020-01-12 |
| URL | https://arxiv.org/abs/2001.03857v1 |
| https://arxiv.org/pdf/2001.03857v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-brain-magnetic-resonance-image |
| Repo | |
| Framework | |
Deep generative models in DataSHIELD
| Title | Deep generative models in DataSHIELD |
| Authors | Stefan Lenz, Harald Binder |
| Abstract | The best way to calculate statistics from medical data is to use the data of individual patients. In some settings, this data is difficult to obtain due to privacy restrictions. In Germany, for example, it is not possible to pool routine data from different hospitals for research purposes without the consent of the patients. The DataSHIELD software provides an infrastructure and a set of statistical methods for joint analyses of distributed data. The contained algorithms are reformulated to work with aggregated data from the participating sites instead of the individual data. If a desired algorithm is not implemented in DataSHIELD or cannot be reformulated in such a way, using artificial data is an alternative. We present a methodology together with a software implementation that builds on DataSHIELD to create artificial data that preserve complex patterns from distributed individual patient data. Such data sets of artificial patients, which are not linked to real patients, can then be used for joint analyses. We use deep Boltzmann machines (DBMs) as generative models for capturing the distribution of data. For the implementation, we employ the package “BoltzmannMachines” from the Julia programming language and wrap it for use with DataSHIELD, which is based on R. As an exemplary application, we conduct a distributed analysis with DBMs on a synthetic data set, which simulates genetic variant data. Patterns from the original data can be recovered in the artificial data using hierarchical clustering of the virtual patients, demonstrating the feasibility of the approach. Our implementation adds to DataSHIELD the ability to generate artificial data that can be used for various analyses, e. g. for pattern recognition with deep learning. This also demonstrates more generally how DataSHIELD can be flexibly extended with advanced algorithms from languages other than R. |
| Tasks | |
| Published | 2020-03-11 |
| URL | https://arxiv.org/abs/2003.07775v1 |
| https://arxiv.org/pdf/2003.07775v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-generative-models-in-datashield |
| Repo | |
| Framework | |
Bayesian Hierarchical Multi-Objective Optimization for Vehicle Parking Route Discovery
| Title | Bayesian Hierarchical Multi-Objective Optimization for Vehicle Parking Route Discovery |
| Authors | Romit S Beed, Sunita Sarkar, Arindam Roy |
| Abstract | Discovering an optimal route to the most feasible parking lot has been a matter of concern for any driver which aggravates further during peak hours of the day and at congested places leading to considerable wastage of time and fuel. This paper proposes a Bayesian hierarchical technique for obtaining the most optimal route to a parking lot. The route selection is based on conflicting objectives and hence the problem belongs to the domain of multi-objective optimization. A probabilistic data driven method has been used to overcome the inherent problem of weight selection in the popular weighted sum technique. The weights of these conflicting objectives have been refined using a Bayesian hierarchical model based on Multinomial and Dirichlet prior. Genetic algorithm has been used to obtain optimal solutions. Simulated data has been used to obtain routes which are in close agreement with real life situations. |
| Tasks | |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12508v1 |
| https://arxiv.org/pdf/2003.12508v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-hierarchical-multi-objective |
| Repo | |
| Framework | |
Keeping it simple: Implementation and performance of the proto-principle of adaptation and learning in the language sciences
| Title | Keeping it simple: Implementation and performance of the proto-principle of adaptation and learning in the language sciences |
| Authors | Petar Milin, Harish Tayyar Madabushi, Michael Croucher, Dagmar Divjak |
| Abstract | In this paper we present the Widrow-Hoff rule and its applications to language data. After contextualizing the rule historically and placing it in the chain of neurally inspired artificial learning models, we explain its rationale and implementational considerations. Using a number of case studies we illustrate how the Widrow-Hoff rule offers unexpected opportunities for the computational simulation of a range of language phenomena that make it possible to approach old problems from a novel perspective. |
| Tasks | |
| Published | 2020-03-08 |
| URL | https://arxiv.org/abs/2003.03813v1 |
| https://arxiv.org/pdf/2003.03813v1.pdf | |
| PWC | https://paperswithcode.com/paper/keeping-it-simple-implementation-and |
| Repo | |
| Framework | |
Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
| Title | Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework |
| Authors | Yaochen Zhu, Jiayi Xie, Zhenzhong Chen |
| Abstract | As an emerging type of user-generated content, micro-video drastically enriches people’s entertainment experiences and social interactions. However, the popularity pattern of an individual micro-video still remains elusive among the researchers. One of the major challenges is that the potential popularity of a micro-video tends to fluctuate under the impact of various external factors, which makes it full of uncertainties. In addition, since micro-videos are mainly uploaded by individuals that lack professional techniques, multiple types of noise could exist that obscure useful information. In this paper, we propose a multimodal variational encoder-decoder (MMVED) framework for micro-video popularity prediction tasks. MMVED learns a stochastic Gaussian embedding of a micro-video that is informative to its popularity level while preserves the inherent uncertainties simultaneously. Moreover, through the optimization of a deep variational information bottleneck lower-bound (IBLBO), the learned hidden representation is shown to be maximally expressive about the popularity target while maximally compressive to the noise in micro-video features. Furthermore, the Bayesian product-of-experts principle is applied to the multimodal encoder, where the decision for information keeping or discarding is made comprehensively with all available modalities. Extensive experiments conducted on a public dataset and a dataset we collect from Xigua demonstrate the effectiveness of the proposed MMVED framework. |
| Tasks | |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12724v1 |
| https://arxiv.org/pdf/2003.12724v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-popularity-of-micro-videos |
| Repo | |
| Framework | |
Fast Compliance Checking with General Vocabularies
| Title | Fast Compliance Checking with General Vocabularies |
| Authors | P. A. Bonatti, L. Ioffredo, I. M. Petrova, L. Sauro |
| Abstract | We address the problem of complying with the GDPR while processing and transferring personal data on the web. For this purpose we introduce an extensible profile of OWL2 for representing data protection policies. With this language, a company’s data usage policy can be checked for compliance with data subjects’ consent and with a formalized fragment of the GDPR by means of subsumption queries. The outer structure of the policies is restricted in order to make compliance checking highly scalable, as required when processing high-frequency data streams or large data volumes. However, the vocabularies for specifying policy properties can be chosen rather freely from expressive Horn fragments of OWL2. We exploit IBQ reasoning to integrate specialized reasoners for the policy language and the vocabulary’s language. Our experiments show that this approach significantly improves performance. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.06322v1 |
| https://arxiv.org/pdf/2001.06322v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-compliance-checking-with-general |
| Repo | |
| Framework | |
OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning
| Title | OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning |
| Authors | Shuo Wang, Tianle Chen, Shangyu Chen, Carsten Rudolph, Surya Nepal, Marthie Grobler |
| Abstract | Anomaly detection aims to recognize samples with anomalous and unusual patterns with respect to a set of normal data. This is significant for numerous domain applications, such as industrial inspection, medical imaging, and security enforcement. There are two key research challenges associated with existing anomaly detection approaches: (1) many approaches perform well on low-dimensional problems however the performance on high-dimensional instances, such as images, is limited; (2) many approaches often rely on traditional supervised approaches and manual engineering of features, while the topic has not been fully explored yet using modern deep learning approaches, even when the well-label samples are limited. In this paper, we propose a One-for-all Image Anomaly Detection system (OIAD) based on disentangled learning using only clean samples. Our key insight is that the impact of small perturbation on the latent representation can be bounded for normal samples while anomaly images are usually outside such bounded intervals, referred to as structure consistency. We implement this idea and evaluate its performance for anomaly detection. Our experiments with three datasets show that OIAD can detect over $90%$ of anomalies while maintaining a low false alarm rate. It can also detect suspicious samples from samples labeled as clean, coincided with what humans would deem unusual. |
| Tasks | Anomaly Detection |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.06640v2 |
| https://arxiv.org/pdf/2001.06640v2.pdf | |
| PWC | https://paperswithcode.com/paper/oiad-one-for-all-image-anomaly-detection-with |
| Repo | |
| Framework | |
