April 3, 2020

2920 words 14 mins read

Paper Group ANR 40

Paper Group ANR 40

Probabilistic learning of boolean functions applied to the binary classification problem with categorical covariates. Using wavelets to analyze similarities in image datasets. Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation. k-means++: few more steps yield constant approxima …

Probabilistic learning of boolean functions applied to the binary classification problem with categorical covariates

Title Probabilistic learning of boolean functions applied to the binary classification problem with categorical covariates
Authors Paulo Hubert
Abstract In this work we cast the problem of binary classification in terms of estimating a partition on Bernoulli data. When the explanatory variables are all categorical, the problem can be modelled using the language of boolean functions. We offer a probabilistic analysis of the problem, and propose two algorithms for learning boolean functions from binary data.
Tasks
Published 2020-03-20
URL https://arxiv.org/abs/2003.09454v1
PDF https://arxiv.org/pdf/2003.09454v1.pdf
PWC https://paperswithcode.com/paper/probabilistic-learning-of-boolean-functions
Repo
Framework

Using wavelets to analyze similarities in image datasets

Title Using wavelets to analyze similarities in image datasets
Authors Roozbeh Yousefzadeh
Abstract Deep learning image classifiers usually rely on huge training sets and their training process can be described as learning the similarities and differences among training images. But, images in large training sets are not usually studied from this perspective and fine-level similarities and differences among images is usually overlooked. Some studies aim to identify the influential and redundant training images, but such methods require a model that is already trained on the entire training set. Here, we show that analyzing the contents of large training sets can provide valuable insights about the classification task at hand, prior to training a model on them. We use wavelet decomposition of images and other image processing tools to perform such analysis, with no need for a pre-trained model. This makes the analysis of training sets, straightforward and fast. We show that similar images in standard datasets (such as CIFAR) can be identified in a few seconds, a significant speed-up compared to alternative methods in the literature. We also show that similarities between training and testing images may explain the generalization of models and their mistakes. Finally, we investigate the similarities between images in relation to decision boundaries of a trained model.
Tasks
Published 2020-02-24
URL https://arxiv.org/abs/2002.10257v1
PDF https://arxiv.org/pdf/2002.10257v1.pdf
PWC https://paperswithcode.com/paper/using-wavelets-to-analyze-similarities-in
Repo
Framework

Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation

Title Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
Authors Arnulf Jentzen, Timo Welti
Abstract In spite of the accomplishments of deep learning based algorithms in numerous applications and very broad corresponding research interest, at the moment there is still no rigorous understanding of the reasons why such algorithms produce useful results in certain situations. A thorough mathematical analysis of deep learning based algorithms seems to be crucial in order to improve our understanding and to make their implementation more effective and efficient. In this article we provide a mathematically rigorous full error analysis of deep learning based empirical risk minimisation with quadratic loss function in the probabilistically strong sense, where the underlying deep neural networks are trained using stochastic gradient descent with random initialisation. The convergence speed we obtain is presumably far from optimal and suffers under the curse of dimensionality. To the best of our knowledge, we establish, however, the first full error analysis in the scientific literature for a deep learning based algorithm in the probabilistically strong sense and, moreover, the first full error analysis in the scientific literature for a deep learning based algorithm where stochastic gradient descent with random initialisation is the employed optimisation method.
Tasks
Published 2020-03-03
URL https://arxiv.org/abs/2003.01291v1
PDF https://arxiv.org/pdf/2003.01291v1.pdf
PWC https://paperswithcode.com/paper/overall-error-analysis-for-the-training-of
Repo
Framework

k-means++: few more steps yield constant approximation

Title k-means++: few more steps yield constant approximation
Authors Davin Choo, Christoph Grunau, Julian Portmann, Václav Rozhoň
Abstract The k-means++ algorithm of Arthur and Vassilvitskii (SODA 2007) is a state-of-the-art algorithm for solving the k-means clustering problem and is known to give an O(log k)-approximation in expectation. Recently, Lattanzi and Sohler (ICML 2019) proposed augmenting k-means++ with O(k log log k) local search steps to yield a constant approximation (in expectation) to the k-means clustering problem. In this paper, we improve their analysis to show that, for any arbitrarily small constant $\eps > 0$, with only $\eps k$ additional local search steps, one can achieve a constant approximation guarantee (with high probability in k), resolving an open problem in their paper.
Tasks
Published 2020-02-18
URL https://arxiv.org/abs/2002.07784v1
PDF https://arxiv.org/pdf/2002.07784v1.pdf
PWC https://paperswithcode.com/paper/k-means-few-more-steps-yield-constant
Repo
Framework

Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems

Title Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems
Authors Nader Karballaeezadeh, Farah Zaremotekhases, Shahaboddin Shamshirband, Amir Mosavi, Narjes Nabipour, Peter Csiba, Annamaria R. Varkonyi-Koczy
Abstract Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods. This paper proposes novel machine learning models for intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well as their hybrids, i.e., Levenberg-Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), and standard error (SD). The CMIS model outperforms other models with the promising results of APRE=2.3303, AAPRE=11.6768, RMSE=12.0056, and SD=0.0210.
Tasks
Published 2020-01-18
URL https://arxiv.org/abs/2001.08583v1
PDF https://arxiv.org/pdf/2001.08583v1.pdf
PWC https://paperswithcode.com/paper/intelligent-road-inspection-with-advanced
Repo
Framework

Towards Time-Aware Context-Aware Deep Trust Prediction in Online Social Networks

Title Towards Time-Aware Context-Aware Deep Trust Prediction in Online Social Networks
Authors Seyed Mohssen Ghafari
Abstract Trust can be defined as a measure to determine which source of information is reliable and with whom we should share or from whom we should accept information. There are several applications for trust in Online Social Networks (OSNs), including social spammer detection, fake news detection, retweet behaviour detection and recommender systems. Trust prediction is the process of predicting a new trust relation between two users who are not currently connected. In applications of trust, trust relations among users need to be predicted. This process faces many challenges, such as the sparsity of user-specified trust relations, the context-awareness of trust and changes in trust values over time. In this dissertation, we analyse the state-of-the-art in pair-wise trust prediction models in OSNs. We discuss three main challenges in this domain and present novel trust prediction approaches to address them. We first focus on proposing a low-rank representation of users that incorporates users’ personality traits as additional information. Then, we propose a set of context-aware trust prediction models. Finally, by considering the time-dependency of trust relations, we propose a dynamic deep trust prediction approach. We design and implement five pair-wise trust prediction approaches and evaluate them with real-world datasets collected from OSNs. The experimental results demonstrate the effectiveness of our approaches compared to other state-of-the-art pair-wise trust prediction models.
Tasks Fake News Detection, Recommendation Systems
Published 2020-03-21
URL https://arxiv.org/abs/2003.09543v1
PDF https://arxiv.org/pdf/2003.09543v1.pdf
PWC https://paperswithcode.com/paper/towards-time-aware-context-aware-deep-trust
Repo
Framework

SAFE: Similarity-Aware Multi-Modal Fake News Detection

Title SAFE: Similarity-Aware Multi-Modal Fake News Detection
Authors Xinyi Zhou, Jindi Wu, Reza Zafarani
Abstract Effective detection of fake news has recently attracted significant attention. Current studies have made significant contributions to predicting fake news with less focus on exploiting the relationship (similarity) between the textual and visual information in news articles. Attaching importance to such similarity helps identify fake news stories that, for example, attempt to use irrelevant images to attract readers’ attention. In this work, we propose a $\mathsf{S}$imilarity-$\mathsf{A}$ware $\mathsf{F}$ak$\mathsf{E}$ news detection method ($\mathsf{SAFE}$) which investigates multi-modal (textual and visual) information of news articles. First, neural networks are adopted to separately extract textual and visual features for news representation. We further investigate the relationship between the extracted features across modalities. Such representations of news textual and visual information along with their relationship are jointly learned and used to predict fake news. The proposed method facilitates recognizing the falsity of news articles based on their text, images, or their “mismatches.” We conduct extensive experiments on large-scale real-world data, which demonstrate the effectiveness of the proposed method.
Tasks Fake News Detection
Published 2020-02-19
URL https://arxiv.org/abs/2003.04981v1
PDF https://arxiv.org/pdf/2003.04981v1.pdf
PWC https://paperswithcode.com/paper/safe-similarity-aware-multi-modal-fake-news
Repo
Framework

Fake News Detection by means of Uncertainty Weighted Causal Graphs

Title Fake News Detection by means of Uncertainty Weighted Causal Graphs
Authors Eduardo C. Garrido-Merchán, Cristina Puente, Rafael Palacios
Abstract Society is experimenting changes in information consumption, as new information channels such as social networks let people share news that do not necessarily be trust worthy. Sometimes, these sources of information produce fake news deliberately with doubtful purposes and the consumers of that information share it to other users thinking that the information is accurate. This transmission of information represents an issue in our society, as can influence negatively the opinion of people about certain figures, groups or ideas. Hence, it is desirable to design a system that is able to detect and classify information as fake and categorize a source of information as trust worthy or not. Current systems experiment difficulties performing this task, as it is complicated to design an automatic procedure that can classify this information independent on the context. In this work, we propose a mechanism to detect fake news through a classifier based on weighted causal graphs. These graphs are specific hybrid models that are built through causal relations retrieved from texts and consider the uncertainty of causal relations. We take advantage of this representation to use the probability distributions of this graph and built a fake news classifier based on the entropy and KL divergence of learned and new information. We believe that the problem of fake news is accurately tackled by this model due to its hybrid nature between a symbolic and quantitative methodology. We describe the methodology of this classifier and add empirical evidence of the usefulness of our proposed approach in the form of synthetic experiments and a real experiment involving lung cancer.
Tasks Fake News Detection
Published 2020-02-04
URL https://arxiv.org/abs/2002.01065v1
PDF https://arxiv.org/pdf/2002.01065v1.pdf
PWC https://paperswithcode.com/paper/fake-news-detection-by-means-of-uncertainty
Repo
Framework

On the Sensory Commutativity of Action Sequences for Embodied Agents

Title On the Sensory Commutativity of Action Sequences for Embodied Agents
Authors Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
Abstract We study perception in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom. Inspired by two theories of perception in artificial agents (Higgins (2018), Poincar'e (1895)) we consider theoretically the commutation properties of action sequences with respect to sensory information perceived by such embodied agent. From the theoretical derivations, we define the Sensory Commutativity Probability criterion which measures how much an agent’s degree of freedom affects the environment in embodied scenarios. We empirically illustrate how it can be used to improve sample-efficiency in Reinforcement Learning.
Tasks
Published 2020-02-13
URL https://arxiv.org/abs/2002.05630v1
PDF https://arxiv.org/pdf/2002.05630v1.pdf
PWC https://paperswithcode.com/paper/on-the-sensory-commutativity-of-action
Repo
Framework

FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation

Title FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation
Authors Hanchao Yu, Shanhui Sun, Haichao Yu, Xiao Chen, Honghui Shi, Thomas Huang, Terrence Chen
Abstract Motion estimation of cardiac MRI videos is crucial for the evaluation of human heart anatomy and function. Recent researches show promising results with deep learning-based methods. In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment. On the other hand, it is arguably impossible to collect all representative datasets and to train a universal tracker before deployment. In this context, we proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation. We evaluated our method through extensive experiments on two public clinical datasets. The results showed the superior performance of FOAL in accuracy compared to the offline-trained tracking method. On average, the FOAL took only $0.4$ second per video for online optimization.
Tasks Motion Estimation
Published 2020-03-10
URL https://arxiv.org/abs/2003.04492v1
PDF https://arxiv.org/pdf/2003.04492v1.pdf
PWC https://paperswithcode.com/paper/foal-fast-online-adaptive-learning-for
Repo
Framework

CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance

Title CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance
Authors Subhayan Mukherjee, Navaneeth Kamballur Kottayil, Xinyao Sun, Irene Cheng
Abstract We propose a novel direction to improve the denoising quality of filtering-based denoising algorithms in real time by predicting the best filter parameter value using a Convolutional Neural Network (CNN). We take the use case of BM3D, the state-of-the-art filtering-based denoising algorithm, to demonstrate and validate our approach. We propose and train a simple, shallow CNN to predict in real time, the optimum filter parameter value, given the input noisy image. Each training example consists of a noisy input image (training data) and the filter parameter value that produces the best output (training label). Both qualitative and quantitative results using the widely used PSNR and SSIM metrics on the popular BSD68 dataset show that the CNN-guided BM3D outperforms the original, unguided BM3D across different noise levels. Thus, our proposed method is a CNN-based improvement on the original BM3D which uses a fixed, default parameter value for all images.
Tasks Denoising
Published 2020-01-20
URL https://arxiv.org/abs/2001.06961v1
PDF https://arxiv.org/pdf/2001.06961v1.pdf
PWC https://paperswithcode.com/paper/cnn-based-real-time-parameter-tuning-for
Repo
Framework

Optimising Lockdown Policies for Epidemic Control using Reinforcement Learning

Title Optimising Lockdown Policies for Epidemic Control using Reinforcement Learning
Authors Harshad Khadilkar, Tanuja Ganu, Deva P Seetharam
Abstract In the context of the ongoing Covid-19 pandemic, several reports and studies have attempted to model and predict the spread of the disease. There is also intense debate about policies for limiting the damage, both to health and to the economy. On the one hand, the health and safety of the population is the principal consideration for most countries. On the other hand, we cannot ignore the potential for long-term economic damage caused by strict nation-wide lockdowns. In this working paper, we present a quantitative way to compute lockdown decisions for individual cities or regions, while balancing health and economic considerations. Furthermore, these policies are \textit{learnt} automatically by the proposed algorithm, as a function of disease parameters (infectiousness, gestation period, duration of symptoms, probability of death) and population characteristics (density, movement propensity). We account for realistic considerations such as imperfect lockdowns, and show that the policy obtained using reinforcement learning is a viable quantitative approach towards lockdowns.
Tasks
Published 2020-03-31
URL https://arxiv.org/abs/2003.14093v1
PDF https://arxiv.org/pdf/2003.14093v1.pdf
PWC https://paperswithcode.com/paper/optimising-lockdown-policies-for-epidemic
Repo
Framework

A New Arc-Routing Algorithm Applied to Winter Road Maintenance

Title A New Arc-Routing Algorithm Applied to Winter Road Maintenance
Authors Jiří Fink, Martin Loebl, Petra Pelikánová
Abstract This paper studies large scale instances of a fairly general arc-routing problem as well as incorporate practical constraints in particular coming from the scheduling problem of the winter road maintenance (e.g. different priorities for and methods of road maintenance). We develop a new algorithm based on a bin-packing heuristic which is well-scalable and able to solve road networks on thousands of crossroads and road segments in few minutes. Since it is impossible to find an optimal solution for such a large instances to compare it with a result of our algorithm, we also develop techniques to compute lower bounds which are based on Integer Linear Programming and Lazy Constraints.
Tasks
Published 2020-01-23
URL https://arxiv.org/abs/2001.10828v1
PDF https://arxiv.org/pdf/2001.10828v1.pdf
PWC https://paperswithcode.com/paper/a-new-arc-routing-algorithm-applied-to-winter
Repo
Framework

Conditioning Autoencoder Latent Spaces for Real-Time Timbre Interpolation and Synthesis

Title Conditioning Autoencoder Latent Spaces for Real-Time Timbre Interpolation and Synthesis
Authors Joseph T Colonel, Sam Keene
Abstract We compare standard autoencoder topologies’ performances for timbre generation. We demonstrate how different activation functions used in the autoencoder’s bottleneck distributes a training corpus’s embedding. We show that the choice of sigmoid activation in the bottleneck produces a more bounded and uniformly distributed embedding than a leaky rectified linear unit activation. We propose a one-hot encoded chroma feature vector for use in both input augmentation and latent space conditioning. We measure the performance of these networks, and characterize the latent embeddings that arise from the use of this chroma conditioning vector. An open source, real-time timbre synthesis algorithm in Python is outlined and shared.
Tasks
Published 2020-01-30
URL https://arxiv.org/abs/2001.11296v1
PDF https://arxiv.org/pdf/2001.11296v1.pdf
PWC https://paperswithcode.com/paper/conditioning-autoencoder-latent-spaces-for
Repo
Framework

Critical Limits in a Bump Attractor Network of Spiking Neurons

Title Critical Limits in a Bump Attractor Network of Spiking Neurons
Authors Alberto Arturo Vergani, Christian Robert Huyck
Abstract A bump attractor network is a model that implements a competitive neuronal process emerging from a spike pattern related to an input source. Since the bump network could behave in many ways, this paper explores some critical limits of the parameter space using various positive and negative weights and an increasing size of the input spike sources The neuromorphic simulation of the bumpattractor network shows that it exhibits a stationary, a splitting and a divergent spike pattern, in relation to different sets of weights and input windows. The balance between the values of positive and negative weights is important in determining the splitting or diverging behaviour of the spike train pattern and in defining the minimal firing conditions.
Tasks
Published 2020-03-30
URL https://arxiv.org/abs/2003.13365v1
PDF https://arxiv.org/pdf/2003.13365v1.pdf
PWC https://paperswithcode.com/paper/critical-limits-in-a-bump-attractor-network
Repo
Framework
comments powered by Disqus