October 17, 2019

2899 words 14 mins read

Paper Group ANR 928

Paper Group ANR 928

A cortical-inspired model for orientation-dependent contrast perception: a link with Wilson-Cowan equations. Improving fairness in machine learning systems: What do industry practitioners need?. A Hierarchical Fuzzy System for an Advanced Driving Assistance System. A Portuguese Native Language Identification Dataset. Band Target Entropy Minimizatio …

Title A cortical-inspired model for orientation-dependent contrast perception: a link with Wilson-Cowan equations
Authors Marcelo Bertalmío, Luca Calatroni, Valentina Franceschi, Benedetta Franceschiello, Dario Prandi
Abstract We consider a differential model describing neuro-physiological contrast perception phenomena induced by surrounding orientations. The mathematical formulation relies on a cortical-inspired modelling [10] largely used over the last years to describe neuron interactions in the primary visual cortex (V1) and applied to several image processing problems [12,19,13]. Our model connects to Wilson-Cowan-type equations [23] and it is analogous to the one used in [3,2,14] to describe assimilation and contrast phenomena, the main novelty being its explicit dependence on local image orientation. To confirm the validity of the model, we report some numerical tests showing its ability to explain orientation-dependent phenomena (such as grating induction) and geometric-optical illusions [21,16] classically explained only by filtering-based techniques [6,18].
Tasks
Published 2018-12-18
URL http://arxiv.org/abs/1812.07425v1
PDF http://arxiv.org/pdf/1812.07425v1.pdf
PWC https://paperswithcode.com/paper/a-cortical-inspired-model-for-orientation
Repo
Framework

Improving fairness in machine learning systems: What do industry practitioners need?

Title Improving fairness in machine learning systems: What do industry practitioners need?
Authors Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miro Dudík, Hanna Wallach
Abstract The potential for machine learning (ML) systems to amplify social inequities and unfairness is receiving increasing popular and academic attention. A surge of recent work has focused on the development of algorithmic tools to assess and mitigate such unfairness. If these tools are to have a positive impact on industry practice, however, it is crucial that their design be informed by an understanding of real-world needs. Through 35 semi-structured interviews and an anonymous survey of 267 ML practitioners, we conduct the first systematic investigation of commercial product teams’ challenges and needs for support in developing fairer ML systems. We identify areas of alignment and disconnect between the challenges faced by industry practitioners and solutions proposed in the fair ML research literature. Based on these findings, we highlight directions for future ML and HCI research that will better address industry practitioners’ needs.
Tasks
Published 2018-12-13
URL http://arxiv.org/abs/1812.05239v2
PDF http://arxiv.org/pdf/1812.05239v2.pdf
PWC https://paperswithcode.com/paper/improving-fairness-in-machine-learning
Repo
Framework

A Hierarchical Fuzzy System for an Advanced Driving Assistance System

Title A Hierarchical Fuzzy System for an Advanced Driving Assistance System
Authors Mejdi Ben Dkhil, Ali Wali, Adel M. Alimi
Abstract In this study, we present a hierarchical fuzzy system by evaluating the risk state for a Driver Assistance System in order to contribute in reducing the road accident’s number. A key component of this system is its ability to continually detect and test the inside and outside risks in real time: The outside car risks by detecting various road moving objects; this proposed system stands on computer vision approaches. The inside risks by presenting an automatic system for drowsy driving identification or detection by evaluating EEG signals of the driver; this developed system is based on computer vision techniques and biometrics factors (electroencephalogram EEG). This proposed system is then composed of three main modules. The first module is responsible for identifying the driver drowsiness state through his eye movements (physical drowsiness). The second one is responsible for detecting and analysing his physiological signals to also identify his drowsiness state (moral drowsiness). The third module is responsible to evaluate the road driving risks by detecting of the road different moving objects in a real time. The final decision will be obtained by merging of the three detection systems through the use of fuzzy decision rules. Finally, the proposed approach has been improved on ten samples from a proposed dataset.
Tasks EEG
Published 2018-06-02
URL http://arxiv.org/abs/1806.04611v1
PDF http://arxiv.org/pdf/1806.04611v1.pdf
PWC https://paperswithcode.com/paper/a-hierarchical-fuzzy-system-for-an-advanced
Repo
Framework

A Portuguese Native Language Identification Dataset

Title A Portuguese Native Language Identification Dataset
Authors Iria del Río, Marcos Zampieri, Shervin Malmasi
Abstract In this paper we present NLI-PT, the first Portuguese dataset compiled for Native Language Identification (NLI), the task of identifying an author’s first language based on their second language writing. The dataset includes 1,868 student essays written by learners of European Portuguese, native speakers of the following L1s: Chinese, English, Spanish, German, Russian, French, Japanese, Italian, Dutch, Tetum, Arabic, Polish, Korean, Romanian, and Swedish. NLI-PT includes the original student text and four different types of annotation: POS, fine-grained POS, constituency parses, and dependency parses. NLI-PT can be used not only in NLI but also in research on several topics in the field of Second Language Acquisition and educational NLP. We discuss possible applications of this dataset and present the results obtained for the first lexical baseline system for Portuguese NLI.
Tasks Language Acquisition, Language Identification, Native Language Identification
Published 2018-04-30
URL http://arxiv.org/abs/1804.11346v1
PDF http://arxiv.org/pdf/1804.11346v1.pdf
PWC https://paperswithcode.com/paper/a-portuguese-native-language-identification
Repo
Framework

Band Target Entropy Minimization and Target Partial Least Squares for Spectral Recovery and Calibration

Title Band Target Entropy Minimization and Target Partial Least Squares for Spectral Recovery and Calibration
Authors Casey Kneale, Steven D. Brown
Abstract The resolution and calibration of pure spectra of minority components in measurements of chemical mixtures without prior knowledge of the mixture is a challenging problem. In this work, a combination of band target entropy minimization (BTEM) and target partial least squares (T-PLS) was used to obtain estimates for single pure component spectra and to calibrate those estimates in a true, one-at-a-time fashion. This approach allows for minor components to be targeted and their relative amounts estimated in the presence of other varying components in spectral data. The use of T-PLS estimation is an improvement to the BTEM method because it overcomes the need to identify all of the pure components prior to estimation. Estimated amounts from this combination were found to be similar to those obtained from a standard method, multivariate curve resolution-alternating least squares (MCR-ALS), on a simple, three component mixture dataset. Studies from two experimental datasets demonstrate where the combination of BTEM and T-PLS could model the pure component spectra and obtain concentration profiles of minor components but MCR-ALS could not.
Tasks Calibration
Published 2018-02-11
URL http://arxiv.org/abs/1802.03839v2
PDF http://arxiv.org/pdf/1802.03839v2.pdf
PWC https://paperswithcode.com/paper/band-target-entropy-minimization-and-target
Repo
Framework

Label Aggregation via Finding Consensus Between Models

Title Label Aggregation via Finding Consensus Between Models
Authors Chi Hong, Yichi Zhou
Abstract Label aggregation is an efficient and low cost way to make large datasets for supervised learning. It takes the noisy labels provided by non-experts and infers the unknown true labels. In this paper, we propose a novel label aggregation algorithm which includes a label aggregation neural network. The learning task in this paper is unsupervised. In order to train the neural network, we try to design a suitable guiding model to define the loss function. The optimization goal of our algorithm is to find the consensus between the predictions of the neural network and the guiding model. This algorithm is easy to optimize using mini-batch stochastic optimization methods. Since the choices of the neural network and the guiding model are very flexible, our label aggregation algorithm is easy to extend. According to the algorithm framework, we design two novel models to aggregate noisy labels. Experimental results show that our models achieve better results than state-of-the-art label aggregation methods.
Tasks Stochastic Optimization
Published 2018-07-19
URL http://arxiv.org/abs/1807.07291v1
PDF http://arxiv.org/pdf/1807.07291v1.pdf
PWC https://paperswithcode.com/paper/label-aggregation-via-finding-consensus
Repo
Framework

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Title Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Authors Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor
Abstract Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination Deep Q-Network (AE-DQN) architecture that combines a Deep RL algorithm with an Action Elimination Network (AEN) that eliminates sub-optimal actions. The AEN is trained to predict invalid actions, supervised by an external elimination signal provided by the environment. Simulations demonstrate a considerable speedup and added robustness over vanilla DQN in text-based games with over a thousand discrete actions.
Tasks
Published 2018-09-06
URL http://arxiv.org/abs/1809.02121v3
PDF http://arxiv.org/pdf/1809.02121v3.pdf
PWC https://paperswithcode.com/paper/learn-what-not-to-learn-action-elimination
Repo
Framework

Probably Approximately Metric-Fair Learning

Title Probably Approximately Metric-Fair Learning
Authors Guy N. Rothblum, Gal Yona
Abstract The seminal work of Dwork {\em et al.} [ITCS 2012] introduced a metric-based notion of individual fairness. Given a task-specific similarity metric, their notion required that every pair of similar individuals should be treated similarly. In the context of machine learning, however, individual fairness does not generalize from a training set to the underlying population. We show that this can lead to computational intractability even for simple fair-learning tasks. With this motivation in mind, we introduce and study a relaxed notion of {\em approximate metric-fairness}: for a random pair of individuals sampled from the population, with all but a small probability of error, if they are similar then they should be treated similarly. We formalize the goal of achieving approximate metric-fairness simultaneously with best-possible accuracy as Probably Approximately Correct and Fair (PACF) Learning. We show that approximate metric-fairness {\em does} generalize, and leverage these generalization guarantees to construct polynomial-time PACF learning algorithms for the classes of linear and logistic predictors.
Tasks
Published 2018-03-08
URL http://arxiv.org/abs/1803.03242v2
PDF http://arxiv.org/pdf/1803.03242v2.pdf
PWC https://paperswithcode.com/paper/probably-approximately-metric-fair-learning
Repo
Framework

Real-time regression analysis with deep convolutional neural networks

Title Real-time regression analysis with deep convolutional neural networks
Authors E. A. Huerta, Daniel George, Zhizhen Zhao, Gabrielle Allen
Abstract We discuss the development of novel deep learning algorithms to enable real-time regression analysis for time series data. We showcase the application of this new method with a timely case study, and then discuss the applicability of this approach to tackle similar challenges across science domains.
Tasks Time Series
Published 2018-05-07
URL http://arxiv.org/abs/1805.02716v1
PDF http://arxiv.org/pdf/1805.02716v1.pdf
PWC https://paperswithcode.com/paper/real-time-regression-analysis-with-deep
Repo
Framework

Sparse Reject Option Classifier Using Successive Linear Programming

Title Sparse Reject Option Classifier Using Successive Linear Programming
Authors Kulin Shah, Naresh Manwani
Abstract In this paper, we propose an approach for learning sparse reject option classifiers using double ramp loss $L_{dr}$. We use DC programming to find the risk minimizer. The algorithm solves a sequence of linear programs to learn the reject option classifier. We show that the loss $L_{dr}$ is Fisher consistent. We also show that the excess risk of loss $L_d$ is upper bounded by the excess risk of $L_{dr}$. We derive the generalization error bounds for the proposed approach. We show the effectiveness of the proposed approach by experimenting it on several real world datasets. The proposed approach not only performs comparable to the state of the art but it also successfully learns sparse classifiers.
Tasks
Published 2018-02-12
URL http://arxiv.org/abs/1802.04235v2
PDF http://arxiv.org/pdf/1802.04235v2.pdf
PWC https://paperswithcode.com/paper/sparse-and-robust-reject-option-classifier
Repo
Framework

Staircase Network: structural language identification via hierarchical attentive units

Title Staircase Network: structural language identification via hierarchical attentive units
Authors Trung Ngo Trong, Ville Hautamäki, Kristiina Jokinen
Abstract Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not independent of each other, there is a dependency enforced by, for example, the language family, which affects negatively on classification. The other external information sources (e.g. audio encoding, telephony or video speech) can also decrease classification accuracy. In this paper, we attempt to solve these issues by constructing a deep hierarchical neural network, where different levels of meta-information are encapsulated by attentive prediction units and also embedded into the training progress. The proposed method learns auxiliary tasks to obtain robust internal representation and to construct a variant of attentive units within the hierarchical model. The final result is the structural prediction of the target language and a closely related language family. The algorithm reflects a “staircase” way of learning in both its architecture and training, advancing from the fundamental audio encoding to the language family level and finally to the target language level. This process not only improves generalization but also tackles the issues of imbalanced class priors and channel variability in the deep neural network model. Our experimental findings show that the proposed architecture outperforms the state-of-the-art i-vector approaches on both small and big language corpora by a significant margin.
Tasks Language Identification
Published 2018-04-30
URL http://arxiv.org/abs/1804.11067v1
PDF http://arxiv.org/pdf/1804.11067v1.pdf
PWC https://paperswithcode.com/paper/staircase-network-structural-language
Repo
Framework

Deep Tractable Probabilistic Models for Moral Responsibility

Title Deep Tractable Probabilistic Models for Moral Responsibility
Authors Lewis Hammond, Vaishak Belle
Abstract Moral responsibility is a major concern in automated decision-making, with applications ranging from self-driving cars to kidney exchanges. From the viewpoint of automated systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data? (b) How can judgements be computed tractably, given the split-second decision points faced by the system? By building on deep tractable probabilistic learning, we propose a learning regime for inducing models of such scenarios automatically from data and reasoning tractably from them. We report on experiments that compare our system with human judgement in three illustrative domains: lung cancer staging, teamwork management, and trolley problems.
Tasks Decision Making, Self-Driving Cars
Published 2018-10-08
URL https://arxiv.org/abs/1810.03736v2
PDF https://arxiv.org/pdf/1810.03736v2.pdf
PWC https://paperswithcode.com/paper/deep-tractable-probabilistic-models-for-moral
Repo
Framework

Streaming PCA and Subspace Tracking: The Missing Data Case

Title Streaming PCA and Subspace Tracking: The Missing Data Case
Authors Laura Balzano, Yuejie Chi, Yue M. Lu
Abstract For many modern applications in science and engineering, data are collected in a streaming fashion carrying time-varying information, and practitioners need to process them with a limited amount of memory and computational resources in a timely manner for decision making. This often is coupled with the missing data problem, such that only a small fraction of data attributes are observed. These complications impose significant, and unconventional, constraints on the problem of streaming Principal Component Analysis (PCA) and subspace tracking, which is an essential building block for many inference tasks in signal processing and machine learning. This survey article reviews a variety of classical and recent algorithms for solving this problem with low computational and memory complexities, particularly those applicable in the big data regime with missing data. We illustrate that streaming PCA and subspace tracking algorithms can be understood through algebraic and geometric perspectives, and they need to be adjusted carefully to handle missing data. Both asymptotic and non-asymptotic convergence guarantees are reviewed. Finally, we benchmark the performance of several competitive algorithms in the presence of missing data for both well-conditioned and ill-conditioned systems.
Tasks Decision Making
Published 2018-06-12
URL http://arxiv.org/abs/1806.04609v1
PDF http://arxiv.org/pdf/1806.04609v1.pdf
PWC https://paperswithcode.com/paper/streaming-pca-and-subspace-tracking-the
Repo
Framework

Deep Representation Learning for Clustering of Health Tweets

Title Deep Representation Learning for Clustering of Health Tweets
Authors Oguzhan Gencoglu
Abstract Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering algorithms. Our results show that the clustering performance using proposed representation learning scheme significantly outperforms that of conventional methods for all experiments of different number of clusters. In addition, we propose a constraint on the learned representations during the neural network training in order to further enhance the clustering performance. All in all, this study introduces utilization of deep neural network-based architectures, i.e., deep convolutional autoencoders, for learning informative representations of health-related tweets.
Tasks Representation Learning
Published 2018-12-25
URL http://arxiv.org/abs/1901.00439v1
PDF http://arxiv.org/pdf/1901.00439v1.pdf
PWC https://paperswithcode.com/paper/deep-representation-learning-for-clustering
Repo
Framework

The Recognition Of Persian Phonemes Using PPNet

Title The Recognition Of Persian Phonemes Using PPNet
Authors Saber Malekzadeh, Mohammad Hossein Gholizadeh, Hossein Ghayoumi zadeh, Seyed Naser Razavi
Abstract In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian Consonant-Vowel Combination (PCVC) speech dataset. Nowadays, deep neural networks play a crucial role in classification tasks. However, the best results in speech recognition are not yet as perfect as human recognition rate. Deep learning techniques show outstanding performance over many other classification tasks like image classification, document classification, etc. Furthermore, the performance is sometimes better than a human. The reason why automatic speech recognition (ASR) systems are not as qualified as the human speech recognition system, mostly depends on features of data which is fed to deep neural networks. Methods: In this research, firstly, the sound samples are cut for the exact extraction of phoneme sounds in 50ms samples. Then, phonemes are divided into 30 groups, containing 23 consonants, 6 vowels, and a silence phoneme. Results: The short-time Fourier transform (STFT) is conducted on them, and the results are given to PPNet (A new deep convolutional neural network architecture) classifier and a total average of 75.87% accuracy is reached which is the best result ever compared to other algorithms on separated Persian phonemes (Like in PCVC speech dataset). Conclusion: This method can be used not only for recognizing mono-phonemes but also it can be adopted as an input to the selection of the best words in speech transcription.
Tasks Document Classification, Image Classification, Speech Recognition
Published 2018-12-17
URL https://arxiv.org/abs/1812.08600v2
PDF https://arxiv.org/pdf/1812.08600v2.pdf
PWC https://paperswithcode.com/paper/persian-phonemes-recognition-using-ppnet
Repo
Framework
comments powered by Disqus