January 28, 2020

3123 words 15 mins read

Paper Group ANR 931

MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech. MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning. DANTE: Deep AlterNations for Training nEural networks. Tree-based Intelligent Intrusion Detection System in Internet of Vehicles. Acquiring Knowledge from Pre-trained Mode …

MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech


Title	MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech
Authors	Emna Rejaibi, Ali Komaty, Fabrice Meriaudeau, Said Agrebi, Alice Othmani
Abstract	Clinical depression or Major Depressive Disorder (MDD) is a common and serious medical illness. In this paper, a deep recurrent neural network-based framework is presented to detect depression and to predict its severity level from speech. Low-level and high-level audio features are extracted from audio recordings to predict the 24 scores of the Patient Health Questionnaire and the binary class of depression diagnosis. To overcome the problem of the small size of Speech Depression Recognition (SDR) datasets, expanding training labels and transferred features are considered. The proposed approach outperforms the state-of-art approaches on the DAIC-WOZ database with an overall accuracy of 76.27% and a root mean square error of 0.4 in assessing depression, while a root mean square error of 0.168 is achieved in predicting the depression severity levels. The proposed framework has several advantages (fastness, non-invasiveness, and non-intrusion), which makes it convenient for real-time applications. The performances of the proposed approach are evaluated under a multi-modal and a multi-features experiments. MFCC based high-level features hold relevant information related to depression. Yet, adding visual action units and different other acoustic features further boosts the classification results by 20% and 10% to reach an accuracy of 95.6% and 86%, respectively. Considering visual-facial modality needs to be carefully studied as it sparks patient privacy concerns while adding more acoustic features increases the computation time.
Tasks	Data Augmentation, Transfer Learning
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07208v2
PDF	https://arxiv.org/pdf/1909.07208v2.pdf
PWC	https://paperswithcode.com/paper/mfcc-based-recurrent-neural-network-for
Repo
Framework

MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning


Title	MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
Authors	Haotian Fu, Hongyao Tang, Jianye Hao, Wulong Liu, Chen Chen
Abstract	Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly learn such a meta-policy. In this paper, we propose a new meta-RL algorithm called Meta Goal-generation for Hierarchical RL (MGHRL). Instead of directly generating policies over primitive action space for new tasks, MGHRL learns to generate high-level meta strategies over subgoals given past experience and leaves the rest of how to achieve subgoals as independent RL subtasks. Our empirical results on several challenging simulated robotics environments show that our method enables more efficient and generalized meta-learning from past experience.
Tasks	Hierarchical Reinforcement Learning, Meta-Learning
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13607v4
PDF	https://arxiv.org/pdf/1909.13607v4.pdf
PWC	https://paperswithcode.com/paper/efficient-meta-reinforcement-learning-via-1
Repo
Framework

DANTE: Deep AlterNations for Training nEural networks


Title	DANTE: Deep AlterNations for Training nEural networks
Authors	Sneha Kudugunta, Vaibhav B Sinha, Adepu Ravi Sankar, Surya Teja Chavali, Purushottam Kar, Vineeth N Balasubramanian
Abstract	We present DANTE, a novel method for training neural networks using the alternating minimization principle. DANTE provides an alternate perspective to traditional gradient-based backpropagation techniques commonly used to train deep networks. It utilizes an adaptation of quasi-convexity to cast training a neural network as a bi-quasi-convex optimization problem. We show that for neural network configurations with both differentiable (e.g. sigmoid) and non-differentiable (e.g. ReLU) activation functions, we can perform the alternations very effectively. DANTE can also be extended to networks with multiple hidden layers. In experiments on standard datasets, neural networks trained using the proposed method were found to be very promising and competitive to traditional backpropagation techniques, both in terms of quality of the solution, as well as training speed.
Tasks
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00491v2
PDF	https://arxiv.org/pdf/1902.00491v2.pdf
PWC	https://paperswithcode.com/paper/dante-deep-alternations-for-training-neural
Repo
Framework

Tree-based Intelligent Intrusion Detection System in Internet of Vehicles


Title	Tree-based Intelligent Intrusion Detection System in Internet of Vehicles
Authors	Li Yang, Abdallah Moubayed, Ismail Hamieh, Abdallah Shami
Abstract	The use of autonomous vehicles (AVs) is a promising technology in Intelligent Transportation Systems (ITSs) to improve safety and driving efficiency. Vehicle-to-everything (V2X) technology enables communication among vehicles and other infrastructures. However, AVs and Internet of Vehicles (IoV) are vulnerable to different types of cyber-attacks such as denial of service, spoofing, and sniffing attacks. In this paper, an intelligent intrusion detection system (IDS) is proposed based on tree-structure machine learning models. The results from the implementation of the proposed intrusion detection system on standard data sets indicate that the system has the ability to identify various cyber-attacks in the AV networks. Furthermore, the proposed ensemble learning and feature selection approaches enable the proposed system to achieve high detection rate and low computational cost simultaneously.
Tasks	Autonomous Vehicles, Feature Selection, Intrusion Detection
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08635v1
PDF	https://arxiv.org/pdf/1910.08635v1.pdf
PWC	https://paperswithcode.com/paper/tree-based-intelligent-intrusion-detection
Repo
Framework

Acquiring Knowledge from Pre-trained Model to Neural Machine Translation


Title	Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
Authors	Rongxiang Weng, Heng Yu, Shujian Huang, Shanbo Cheng, Weihua Luo
Abstract	Pre-training and fine-tuning have achieved great success in the natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual data. Then, fine-tuning the pre-trained model with labeled data from downstream tasks. However, in neural machine translation (NMT), we address the problem that the training objective of the bilingual task is far different from the monolingual pre-trained model. This gap leads that only using fine-tuning in NMT can not fully utilize prior language knowledge. In this paper, we propose an APT framework for acquiring knowledge from the pre-trained model to NMT. The proposed approach includes two modules: 1). a dynamic fusion mechanism to fuse task-specific features adapted from general knowledge into NMT network, 2). a knowledge distillation paradigm to learn language knowledge continuously during the NMT training process. The proposed approach could integrate suitable knowledge from pre-trained models to improve the NMT. Experimental results on WMT English to German, German to English and Chinese to English machine translation tasks show that our model outperforms strong baselines and the fine-tuning counterparts.
Tasks	Machine Translation
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01774v1
PDF	https://arxiv.org/pdf/1912.01774v1.pdf
PWC	https://paperswithcode.com/paper/acquiring-knowledge-from-pre-trained-model-to
Repo
Framework

Cascaded Generation of High-quality Color Visible Face Images from Thermal Captures


Title	Cascaded Generation of High-quality Color Visible Face Images from Thermal Captures
Authors	Naser Damer, Fadi Boutros, Khawla Mallat, Florian Kirchbuchner, Jean-Luc Dugelay, Arjan Kuijper
Abstract	Generating visible-like face images from thermal images is essential to perform manual and automatic cross-spectrum face recognition. We successfully propose a solution based on cascaded refinement network that, unlike previous works, produces high quality generated color images without the need for face alignment, large databases, data augmentation, polarimetric sensors, computationally-intense training, or unrealistic restriction on the generated resolution. The training of our solution is based on the contextual loss, making it inherently scale (face area) and rotation invariant. We present generated image samples of unknown individuals under different poses and occlusion conditions.We also prove the high similarity in image quality between ground-truth images and generated ones by comparing seven quality metrics. We compare our results with two state-of-the-art approaches proving the superiority of our proposed approach.
Tasks	Data Augmentation, Face Alignment, Face Recognition
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09524v1
PDF	https://arxiv.org/pdf/1910.09524v1.pdf
PWC	https://paperswithcode.com/paper/cascaded-generation-of-high-quality-color
Repo
Framework

How Much Does Audio Matter to Recognize Egocentric Object Interactions?


Title	How Much Does Audio Matter to Recognize Egocentric Object Interactions?
Authors	Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli
Abstract	Sounds are an important source of information on our daily interactions with objects. For instance, a significant amount of people can discern the temperature of water that it is being poured just by using the sense of hearing. However, only a few works have explored the use of audio for the classification of object interactions in conjunction with vision or as single modality. In this preliminary work, we propose an audio model for egocentric action recognition and explore its usefulness on the parts of the problem (noun, verb, and action classification). Our model achieves a competitive result in terms of verb classification (34.26% accuracy) on a standard benchmark with respect to vision-based state of the art systems, using a comparatively lighter architecture.
Tasks	Action Classification
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00634v1
PDF	https://arxiv.org/pdf/1906.00634v1.pdf
PWC	https://paperswithcode.com/paper/190600634
Repo
Framework

Relative contributions of Shakespeare and Fletcher in Henry VIII: An Analysis Based on Most Frequent Words and Most Frequent Rhythmic Patterns


Title	Relative contributions of Shakespeare and Fletcher in Henry VIII: An Analysis Based on Most Frequent Words and Most Frequent Rhythmic Patterns
Authors	Petr Plecháč
Abstract	The versified play Henry VIII is nowadays widely recognized to be a collaborative work not written solely by William Shakespeare. We employ combined analysis of vocabulary and versification together with machine learning techniques to determine which authors also took part in the writing of the play and what were their relative contributions. Unlike most previous studies, we go beyond the attribution of particular scenes and use the rolling attribution approach to determine the probabilities of authorship of pieces of texts, without respecting the scene boundaries. Our results highly support the canonical division of the play between William Shakespeare and John Fletcher proposed by James Spedding, but also bring new evidence supporting the modifications proposed later by Thomas Merriam.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1911.05652v1
PDF	https://arxiv.org/pdf/1911.05652v1.pdf
PWC	https://paperswithcode.com/paper/relative-contributions-of-shakespeare-and
Repo
Framework

Map as The Hidden Sensor: Fast Odometry-Based Global Localization


Title	Map as The Hidden Sensor: Fast Odometry-Based Global Localization
Authors	Cheng Peng, David Weikersdorfer
Abstract	Accurate and robust global localization is essential to robotics applications. We propose a novel global localization method that employs the map traversability as a hidden observation. The resulting map-corrected odometry localization is able to provide an accurate belief tensor of the robot state. Our method can be used for blind robots in dark or highly reflective areas. In contrast to odometry drift in long-term, our method using only odometry and the map converges in longterm. Our method can also be integrated with other sensors to boost the localization performance. The algorithm does not have any initial state assumption and tracks all possible robot states at all times. Therefore, our method is global and is robust in the event of ambiguous observations. We parallel each step of our algorithm such that it can be performed in real-time (up to ~ 300 Hz) using GPU. We validate our algorithm in different publicly available floor-plans and show that it is able to converge to the ground truth fast while being robust to ambiguities.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1910.00572v1
PDF	https://arxiv.org/pdf/1910.00572v1.pdf
PWC	https://paperswithcode.com/paper/map-as-the-hidden-sensor-fast-odometry-based
Repo
Framework

Data-Driven Randomized Learning of Feedforward Neural Networks


Title	Data-Driven Randomized Learning of Feedforward Neural Networks
Authors	Grzegorz Dudek
Abstract	Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed interval which is independent of the data scope and activation function type. This does not lead to good results in the approximation of the strongly nonlinear functions. In this work, a method which adjusts the random parameters, representing the slopes and positions of the sigmoids, to the target function features is proposed. The method randomly selects the input space regions, places the sigmoids in these regions and then adjusts the sigmoid slopes to the local fluctuations of the target function. This brings very good results in the approximation of the complex target functions when compared to the standard fixed interval method and other methods recently proposed in the literature.
Tasks
Published	2019-08-11
URL	https://arxiv.org/abs/1908.03891v1
PDF	https://arxiv.org/pdf/1908.03891v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-randomized-learning-of
Repo
Framework

Safety and Robustness in Decision Making: Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer


Title	Safety and Robustness in Decision Making: Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer
Authors	Geoffroy Dubourg-Felonneau, Omar Darwish, Christopher Parsons, Dami Rebergen, John W Cassidy, Nirmesh Patel, Harry W Clifford
Abstract	The genomic profile underlying an individual tumor can be highly informative in the creation of a personalized cancer treatment strategy for a given patient; a practice known as precision oncology. This involves next generation sequencing of a tumor sample and the subsequent identification of genomic aberrations, such as somatic mutations, to provide potential candidates of targeted therapy. The identification of these aberrations from sequencing noise and germline variant background poses a classic classification-style problem. This has been previously broached with many different supervised machine learning methods, including deep-learning neural networks. However, these neural networks have thus far not been tailored to give any indication of confidence in the mutation call, meaning an oncologist could be targeting a mutation with a low probability of being true. To address this, we present here a deep bayesian recurrent neural network for cancer variant calling, which shows no degradation in performance compared to standard neural networks. This approach enables greater flexibility through different priors to avoid overfitting to a single dataset. We will be incorporating this approach into software for oncologists to obtain safe, robust, and statistically confident somatic mutation calls for precision oncology treatment choices.
Tasks	Decision Making
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02065v1
PDF	https://arxiv.org/pdf/1912.02065v1.pdf
PWC	https://paperswithcode.com/paper/safety-and-robustness-in-decision-making-deep
Repo
Framework

Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information


Title	Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information
Authors	Yiren Zhao, Ilia Shumailov, Han Cui, Xitong Gao, Robert Mullins, Ross Anderson
Abstract	Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a strong Black-box case, where the attacker has no knowledge of the agents, their training parameters and their training methods. We use sequence-to-sequence models to predict a single action or a sequence of future actions that a trained agent will make. First, we show our approximation model, based on time-series information from the agent, consistently predicts RL agents’ future actions with high accuracy in a Black-box setup on a wide range of games and RL algorithms. Second, we find that although adversarial samples are transferable from the target model to our RL agents, they often outperform random Gaussian noise only marginally. This highlights a serious methodological deficiency in previous work on such agents; random jamming should have been taken as the baseline for evaluation. Third, we propose a novel use for adversarial samplesin Black-box attacks of RL agents: they can be used to trigger a trained agent to misbehave after a specific time delay. This appears to be a genuinely new type of attack. It potentially enables an attacker to use devices controlled by RL agents as time bombs.
Tasks	Time Series
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02918v2
PDF	https://arxiv.org/pdf/1909.02918v2.pdf
PWC	https://paperswithcode.com/paper/blackbox-attacks-on-reinforcement-learning
Repo
Framework

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables


Title	ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
Authors	Mingzhang Yin, Yuguang Yue, Mingyuan Zhou
Abstract	To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation under the Dirichlet distribution, then uses variable swapping to construct differently expressed but equivalent expectations, and finally shares common random numbers between these expectations to achieve significant variance reduction. Experimental results show ARSM closely resembles the performance of the true gradient for optimization in univariate settings; outperforms existing estimators by a large margin when applied to categorical variational auto-encoders; and provides a “try-and-see self-critic” variance reduction method for discrete-action policy gradient, which removes the need of estimating baselines by generating a random number of pseudo actions and estimating their action-value functions.
Tasks
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01413v2
PDF	https://arxiv.org/pdf/1905.01413v2.pdf
PWC	https://paperswithcode.com/paper/arsm-augment-reinforce-swap-merge-estimator
Repo
Framework

Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing


Title	Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing
Authors	Ricardo Augusto Borsoi, Tales Imbiriba, José Carlos Moreira Bermudez
Abstract	Endmember (EM) spectral variability can greatly impact the performance of standard hyperspectral image analysis algorithms. Extended parametric models have been successfully applied to account for the EM spectral variability. However, these models still lack the compromise between flexibility and low-dimensional representation that is necessary to properly explore the fact that spectral variability is often confined to a low-dimensional manifold in real scenes. In this paper we propose to learn a spectral variability model directly form the observed data, instead of imposing it \emph{a priori}. This is achieved through a deep generative EM model, which is estimated using a variational autoencoder (VAE). The encoder and decoder that compose the generative model are trained using pure pixel information extracted directly from the observed image, what allows for an unsupervised formulation. The proposed EM model is applied to the solution of a spectral unmixing problem, which we cast as an alternating nonlinear least-squares problem that is solved iteratively with respect to the abundances and to the low-dimensional representations of the EMs in the latent space of the deep generative model. Simulations using both synthetic and real data indicate that the proposed strategy can outperform the competing state-of-the-art algorithms.
Tasks
Published	2019-02-14
URL	https://arxiv.org/abs/1902.05528v3
PDF	https://arxiv.org/pdf/1902.05528v3.pdf
PWC	https://paperswithcode.com/paper/deep-generative-endmember-modeling-an
Repo
Framework

Deep active subspaces - a scalable method for high-dimensional uncertainty propagation


Title	Deep active subspaces - a scalable method for high-dimensional uncertainty propagation
Authors	Rohit Tripathy, Ilias Bilionis
Abstract	A problem of considerable importance within the field of uncertainty quantification (UQ) is the development of efficient methods for the construction of accurate surrogate models. Such efforts are particularly important to applications constrained by high-dimensional uncertain parameter spaces. The difficulty of accurate surrogate modeling in such systems, is further compounded by data scarcity brought about by the large cost of forward model evaluations. Traditional response surface techniques, such as Gaussian process regression (or Kriging) and polynomial chaos are difficult to scale to high dimensions. To make surrogate modeling tractable in expensive high-dimensional systems, one must resort to dimensionality reduction of the stochastic parameter space. A recent dimensionality reduction technique that has shown great promise is the method of `active subspaces’. The classical formulation of active subspaces, unfortunately, requires gradient information from the forward model - often impossible to obtain. In this work, we present a simple, scalable method for recovering active subspaces in high-dimensional stochastic systems, without gradient-information that relies on a reparameterization of the orthogonal active subspace projection matrix, and couple this formulation with deep neural networks. We demonstrate our approach on synthetic and real world datasets and show favorable predictive comparison to classical active subspaces. \|
Tasks	Dimensionality Reduction
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10527v2
PDF	http://arxiv.org/pdf/1902.10527v2.pdf
PWC	https://paperswithcode.com/paper/deep-active-subspaces-a-scalable-method-for
Repo
Framework