October 16, 2019

3296 words 16 mins read

Paper Group ANR 1038

Dyna Planning using a Feature Based Generative Model. Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions. Graph Based Semi-supervised Learning with Convolution Neural Networks to Classify Crisis Related Tweets. Brain-inspired robust delineation operator. Private Sequential Learning. Evolving Differentiable Gene Reg …

Dyna Planning using a Feature Based Generative Model


Title	Dyna Planning using a Feature Based Generative Model
Authors	Ryan Faulkner, Doina Precup
Abstract	Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement real trajectories, or sequences of sampled states over time, with simulated ones sampled from a learned model of the environment. However, in large state spaces, the problem of learning a good generative model of the environment has been open so far. We propose to use deep belief networks to learn an environment model for use in Dyna. We present our approach and validate it empirically on problems where the state observations consist of images. Our results demonstrate that using deep belief networks, which are full generative models, significantly outperforms the use of linear expectation models, proposed in Sutton et al. (2008)
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.10129v1
PDF	http://arxiv.org/pdf/1805.10129v1.pdf
PWC	https://paperswithcode.com/paper/dyna-planning-using-a-feature-based
Repo
Framework

Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions


Title	Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions
Authors	Albert Haque, Michelle Guo, Adam S Miner, Li Fei-Fei
Abstract	With more than 300 million people depressed worldwide, depression is a global problem. Due to access barriers such as social stigma, cost, and treatment availability, 60% of mentally-ill adults do not receive any mental health services. Effective and efficient diagnosis relies on detecting clinical symptoms of depression. Automatic detection of depressive symptoms would potentially improve diagnostic accuracy and availability, leading to faster intervention. In this work, we present a machine learning method for measuring the severity of depressive symptoms. Our multi-modal method uses 3D facial expressions and spoken language, commonly available from modern cell phones. It demonstrates an average error of 3.67 points (15.3% relative) on the clinically-validated Patient Health Questionnaire (PHQ) scale. For detecting major depressive disorder, our model demonstrates 83.3% sensitivity and 82.6% specificity. Overall, this paper shows how speech recognition, computer vision, and natural language processing can be combined to assist mental health patients and practitioners. This technology could be deployed to cell phones worldwide and facilitate low-cost universal access to mental health care.
Tasks	Speech Recognition
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08592v2
PDF	http://arxiv.org/pdf/1811.08592v2.pdf
PWC	https://paperswithcode.com/paper/measuring-depression-symptom-severity-from
Repo
Framework


Title	Graph Based Semi-supervised Learning with Convolution Neural Networks to Classify Crisis Related Tweets
Authors	Firoj Alam, Shafiq Joty, Muhammad Imran
Abstract	During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity of labeled data in the early hours of a crisis hinders machine learning tasks thus delays crisis response. In this work, we propose to use an inductive semi-supervised technique to utilize unlabeled data, which is often abundant at the onset of a crisis event, along with fewer labeled data. Specif- ically, we adopt a graph-based deep learning framework to learn an inductive semi-supervised model. We use two real-world crisis datasets from Twitter to evaluate the proposed approach. Our results show significant improvements using unlabeled data as compared to only using labeled data.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.06289v1
PDF	http://arxiv.org/pdf/1805.06289v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-semi-supervised-learning-with
Repo
Framework

Brain-inspired robust delineation operator


Title	Brain-inspired robust delineation operator
Authors	Nicola Strisciuglio, George Azzopardi, Nicolai Petkov
Abstract	In this paper we present a novel filter, based on the existing COSFIRE filter, for the delineation of patterns of interest. It includes a mechanism of push-pull inhibition that improves robustness to noise in terms of spurious texture. Push-pull inhibition is a phenomenon that is observed in neurons in area V1 of the visual cortex, which suppresses the response of certain simple cells for stimuli of preferred orientation but of non-preferred contrast. This type of inhibition allows for sharper detection of the patterns of interest and improves the quality of delineation especially in images with spurious texture. We performed experiments on images from different applications, namely the detection of rose stems for automatic gardening, the delineation of cracks in pavements and road surfaces, and the segmentation of blood vessels in retinal images. Push-pull inhibition helped to improve results considerably in all applications.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10240v1
PDF	http://arxiv.org/pdf/1811.10240v1.pdf
PWC	https://paperswithcode.com/paper/brain-inspired-robust-delineation-operator
Repo
Framework

Private Sequential Learning


Title	Private Sequential Learning
Authors	John N. Tsitsiklis, Kuang Xu, Zhi Xu
Abstract	We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, $v^$, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes the learner’s queries, though not the responses, and tries to infer from them the value of $v^$. The objective of the learner is to obtain an accurate estimate of $v^$ using only a small number of queries, while simultaneously protecting her privacy by making $v^$ provably difficult to learn for the adversary. Our main results provide tight upper and lower bounds on the learner’s query complexity as a function of desired levels of privacy and estimation accuracy. We also construct explicit query strategies whose complexity is optimal up to an additive constant.
Tasks
Published	2018-05-06
URL	https://arxiv.org/abs/1805.02136v3
PDF	https://arxiv.org/pdf/1805.02136v3.pdf
PWC	https://paperswithcode.com/paper/private-sequential-learning
Repo
Framework

Evolving Differentiable Gene Regulatory Networks


Title	Evolving Differentiable Gene Regulatory Networks
Authors	Dennis G Wilson, Kyle Harrington, Sylvain Cussat-Blanc, Hervé Luga
Abstract	Over the past twenty years, artificial Gene Regulatory Networks (GRNs) have shown their capacity to solve real-world problems in various domains such as agent control, signal processing and artificial life experiments. They have also benefited from new evolutionary approaches and improvements to dynamic which have increased their optimization efficiency. In this paper, we present an additional step toward their usability in machine learning applications. We detail an GPU-based implementation of differentiable GRNs, allowing for local optimization of GRN architectures with stochastic gradient descent (SGD). Using a standard machine learning dataset, we evaluate the ways in which evolution and SGD can be combined to further GRN optimization. We compare these approaches with neural network models trained by SGD and with support vector machines.
Tasks	Artificial Life
Published	2018-07-16
URL	http://arxiv.org/abs/1807.05948v1
PDF	http://arxiv.org/pdf/1807.05948v1.pdf
PWC	https://paperswithcode.com/paper/evolving-differentiable-gene-regulatory
Repo
Framework

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension


Title	DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension
Authors	Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan
Abstract	We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets. DuoRC contains 186,089 unique question-answer pairs created from a collection of 7680 pairs of movie plots where each pair in the collection reflects two versions of the same movie - one from Wikipedia and the other from IMDb - written by two different authors. We asked crowdsourced workers to create questions from one version of the plot and a different set of workers to extract or synthesize answers from the other version. This unique characteristic of DuoRC where questions and answers are created from different versions of a document narrating the same underlying story, ensures by design, that there is very little lexical overlap between the questions created from one version and the segments containing the answer in the other version. Further, since the two versions have different levels of plot detail, narration style, vocabulary, etc., answering questions from the second version requires deeper language understanding and incorporating external background knowledge. Additionally, the narrative style of passages arising from movie plots (as opposed to typical descriptive passages in existing datasets) exhibits the need to perform complex reasoning over events across multiple sentences. Indeed, we observe that state-of-the-art neural RC models which have achieved near human performance on the SQuAD dataset, even when coupled with traditional NLP techniques to address the challenges presented in DuoRC exhibit very poor performance (F1 score of 37.42% on DuoRC v/s 86% on SQuAD dataset). This opens up several interesting research avenues wherein DuoRC could complement other RC datasets to explore novel neural approaches for studying language understanding.
Tasks	Reading Comprehension
Published	2018-04-21
URL	http://arxiv.org/abs/1804.07927v4
PDF	http://arxiv.org/pdf/1804.07927v4.pdf
PWC	https://paperswithcode.com/paper/duorc-towards-complex-language-understanding
Repo
Framework

Weakly Supervised Object Detection with Pointwise Mutual Information


Title	Weakly Supervised Object Detection with Pointwise Mutual Information
Authors	Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink
Abstract	In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object class. The resulting feature map indicates the location of objects in an image, yielding an intuitive representation of a class activation map. While traditionally such networks are learned by a softmax or binary logistic regression (sigmoid cross-entropy loss), a learning approach based on a cosine loss is introduced. A pointwise mutual information layer is incorporated in the network in order to project predictions and ground truth presence labels in a non-categorical embedding space. Thus, the cosine loss can be employed in this non-categorical representation. Besides integrating image level annotations, it is shown how to integrate point-wise annotations using a Spatial Pyramid Pooling layer. The approach is evaluated on the VOC2012 dataset for classification, point localization and weakly supervised bounding box localization. It is shown that the combination of pointwise mutual information and a cosine loss eases the learning process and thus improves the accuracy. The integration of coarse point-wise localizations further improves the results at minimal annotation costs.
Tasks	Object Detection, Weakly Supervised Object Detection
Published	2018-01-26
URL	http://arxiv.org/abs/1801.08747v1
PDF	http://arxiv.org/pdf/1801.08747v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-object-detection-with
Repo
Framework

Dendritic cortical microcircuits approximate the backpropagation algorithm


Title	Dendritic cortical microcircuits approximate the backpropagation algorithm
Authors	João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn
Abstract	Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and synaptic learning is driven by local dendritic prediction errors continuously in time. Such errors originate at apical dendrites and occur due to a mismatch between predictive input from lateral interneurons and activity from actual top-down feedback. Through the use of simple dendritic compartments and different cell-types our model can represent both error and normal activity within a pyramidal neuron. We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm. Moreover, our framework is consistent with recent observations of learning between brain areas and the architecture of cortical microcircuits. Overall, we introduce a novel view of learning on dendritic cortical circuits and on how the brain may solve the long-standing synaptic credit assignment problem.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11393v1
PDF	http://arxiv.org/pdf/1810.11393v1.pdf
PWC	https://paperswithcode.com/paper/dendritic-cortical-microcircuits-approximate
Repo
Framework

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees


Title	Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees
Authors	Hamid Hamraz, Nathan B. Jacobs, Marco A. Contreras, Chase H. Clark
Abstract	The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees from airborne LiDAR data. To enable efficient processing by a deep convolutional neural network (CNN), we designed two discrete representations using leaf-off and leaf-on LiDAR data: a digital surface model with four channels (DSMx4) and a set of four 2D views (4x2D). A training dataset of labeled tree crowns was generated via segmentation of tree crowns, followed by co-registration with field data. Potential mislabels due to GPS error or tree leaning were corrected using a statistical ensemble filtering procedure. Because the training data was heavily unbalanced (~8% conifers), we trained an ensemble of CNNs on random balanced sub-samples of augmented data (180 rotational variations per instance). The 4x2D representation yielded similar classification accuracies to the DSMx4 representation (~82% coniferous and ~90% deciduous) while converging faster. The data augmentation improved the classification accuracies, but more real training instances (especially coniferous) likely results in much stronger improvements. Leaf-off LiDAR data were the primary source of useful information, which is likely due to the perennial nature of coniferous foliage. LiDAR intensity values also proved to be useful, but normalization yielded no significant improvements. Lastly, the classification accuracies of overstory trees (~90%) were more balanced than those of understory trees (~90% deciduous and ~65% coniferous), which is likely due to the incomplete capture of understory tree crowns via airborne LiDAR. Automatic derivation of optimal features via deep learning provide the opportunity for remarkable improvements in prediction tasks where captured data are not friendly to human visual system - likely yielding sub-optimal human-designed features.
Tasks	Data Augmentation
Published	2018-02-24
URL	http://arxiv.org/abs/1802.08872v1
PDF	http://arxiv.org/pdf/1802.08872v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-coniferdeciduous
Repo
Framework

An explicit analysis of the entropic penalty in linear programming


Title	An explicit analysis of the entropic penalty in linear programming
Authors	Jonathan Weed
Abstract	Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications has been an analysis of how quickly solutions to the penalized program approach true optima to the original linear program. More than 20 years ago, Cominetti and San Mart'in showed that this convergence is exponentially fast; however, their proof is asymptotic and does not give any indication of how accurately the entropic program approximates the original program for any particular choice of the penalization parameter. We close this long-standing gap in the literature regarding entropic penalization by giving a new proof of the exponential convergence, valid for any linear program. Our proof is non-asymptotic, yields explicit constants, and has the virtue of being extremely simple. We provide matching lower bounds and show that the entropic approach does not lead to a near-linear time approximation scheme for the linear assignment problem.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01879v1
PDF	http://arxiv.org/pdf/1806.01879v1.pdf
PWC	https://paperswithcode.com/paper/an-explicit-analysis-of-the-entropic-penalty
Repo
Framework

HOGWILD!-Gibbs can be PanAccurate


Title	HOGWILD!-Gibbs can be PanAccurate
Authors	Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti
Abstract	Asynchronous Gibbs sampling has been recently shown to be fast-mixing and an accurate method for estimating probabilities of events on a small number of variables of a graphical model satisfying Dobrushin’s condition~\cite{DeSaOR16}. We investigate whether it can be used to accurately estimate expectations of functions of {\em all the variables} of the model. Under the same condition, we show that the synchronous (sequential) and asynchronous Gibbs samplers can be coupled so that the expected Hamming distance between their (multivariate) samples remains bounded by $O(\tau \log n),$ where $n$ is the number of variables in the graphical model, and $\tau$ is a measure of the asynchronicity. A similar bound holds for any constant power of the Hamming distance. Hence, the expectation of any function that is Lipschitz with respect to a power of the Hamming distance, can be estimated with a bias that grows logarithmically in $n$. Going beyond Lipschitz functions, we consider the bias arising from asynchronicity in estimating the expectation of polynomial functions of all variables in the model. Using recent concentration of measure results, we show that the bias introduced by the asynchronicity is of smaller order than the standard deviation of the function value already present in the true model. We perform experiments on a multi-processor machine to empirically illustrate our theoretical findings.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10581v1
PDF	http://arxiv.org/pdf/1811.10581v1.pdf
PWC	https://paperswithcode.com/paper/hogwild-gibbs-can-be-panaccurate
Repo
Framework

Airline Passenger Name Record Generation using Generative Adversarial Networks


Title	Airline Passenger Name Record Generation using Generative Adversarial Networks
Authors	Alejandro Mottini, Alix Lheritier, Rodrigo Acuna-Agost
Abstract	Passenger Name Records (PNRs) are at the heart of the travel industry. Created when an itinerary is booked, they contain travel and passenger information. It is usual for airlines and other actors in the industry to inter-exchange and access each other’s PNR, creating the challenge of using them without infringing data ownership laws. To address this difficulty, we propose a method to generate realistic synthetic PNRs using Generative Adversarial Networks (GANs). Unlike other GAN applications, PNRs consist of categorical and numerical features with missing/NaN values, which makes the use of GANs challenging. We propose a solution based on Cram'{e}r GANs, categorical feature embedding and a Cross-Net architecture. The method was tested on a real PNR dataset, and evaluated in terms of distribution matching, memorization, and performance of predictive models for two real business problems: client segmentation and passenger nationality prediction. Results show that the generated data matches well with the real PNRs without memorizing them, and that it can be used to train models for real business applications.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06657v1
PDF	http://arxiv.org/pdf/1807.06657v1.pdf
PWC	https://paperswithcode.com/paper/airline-passenger-name-record-generation
Repo
Framework

Reconstructing Point Sets from Distance Distributions


Title	Reconstructing Point Sets from Distance Distributions
Authors	Shuai Huang, Ivan Dokmanić
Abstract	We address the problem of reconstructing a set of points on a line or a loop from their unassigned noisy pairwise distances. When the points lie on a line, the problem is known as the turnpike problem; when they are on a loop, it is known as the beltway problem. We approximate the problem by discretizing the domain and representing the N points via an N-hot encoding, which is a density supported on the discretized domain. We show how the distance distribution is then simply a collection of quadratic functionals of this density and propose to recover the point locations so that the estimated distance distribution matches the measured distance distribution. This can be cast as a constrained nonconvex optimization problem which we solve using projected gradient descent with a suitable spectral initializer. We derive conditions under which the proposed approach locally converges to a global optimizer with a linear convergence rate. Compared to the conventional backtracking approach, our method jointly reconstructs all the point locations and is robust to noise in the measurements. We substantiate these claims with state-of-the-art performance across a number of numerical experiments. Our method is the first practical approach to solve the large-scale noisy beltway problem where the points lie on a loop.
Tasks
Published	2018-04-06
URL	https://arxiv.org/abs/1804.02465v2
PDF	https://arxiv.org/pdf/1804.02465v2.pdf
PWC	https://paperswithcode.com/paper/reconstructing-point-sets-from-distance
Repo
Framework

Classification of remote sensing images using attribute profiles and feature profiles from different trees: a comparative study


Title	Classification of remote sensing images using attribute profiles and feature profiles from different trees: a comparative study
Authors	Minh-Tan Pham, Erchan Aptoula, Sébastien Lefèvre
Abstract	The motivation of this paper is to conduct a comparative study on remote sensing image classification using the morphological attribute profiles (APs) and feature profiles (FPs) generated from different types of tree structures. Over the past few years, APs have been among the most effective methods to model the image’s spatial and contextual information. Recently, a novel extension of APs called FPs has been proposed by replacing pixel gray-levels with some statistical and geometrical features when forming the output profiles. FPs have been proved to be more efficient than the standard APs when generated from component trees (max-tree and min-tree). In this work, we investigate their performance on the inclusion tree (tree of shapes) and partition trees (alpha tree and omega tree). Experimental results from both panchromatic and hyperspectral images again confirm the efficiency of FPs compared to APs.
Tasks	Image Classification, Remote Sensing Image Classification
Published	2018-06-18
URL	http://arxiv.org/abs/1806.06985v1
PDF	http://arxiv.org/pdf/1806.06985v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-remote-sensing-images-using
Repo
Framework