January 25, 2020

2990 words 15 mins read

Paper Group ANR 1639

Multimodal End-to-End Autonomous Driving. A Sober Look at Neural Network Initializations. Algorithmic Bias in Recidivism Prediction: A Causal Perspective. Addressing Design Issues in Medical Expert System for Low Back Pain Management: Knowledge Representation, Inference Mechanism, and Conflict Resolution Using Bayesian Network. Physics-informed Aut …

Multimodal End-to-End Autonomous Driving


Title	Multimodal End-to-End Autonomous Driving
Authors	Yi Xiao, Felipe Codevilla, Akhil Gurram, Onay Urfalioglu, Antonio M. López
Abstract	Autonomous vehicles (AVs) are key for the intelligent mobility of the future. A crucial component of an AV is the artificial intelligence (AI) able to drive towards a desired destination. Today, there are different paradigms addressing the development of AI drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception (object detection, semantic segmentation, depth estimation, tracking) and maneuver control (local path planing and control). On the other hand, we find end-to-end driving approaches that try to learn a direct mapping from input raw sensor data to vehicle control signals (the steering angle). The later are relatively less studied, but are gaining popularity since they are less demanding in terms of sensor data annotation. This paper focuses on end-to-end autonomous driving. So far, most proposals relying on this paradigm assume RGB images as input sensor data. However, AVs will not be equipped only with cameras, but also with active sensors providing accurate depth information (traditional LiDARs, or new solid state ones). Accordingly, this paper analyses if RGB and depth data, RGBD data, can actually act as complementary information in a multimodal end-to-end driving approach, producing a better AI driver. Using the CARLA simulator functionalities, its standard benchmark, and conditional imitation learning (CIL), we will show how, indeed, RGBD gives rise to more successful end-to-end AI drivers. We will compare the use of RGBD information by means of early, mid and late fusion schemes, both in multisensory and single-sensor (monocular depth estimation) settings.
Tasks	Autonomous Driving, Autonomous Vehicles, Depth Estimation, Imitation Learning, Monocular Depth Estimation, Object Detection, Semantic Segmentation
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03199v1
PDF	https://arxiv.org/pdf/1906.03199v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-end-to-end-autonomous-driving
Repo
Framework

A Sober Look at Neural Network Initializations


Title	A Sober Look at Neural Network Initializations
Authors	Ingo Steinwart
Abstract	Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this paper we discuss some consequences of commonly used initialization strategies for vanilla DNNs with ReLU activations. Based on these insights we then develop an alternative initialization strategy. Finally, we present some large scale experiments assessing the quality of the new initialization strategy.
Tasks
Published	2019-03-27
URL	https://arxiv.org/abs/1903.11482v2
PDF	https://arxiv.org/pdf/1903.11482v2.pdf
PWC	https://paperswithcode.com/paper/a-sober-look-at-neural-network
Repo
Framework

Algorithmic Bias in Recidivism Prediction: A Causal Perspective


Title	Algorithmic Bias in Recidivism Prediction: A Causal Perspective
Authors	Aria Khademi, Vasant Honavar
Abstract	ProPublica’s analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were racially biased against African American defendants. We analyze the COMPAS data using a causal reformulation of the underlying algorithmic fairness problem. Specifically, we assess whether COMPAS exhibits racial bias against African American defendants using FACT, a recently introduced causality grounded measure of algorithmic fairness. We use the Neyman-Rubin potential outcomes framework for causal inference from observational data to estimate FACT from COMPAS data. Our analysis offers strong evidence that COMPAS exhibits racial bias against African American defendants. We further show that the FACT estimates from COMPAS data are robust in the presence of unmeasured confounding.
Tasks	Causal Inference
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10640v1
PDF	https://arxiv.org/pdf/1911.10640v1.pdf
PWC	https://paperswithcode.com/paper/algorithmic-bias-in-recidivism-prediction-a
Repo
Framework

Addressing Design Issues in Medical Expert System for Low Back Pain Management: Knowledge Representation, Inference Mechanism, and Conflict Resolution Using Bayesian Network


Title	Addressing Design Issues in Medical Expert System for Low Back Pain Management: Knowledge Representation, Inference Mechanism, and Conflict Resolution Using Bayesian Network
Authors	Debarpita Santra, Jyotsna Kumar Mandal, Swapan Kumar Basu, Subrata Goswami
Abstract	Aiming at developing a medical expert system for low back pain management, the paper proposes an efficient knowledge representation scheme using frame data structures, and also derives a reliable resolution logic through Bayesian Network. When a patient comes to the intended expert system for diagnosis, the proposed inference engine outputs a number of probable diseases in sorted order, with each disease being associated with a numeric measure to indicate its possibility of occurrence. When two or more diseases in the list have the same or closer possibility of occurrence, Bayesian Network is used for conflict resolution. The proposed scheme has been validated with cases of empirically selected thirty patients. Considering the expected value 0.75 as level of acceptance, the proposed system offers the diagnostic inference with the standard deviation of 0.029. The computational value of Chi-Squared test has been obtained as 11.08 with 12 degree of freedom, implying that the derived results from the designed system conform the homogeneity with the expected outcomes. Prior to any clinical investigations on the selected low back pain patients, the accuracy level (average) of 73.89% has been achieved by the proposed system, which is quite close to the expected clinical accuracy level of 75%.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03987v1
PDF	https://arxiv.org/pdf/1909.03987v1.pdf
PWC	https://paperswithcode.com/paper/addressing-design-issues-in-medical-expert
Repo
Framework

Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction


Title	Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
Authors	N. Benjamin Erichson, Michael Muehlebach, Michael W. Mahoney
Abstract	In addition to providing high-profile successes in computer vision and natural language processing, neural networks also provide an emerging set of techniques for scientific problems. Such data-driven models, however, typically ignore physical insights from the scientific system under consideration. Among other things, a physics-informed model formulation should encode some degree of stability or robustness or well-conditioning (in that a small change of the input will not lead to drastic changes in the output), characteristic of the underlying scientific problem. We investigate whether it is possible to include physics-informed prior knowledge for improving the model quality (e.g., generalization performance, sensitivity to parameter tuning, or robustness in the presence of noisy data). To that extent, we focus on the stability of an equilibrium, one of the most basic properties a dynamic system can have, via the lens of Lyapunov analysis. For the prototypical problem of fluid flow prediction, we show that models preserving Lyapunov stability improve the generalization error and reduce the prediction uncertainty.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10866v1
PDF	https://arxiv.org/pdf/1905.10866v1.pdf
PWC	https://paperswithcode.com/paper/physics-informed-autoencoders-for-lyapunov
Repo
Framework

Challenges of Privacy-Preserving Machine Learning in IoT


Title	Challenges of Privacy-Preserving Machine Learning in IoT
Authors	Mengyao Zheng, Dixing Xu, Linshan Jiang, Chaojie Gu, Rui Tan, Peng Cheng
Abstract	The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence. However, the extensive data collection and processing in IoT also engender various privacy concerns. This paper provides a taxonomy of the existing privacy-preserving machine learning approaches developed in the context of cloud computing and discusses the challenges of applying them in the context of IoT. Moreover, we present a privacy-preserving inference approach that runs a lightweight neural network at IoT objects to obfuscate the data before transmission and a deep neural network in the cloud to classify the obfuscated data. Evaluation based on the MNIST dataset shows satisfactory performance.
Tasks
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09804v1
PDF	https://arxiv.org/pdf/1909.09804v1.pdf
PWC	https://paperswithcode.com/paper/190909804
Repo
Framework

Being the center of attention: A Person-Context CNN framework for Personality Recognition


Title	Being the center of attention: A Person-Context CNN framework for Personality Recognition
Authors	Dario Dotti, Mirela Popa, Stylianos Asteriadis
Abstract	This paper proposes a novel study on personality recognition using video data from different scenarios. Our goal is to jointly model nonverbal behavioral cues with contextual information for a robust, multi-scenario, personality recognition system. Therefore, we build a novel multi-stream Convolutional Neural Network framework (CNN), which considers multiple sources of information. From a given scenario, we extract spatio-temporal motion descriptors from every individual in the scene, spatio-temporal motion descriptors encoding social group dynamics, and proxemics descriptors to encode the interaction with the surrounding context. All the proposed descriptors are mapped to the same feature space facilitating the overall learning effort. Experiments on two public datasets demonstrate the effectiveness of jointly modeling the mutual Person-Context information, outperforming the state-of-the art-results for personality recognition in two different scenarios. Lastly, we present CNN class activation maps for each personality trait, shedding light on behavioral patterns linked with personality attributes.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06690v1
PDF	https://arxiv.org/pdf/1910.06690v1.pdf
PWC	https://paperswithcode.com/paper/being-the-center-of-attention-a-person
Repo
Framework

Probing the Need for Visual Context in Multimodal Machine Translation


Title	Probing the Need for Visual Context in Multimodal Machine Translation
Authors	Ozan Caglayan, Pranava Madhyastha, Lucia Specia, Loïc Barrault
Abstract	Current work on multimodal machine translation (MMT) has suggested that the visual modality is either unnecessary or only marginally beneficial. We posit that this is a consequence of the very simple, short and repetitive sentences used in the only available dataset for the task (Multi30K), rendering the source text sufficient as context. In the general case, however, we believe that it is possible to combine visual and textual information in order to ground translations. In this paper we probe the contribution of the visual modality to state-of-the-art MMT models by conducting a systematic analysis where we partially deprive the models from source-side textual context. Our results show that under limited textual context, models are capable of leveraging the visual input to generate better translations. This contradicts the current belief that MMT models disregard the visual modality because of either the quality of the image features or the way they are integrated into the model.
Tasks	Machine Translation, Multimodal Machine Translation
Published	2019-03-20
URL	https://arxiv.org/abs/1903.08678v2
PDF	https://arxiv.org/pdf/1903.08678v2.pdf
PWC	https://paperswithcode.com/paper/probing-the-need-for-visual-context-in
Repo
Framework

A novel guided deep learning algorithm to design low-cost SPP films


Title	A novel guided deep learning algorithm to design low-cost SPP films
Authors	Yingshi Chen, Jinfeng Zhu
Abstract	The design of surface plasmon polaritons (SPP) films is an ill-posed inverse problem. There are many-to-one correspondence between the structures and user needs. We present a novel guided deep learning algorithm to find optimal solutions (with both high accuracy and low cost). To achieve this goal, we use low cost sample replacement algorithm in training process. The deep CNN would gradually learn better model from samples with lower cost. We have successfully applied this algorithm to the design of low-cost SPP films. Our model learned to replace precious metals with ordinary metals to reduce cost. So the the cost of predicted structure is much lower than standard deep CNN. And the average relative error of spectrum is less than 10%. The source codes are available at https://github.com/closest-git/MetaLab.
Tasks
Published	2019-12-07
URL	https://arxiv.org/abs/1912.03452v2
PDF	https://arxiv.org/pdf/1912.03452v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-guided-deep-learning-algorithm-to
Repo
Framework

De-biased Machine Learning for Compliers


Title	De-biased Machine Learning for Compliers
Authors	Rahul Singh, Liyang Sun
Abstract	Instrumental variable identification is a concept in causal statistics for estimating the counterfactual effect of treatment D on output Y controlling for covariates X using observational data. Even when measurements of (Y,D) are confounded, the treatment effect on the subpopulation of compliers can nonetheless be identified if an instrumental variable Z is available, which is independent of (Y,D) conditional on X and the unmeasured confounder. We introduce a de-biased machine learning (DML) approach to estimating complier parameters with high-dimensional data. Complier parameters include local average treatment effect, average complier characteristics, and complier counterfactual outcome distributions. In our approach, the de-biasing is itself performed by machine learning, a variant called de-biased machine learning via regularized Riesz representers (DML-RRR). We prove our estimator is consistent, asymptotically normal, and semi-parametrically efficient. In experiments, our estimator outperforms state of the art alternatives. We use it to estimate the effect of 401(k) participation on the distribution of net financial assets.
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.05244v1
PDF	https://arxiv.org/pdf/1909.05244v1.pdf
PWC	https://paperswithcode.com/paper/de-biased-machine-learning-for-compliers
Repo
Framework

A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition


Title	A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Authors	Jiabin Xue, Jiqing Han, Tieran Zheng, Xiang Gao, Jiaxing Guo
Abstract	Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining. However, in the processes, the system parameters may well deviate too much from the previously learned parameters. Thus, it is difficult for the system training process to learn knowledge from target domains meanwhile not forgetting knowledge from the previous learning process, which is called as catastrophic forgetting (CF). In this paper, we attempt to solve the CF problem with the lifelong learning and propose a novel multi-task learning (MTL) training framework for ASR. It considers reserving original knowledge and learning new knowledge as two independent tasks, respectively. On the one hand, we constrain the new parameters not to deviate too far from the original parameters and punish the new system when forgetting original knowledge. On the other hand, we force the new system to solve new knowledge quickly. Then, a MTL mechanism is employed to get the balance between the two tasks. We applied our method to an End2End ASR task and obtained the best performance in both target and original datasets.
Tasks	Multi-Task Learning, Speech Recognition, Transfer Learning
Published	2019-04-17
URL	http://arxiv.org/abs/1904.08039v1
PDF	http://arxiv.org/pdf/1904.08039v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-task-learning-framework-for
Repo
Framework

An Arabic Dependency Treebank in the Travel Domain


Title	An Arabic Dependency Treebank in the Travel Domain
Authors	Dima Taji, Jamila El Gizuli, Nizar Habash
Abstract	In this paper we present a dependency treebank of travel domain sentences in Modern Standard Arabic. The text comes from a translation of the English equivalent sentences in the Basic Traveling Expressions Corpus. The treebank dependency representation is in the style of the Columbia Arabic Treebank. The paper motivates the effort and discusses the construction process and guidelines. We also present parsing results and discuss the effect of domain and genre difference on parsing.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10188v1
PDF	http://arxiv.org/pdf/1901.10188v1.pdf
PWC	https://paperswithcode.com/paper/an-arabic-dependency-treebank-in-the-travel
Repo
Framework

Geometry-Aware Graph Transforms for Light Field Compact Representation


Title	Geometry-Aware Graph Transforms for Light Field Compact Representation
Authors	Mira Rizkallah, Xin Su, Thomas Maugey, Christine Guillemot
Abstract	The paper addresses the problem of energy compaction of dense 4D light fields by designing geometry-aware local graph-based transforms. Local graphs are constructed on super-rays that can be seen as a grouping of spatially and geometry-dependent angularly correlated pixels. Both non separable and separable transforms are considered. Despite the local support of limited size defined by the super-rays, the Laplacian matrix of the non separable graph remains of high dimension and its diagonalization to compute the transform eigen vectors remains computationally expensive. To solve this problem, we then perform the local spatio-angular transform in a separable manner. We show that when the shape of corresponding super-pixels in the different views is not isometric, the basis functions of the spatial transforms are not coherent, resulting in decreased correlation between spatial transform coefficients. We hence propose a novel transform optimization method that aims at preserving angular correlation even when the shapes of the super-pixels are not isometric. Experimental results show the benefit of the approach in terms of energy compaction. A coding scheme is also described to assess the rate-distortion perfomances of the proposed transforms and is compared to state of the art encoders namely HEVC and JPEG Pleno VM 1.1.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03556v1
PDF	http://arxiv.org/pdf/1903.03556v1.pdf
PWC	https://paperswithcode.com/paper/geometry-aware-graph-transforms-for-light
Repo
Framework

Deep neural network models for computational histopathology: A survey


Title	Deep neural network models for computational histopathology: A survey
Authors	Chetan L. Srinidhi, Ozan Ciga, Anne L. Martel
Abstract	Histopathological images contain rich phenotypic information that can be used to monitor underlying mechanisms contributing to diseases progression and patient survival outcomes. Recently, deep learning has become the mainstream methodological choice for analyzing and interpreting cancer histology images. In this paper, we present a comprehensive review of state-of-the-art deep learning approaches that have been used in the context of histopathological image analysis. From the survey of over 130 papers, we review the fields progress based on the methodological aspect of different machine learning strategies such as supervised, weakly supervised, unsupervised, transfer learning and various other sub-variants of these methods. We also provide an overview of deep learning based survival models that are applicable for disease-specific prognosis tasks. Finally, we summarize several existing open datasets and highlight critical challenges and limitations with current deep learning approaches, along with possible avenues for future research.
Tasks	Transfer Learning
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12378v1
PDF	https://arxiv.org/pdf/1912.12378v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-models-for-computational
Repo
Framework

MIPaaL: Mixed Integer Program as a Layer


Title	MIPaaL: Mixed Integer Program as a Layer
Authors	Aaron Ferber, Bryan Wilder, Bistra Dilkina, Milind Tambe
Abstract	Machine learning components commonly appear in larger decision-making pipelines; however, the model training process typically focuses only on a loss that measures accuracy between predicted values and ground truth values. Decision-focused learning explicitly integrates the downstream decision problem when training the predictive model, in order to optimize the quality of decisions induced by the predictions. It has been successfully applied to several limited combinatorial problem classes, such as those that can be expressed as linear programs (LP), and submodular optimization. However, these previous applications have uniformly focused on problems from specific classes with simple constraints. Here, we enable decision-focused learning for the broad class of problems that can be encoded as a Mixed Integer Linear Program (MIP), hence supporting arbitrary linear constraints over discrete and continuous variables. We show how to differentiate through a MIP by employing a cutting planes solution approach, which is an exact algorithm that iteratively adds constraints to a continuous relaxation of the problem until an integral solution is found. We evaluate our new end-to-end approach on several real world domains and show that it outperforms the standard two phase approaches that treat prediction and prescription separately, as well as a baseline approach of simply applying decision-focused learning to the LP relaxation of the MIP.
Tasks	Decision Making
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05912v2
PDF	https://arxiv.org/pdf/1907.05912v2.pdf
PWC	https://paperswithcode.com/paper/mipaal-mixed-integer-program-as-a-layer
Repo
Framework