October 17, 2019

2906 words 14 mins read

Paper Group ANR 772

Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity. Contextual Care Protocol using Neural Networks and Decision Trees. Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration. PARyOpt: A software for Parallel Asynchronous Remote Bayesian Optimization. Leveraging M …

Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity


Title	Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity
Authors	Steve DiPaola, Liane Gabora, Graeme McCaig
Abstract	The common view that our creativity is what makes us uniquely human suggests that incorporating research on human creativity into generative deep learning techniques might be a fruitful avenue for making their outputs more compelling and human-like. Using an original synthesis of Deep Dream-based convolutional neural networks and cognitive based computational art rendering systems, we show how honing theory, intrinsic motivation, and the notion of a ‘seed incident’ can be implemented computationally, and demonstrate their impact on the resulting generative art. Conversely, we discuss how explorations in deep learn-ing convolutional neural net generative systems can inform our understanding of human creativity. We conclude with ideas for further cross-fertilization between AI based computational creativity and psychology of creativity.
Tasks
Published	2018-12-11
URL	https://arxiv.org/abs/1812.05556v2
PDF	https://arxiv.org/pdf/1812.05556v2.pdf
PWC	https://paperswithcode.com/paper/informing-artificial-intelligence-generative
Repo
Framework

Contextual Care Protocol using Neural Networks and Decision Trees


Title	Contextual Care Protocol using Neural Networks and Decision Trees
Authors	Yash Pratyush Sinha, Pranshu Malviya, Minerva Panda, Syed Mohd Ali
Abstract	A contextual care protocol is used by a medical practitioner for patient healthcare, given the context or situation that the specified patient is in. This paper proposes a method to build an automated self-adapting protocol which can help make relevant, early decisions for effective healthcare delivery. The hybrid model leverages neural networks and decision trees. The neural network estimates the chances of each disease and each tree in the decision trees represents care protocol for a disease. These trees are subject to change in case of aberrations found by the diagnosticians. These corrections or prediction errors are clustered into similar groups for scalability and review by the experts. The corrections as suggested by the experts are incorporated into the model.
Tasks
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06437v1
PDF	http://arxiv.org/pdf/1811.06437v1.pdf
PWC	https://paperswithcode.com/paper/contextual-care-protocol-using-neural
Repo
Framework

Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration


Title	Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
Authors	Shujian Yu, Kristoffer Wickstrøm, Robert Jenssen, Jose C. Principe
Abstract	The matrix-based Renyi’s \alpha-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS). However, the utility and possible applications of these new estimators are rather new and mostly unknown to practitioners. In this paper, we first show that our estimators enable straightforward measurement of information flow in realistic convolutional neural networks (CNN) without any approximation. Then, we introduce the partial information decomposition (PID) framework and develop three quantities to analyze the synergy and redundancy in convolutional layer representations. Our results validate two fundamental data processing inequalities and reveal some fundamental properties concerning the training of CNN.
Tasks
Published	2018-04-18
URL	https://arxiv.org/abs/1804.06537v5
PDF	https://arxiv.org/pdf/1804.06537v5.pdf
PWC	https://paperswithcode.com/paper/understanding-convolutional-neural-network
Repo
Framework

PARyOpt: A software for Parallel Asynchronous Remote Bayesian Optimization


Title	PARyOpt: A software for Parallel Asynchronous Remote Bayesian Optimization
Authors	Balaji Sesha Sarath Pokuri, Alec Lofquist, Chad M Risko, Baskar Ganapathysubramanian
Abstract	PARyOpt is a python based implementation of the Bayesian optimization routine designed for remote and asynchronous function evaluations. Bayesian optimization is especially attractive for computational optimization due to its low cost function footprint as well as the ability to account for uncertainties in data. A key challenge to efficiently deploy any optimization strategy on distributed computing systems is the synchronization step, where data from multiple function calls is assimilated to identify the next campaign of function calls. Bayesian optimization provides an elegant approach to overcome this issue via asynchronous updates. We formulate, develop and implement a parallel, asynchronous variant of Bayesian optimization. The framework is robust and resilient to external failures. We show how such asynchronous evaluations help reduce the total optimization wall clock time for a suite of test problems. Additionally, we show how the software design of the framework allows easy extension to response surface reconstruction (Kriging), providing a high performance software for autonomous exploration. The software is available on PyPI, with examples and documentation.
Tasks
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04668v1
PDF	http://arxiv.org/pdf/1809.04668v1.pdf
PWC	https://paperswithcode.com/paper/paryopt-a-software-for-parallel-asynchronous
Repo
Framework

Leveraging Motion Priors in Videos for Improving Human Segmentation


Title	Leveraging Motion Priors in Videos for Improving Human Segmentation
Authors	Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu, Tingfan Wu, Min Sun
Abstract	Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to mitigate the performance drop. However, very little attention has been made toward leveraging information in videos which are naturally captured in most camera systems. In this work, we propose to leverage “motion prior” in videos for improving human segmentation in a weakly-supervised active learning setting. By extracting motion information using optical flow in videos, we can extract candidate foreground motion segments (referred to as motion prior) potentially corresponding to human segments. We propose to learn a memory-network-based policy model to select strong candidate segments (referred to as strong motion prior) through reinforcement learning. The selected segments have high precision and are directly used to finetune the model. In a newly collected surveillance camera dataset and a publicly available UrbanStreet dataset, our proposed method improves the performance of human segmentation across multiple scenes and modalities (i.e., RGB to Infrared (IR)). Last but not least, our method is empirically complementary to existing domain adaptation approaches such that additional performance gain is achieved by combining our weakly-supervised active learning approach with domain adaptation approaches.
Tasks	Active Learning, Domain Adaptation, Optical Flow Estimation, Semantic Segmentation
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11436v1
PDF	http://arxiv.org/pdf/1807.11436v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-motion-priors-in-videos-for
Repo
Framework

A Constraint-based Encoding for Domain-Independent Temporal Planning


Title	A Constraint-based Encoding for Domain-Independent Temporal Planning
Authors	Arthur Bit-Monnot
Abstract	We present a general constraint-based encoding for domain-independent task planning. Task planning is characterized by causal relationships expressed as conditions and effects of optional actions. Possible actions are typically represented by templates, where each template can be instantiated into a number of primitive actions. While most previous work for domain-independent task planning has focused on primitive actions in a state-oriented view, our encoding uses a fully lifted representation at the level of action templates. It follows a time-oriented view in the spirit of previous work in constraint-based scheduling. As a result, the proposed encoding is simple and compact as it grows with the number of actions in a solution plan rather than the number of possible primitive actions. When solved with an SMT solver, we show that the proposed encoding is slightly more efficient than state-of-the-art methods on temporally constrained planning benchmarks while clearly outperforming other fully constraint-based approaches.
Tasks
Published	2018-06-26
URL	http://arxiv.org/abs/1806.09954v1
PDF	http://arxiv.org/pdf/1806.09954v1.pdf
PWC	https://paperswithcode.com/paper/a-constraint-based-encoding-for-domain
Repo
Framework

Governing autonomous vehicles: emerging responses for safety, liability, privacy, cybersecurity, and industry risks


Title	Governing autonomous vehicles: emerging responses for safety, liability, privacy, cybersecurity, and industry risks
Authors	Araz Taeihagh, Hazel Si Min Lim
Abstract	The benefits of autonomous vehicles (AVs) are widely acknowledged, but there are concerns about the extent of these benefits and AV risks and unintended consequences. In this article, we first examine AVs and different categories of the technological risks associated with them. We then explore strategies that can be adopted to address these risks, and explore emerging responses by governments for addressing AV risks. Our analyses reveal that, thus far, governments have in most instances avoided stringent measures in order to promote AV developments and the majority of responses are non-binding and focus on creating councils or working groups to better explore AV implications. The US has been active in introducing legislations to address issues related to privacy and cybersecurity. The UK and Germany, in particular, have enacted laws to address liability issues, other countries mostly acknowledge these issues, but have yet to implement specific strategies. To address privacy and cybersecurity risks strategies ranging from introduction or amendment of non-AV specific legislation to creating working groups have been adopted. Much less attention has been paid to issues such as environmental and employment risks, although a few governments have begun programmes to retrain workers who might be negatively affected.
Tasks	Autonomous Vehicles
Published	2018-07-16
URL	http://arxiv.org/abs/1807.05720v1
PDF	http://arxiv.org/pdf/1807.05720v1.pdf
PWC	https://paperswithcode.com/paper/governing-autonomous-vehicles-emerging
Repo
Framework

Deep Spatiotemporal Models for Robust Proprioceptive Terrain Classification


Title	Deep Spatiotemporal Models for Robust Proprioceptive Terrain Classification
Authors	Abhinav Valada, Wolfram Burgard
Abstract	Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep Long-Short Term Memory (LSTM) based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new Convolution Neural Network (CNN) architecture that learns deep spatial features, complemented with LSTM units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00736v1
PDF	http://arxiv.org/pdf/1804.00736v1.pdf
PWC	https://paperswithcode.com/paper/deep-spatiotemporal-models-for-robust
Repo
Framework

Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies


Title	Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies
Authors	Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour
Abstract	In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine them into a composite solution. Our approach builds on mapping this problem into a Reward Discounted Traveling Salesman Problem, and then deriving approximate solutions for it. In particular, we focus on approximate solutions that are local, i.e., solutions that only observe information about the current state. Local policies are easy to implement and do not require substantial computational resources as they do not perform planning. While local deterministic policies, like Nearest Neighbor, are being used in practice for hierarchical reinforcement learning, we propose three stochastic policies that guarantee better performance than any deterministic policy.
Tasks	Hierarchical Reinforcement Learning
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04674v1
PDF	http://arxiv.org/pdf/1803.04674v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-reinforcement-learning
Repo
Framework

New/s/leak 2.0 - Multilingual Information Extraction and Visualization for Investigative Journalism


Title	New/s/leak 2.0 - Multilingual Information Extraction and Visualization for Investigative Journalism
Authors	Gregor Wiedemann, Seid Muhie Yimam, Chris Biemann
Abstract	Investigative journalism in recent years is confronted with two major challenges: 1) vast amounts of unstructured data originating from large text collections such as leaks or answers to Freedom of Information requests, and 2) multi-lingual data due to intensified global cooperation and communication in politics, business and civil society. Faced with these challenges, journalists are increasingly cooperating in international networks. To support such collaborations, we present the new version of new/s/leak 2.0, our open-source software for content-based searching of leaks. It includes three novel main features: 1) automatic language detection and language-dependent information extraction for 40 languages, 2) entity and keyword visualization for efficient exploration, and 3) decentral deployment for analysis of confidential data from various formats. We illustrate the new analysis capabilities with an exemplary case study.
Tasks	Efficient Exploration
Published	2018-07-13
URL	http://arxiv.org/abs/1807.05151v1
PDF	http://arxiv.org/pdf/1807.05151v1.pdf
PWC	https://paperswithcode.com/paper/newsleak-20-multilingual-information
Repo
Framework

Étude de l’informativité des transcriptions : une approche basée sur le résumé automatique


Title	Étude de l’informativité des transcriptions : une approche basée sur le résumé automatique
Authors	Carlos-Emiliano González-Gallardo, Malek Hajjem, Eric SanJuan, Juan-Manuel Torres-Moreno
Abstract	In this paper we propose a new approach to evaluate the informativeness of transcriptions coming from Automatic Speech Recognition systems. This approach, based in the notion of informativeness, is focused on the framework of Automatic Text Summarization performed over these transcriptions. At a first glance we estimate the informative content of the various automatic transcriptions, then we explore the capacity of Automatic Text Summarization to overcome the informative loss. To do this we use an automatic summary evaluation protocol without reference (based on the informative content), which computes the divergence between probability distributions of different textual representations: manual and automatic transcriptions and their summaries. After a set of evaluations this analysis allowed us to judge both the quality of the transcriptions in terms of informativeness and to assess the ability of automatic text summarization to compensate the problems raised during the transcription phase.
Tasks	Speech Recognition, Text Summarization
Published	2018-09-04
URL	http://arxiv.org/abs/1809.00994v1
PDF	http://arxiv.org/pdf/1809.00994v1.pdf
PWC	https://paperswithcode.com/paper/etude-de-linformativite-des-transcriptions
Repo
Framework

PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing


Title	PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
Authors	Dan Xu, Wanli Ouyang, Xiaogang Wang, Nicu Sebe
Abstract	Depth estimation and scene parsing are two particularly important tasks in visual scene understanding. In this paper we tackle the problem of simultaneous depth estimation and scene parsing in a joint CNN. The task can be typically treated as a deep multi-task learning problem [42]. Different from previous methods directly optimizing multiple tasks given the input training data, this paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate auxiliary tasks are utilized as multi-modal input via our proposed multi-modal distillation modules for the final tasks. During the joint learning, the intermediate tasks not only act as supervision for learning more robust deep representations but also provide rich multi-modal information for improving the final tasks. Extensive experiments are conducted on two challenging datasets (i.e. NYUD-v2 and Cityscapes) for both the depth estimation and scene parsing tasks, demonstrating the effectiveness of the proposed approach.
Tasks	Depth Estimation, Multi-Task Learning, Scene Parsing, Scene Understanding
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04409v1
PDF	http://arxiv.org/pdf/1805.04409v1.pdf
PWC	https://paperswithcode.com/paper/pad-net-multi-tasks-guided-prediction-and
Repo
Framework

Grammars and reinforcement learning for molecule optimization


Title	Grammars and reinforcement learning for molecule optimization
Authors	Egor Kraev
Abstract	We seek to automate the design of molecules based on specific chemical properties. Our primary contributions are a simpler method for generating SMILES strings guaranteed to be chemically valid, using a combination of a new context-free grammar for SMILES and additional masking logic; and casting the molecular property optimization as a reinforcement learning problem, specifically best-of-batch policy gradient applied to a Transformer model architecture. This approach uses substantially fewer model steps per atom than earlier approaches, thus enabling generation of larger molecules, and beats previous state-of-the art baselines by a significant margin. Applying reinforcement learning to a combination of a custom context-free grammar with additional masking to enforce non-local constraints is applicable to any optimization of a graph structure under a mixture of local and nonlocal constraints.
Tasks
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11222v1
PDF	http://arxiv.org/pdf/1811.11222v1.pdf
PWC	https://paperswithcode.com/paper/grammars-and-reinforcement-learning-for
Repo
Framework

Predicting Extubation Readiness in Extreme Preterm Infants based on Patterns of Breathing


Title	Predicting Extubation Readiness in Extreme Preterm Infants based on Patterns of Breathing
Authors	Charles C. Onu, Lara J. Kanbar, Wissam Shalish, Karen A. Brown, Guilherme M. Sant’Anna, Robert E. Kearney, Doina Precup
Abstract	Extremely preterm infants commonly require intubation and invasive mechanical ventilation after birth. While the duration of mechanical ventilation should be minimized in order to avoid complications, extubation failure is associated with increases in morbidities and mortality. As part of a prospective observational study aimed at developing an accurate predictor of extubation readiness, Markov and semi-Markov chain models were applied to gain insight into the respiratory patterns of these infants, with more robust time-series modeling using semi-Markov models. This model revealed interesting similarities and differences between newborns who succeeded extubation and those who failed. The parameters of the model were further applied to predict extubation readiness via generative (joint likelihood) and discriminative (support vector machine) approaches. Results showed that up to 84% of infants who failed extubation could have been accurately identified prior to extubation.
Tasks	Time Series
Published	2018-08-24
URL	http://arxiv.org/abs/1808.07991v1
PDF	http://arxiv.org/pdf/1808.07991v1.pdf
PWC	https://paperswithcode.com/paper/predicting-extubation-readiness-in-extreme
Repo
Framework

On Scale-out Deep Learning Training for Cloud and HPC


Title	On Scale-out Deep Learning Training for Cloud and HPC
Authors	Srinivas Sridharan, Karthikeyan Vaidyanathan, Dhiraj Kalamkar, Dipankar Das, Mikhail E. Smorkalov, Mikhail Shiryaev, Dheevatsa Mudigere, Naveen Mellempudi, Sasikanth Avancha, Bharat Kaul, Pradeep Dubey
Abstract	The exponential growth in use of large deep neural networks has accelerated the need for training these deep neural networks in hours or even minutes. This can only be achieved through scalable and efficient distributed training, since a single node/card cannot satisfy the compute, memory, and I/O requirements of today’s state-of-the-art deep neural networks. However, scaling synchronous Stochastic Gradient Descent (SGD) is still a challenging problem and requires continued research/development. This entails innovations spanning algorithms, frameworks, communication libraries, and system design. In this paper, we describe the philosophy, design, and implementation of Intel Machine Learning Scalability Library (MLSL) and present proof-points demonstrating scaling DL training on 100s to 1000s of nodes across Cloud and HPC systems.
Tasks
Published	2018-01-24
URL	http://arxiv.org/abs/1801.08030v1
PDF	http://arxiv.org/pdf/1801.08030v1.pdf
PWC	https://paperswithcode.com/paper/on-scale-out-deep-learning-training-for-cloud
Repo
Framework