October 17, 2019

3042 words 15 mins read

Paper Group ANR 681

Robot Representation and Reasoning with Knowledge from Reinforcement Learning. Detecting Levels of Depression in Text Based on Metrics. Deep Spectral Correspondence for Matching Disparate Image Pairs. Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL. Deep Learning for Launching and Mitigating Wireless Jamming Attacks. …

Robot Representation and Reasoning with Knowledge from Reinforcement Learning


Title	Robot Representation and Reasoning with Knowledge from Reinforcement Learning
Authors	Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen
Abstract	Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms are strong in declarative KRR tasks, but are ill-equipped to learn from such experiences. In this work, we integrate logical-probabilistic KRR with model-based RL, enabling agents to simultaneously reason with declarative knowledge and learn from interaction experiences. The knowledge from humans and RL is unified and used for dynamically computing task-specific planning models under potentially new environments. Experiments were conducted using a mobile robot working on dialog, navigation, and delivery tasks. Results show significant improvements, in comparison to existing model-based RL methods.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1809.11074v3
PDF	http://arxiv.org/pdf/1809.11074v3.pdf
PWC	https://paperswithcode.com/paper/robot-representation-and-reasoning-with
Repo
Framework

Detecting Levels of Depression in Text Based on Metrics


Title	Detecting Levels of Depression in Text Based on Metrics
Authors	Ashwath Kumar Salimath, Robin K Thomas, Sethuram Ramalinga Reddy, Yuhao Qiao
Abstract	Depression is one of the most common and a major concern for society. Proper monitoring using devices that can aid in its detection could be helpful to prevent it all together. The Distress Analysis Interview Corpus (DAIC) is used to build a metric-based depression detection. We have designed a metric to describe the level of depression using negative sentences and classify the participant accordingly. The score generated from the algorithm is then levelled up to denote the intensity of depression. The results show that measuring depression is very complex to using text alone as other factors are not taken into consideration. Further, In the paper, the limitations of measuring depression using text are described, and future suggestions are made.
Tasks
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03397v1
PDF	http://arxiv.org/pdf/1807.03397v1.pdf
PWC	https://paperswithcode.com/paper/detecting-levels-of-depression-in-text-based
Repo
Framework

Deep Spectral Correspondence for Matching Disparate Image Pairs


Title	Deep Spectral Correspondence for Matching Disparate Image Pairs
Authors	Arun CS Kumar, Shefali Srivastava, Anirban Mukhopadhyay, Suchendra M. Bhandarkar
Abstract	A novel, non-learning-based, saliency-aware, shape-cognizant correspondence determination technique is proposed for matching image pairs that are significantly disparate in nature. Images in the real world often exhibit high degrees of variation in scale, orientation, viewpoint, illumination and affine projection parameters, and are often accompanied by the presence of textureless regions and complete or partial occlusion of scene objects. The above conditions confound most correspondence determination techniques by rendering impractical the use of global contour-based descriptors or local pixel-level features for establishing correspondence. The proposed deep spectral correspondence (DSC) determination scheme harnesses the representational power of local feature descriptors to derive a complex high-level global shape representation for matching disparate images. The proposed scheme reasons about correspondence between disparate images using high-level global shape cues derived from low-level local feature descriptors. Consequently, the proposed scheme enjoys the best of both worlds, i.e., a high degree of invariance to affine parameters such as scale, orientation, viewpoint, illumination afforded by the global shape cues and robustness to occlusion provided by the low-level feature descriptors. While the shape-based component within the proposed scheme infers what to look for, an additional saliency-based component dictates where to look at thereby tackling the noisy correspondences arising from the presence of textureless regions and complex backgrounds. In the proposed scheme, a joint image graph is constructed using distances computed between interest points in the appearance (i.e., image) space. Eigenspectral decomposition of the joint image graph allows for reasoning about shape similarity to be performed jointly, in the appearance space and eigenspace.
Tasks	Matching Disparate Images
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04642v1
PDF	http://arxiv.org/pdf/1809.04642v1.pdf
PWC	https://paperswithcode.com/paper/deep-spectral-correspondence-for-matching
Repo
Framework

Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL


Title	Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Authors	Anusha Nagabandi, Chelsea Finn, Sergey Levine
Abstract	Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network models allow us to represent very complex functions, but lack this capacity for rapid online adaptation. The goal in this paper is to develop a method for continual online learning from an incoming stream of data, using deep neural network models. We formulate an online learning procedure that uses stochastic gradient descent to update model parameters, and an expectation maximization algorithm with a Chinese restaurant process prior to develop and maintain a mixture of models to handle non-stationary task distributions. This allows for all models to be adapted as necessary, with new models instantiated for task changes and old models recalled when previously seen tasks are encountered again. Furthermore, we observe that meta-learning can be used to meta-train a model such that this direct online adaptation with SGD is effective, which is otherwise not the case for large function approximators. In this work, we apply our meta-learning for online learning (MOLe) approach to model-based reinforcement learning, where adapting the predictive model is critical for control; we demonstrate that MOLe outperforms alternative prior methods, and enables effective continuous adaptation in non-stationary task distributions such as varying terrains, motor failures, and unexpected disturbances.
Tasks	Meta-Learning
Published	2018-12-18
URL	http://arxiv.org/abs/1812.07671v2
PDF	http://arxiv.org/pdf/1812.07671v2.pdf
PWC	https://paperswithcode.com/paper/deep-online-learning-via-meta-learning
Repo
Framework

Deep Learning for Launching and Mitigating Wireless Jamming Attacks


Title	Deep Learning for Launching and Mitigating Wireless Jamming Attacks
Authors	Tugba Erpek, Yalin E. Sagduyu, Yi Shi
Abstract	An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented. A cognitive transmitter uses a pre-trained classifier to predict the current channel status based on recent sensing results and decides whether to transmit or not, whereas a jammer collects channel status and ACKs to build a deep learning classifier that reliably predicts the next successful transmissions and effectively jams them. This jamming approach is shown to reduce the transmitter’s performance much more severely compared with random or sensing-based jamming. The deep learning classification scores are used by the jammer for power control subject to an average power constraint. Next, a generative adversarial network (GAN) is developed for the jammer to reduce the time to collect the training dataset by augmenting it with synthetic samples. As a defense scheme, the transmitter deliberately takes a small number of wrong actions in spectrum access (in form of a causative attack against the jammer) and therefore prevents the jammer from building a reliable classifier. The transmitter systematically selects when to take wrong actions and adapts the level of defense to mislead the jammer into making prediction errors and consequently increase its throughput.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.02567v2
PDF	http://arxiv.org/pdf/1807.02567v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-launching-and-mitigating
Repo
Framework

GAN Based Medical Image Registration


Title	GAN Based Medical Image Registration
Authors	Dwarikanath Mahapatra
Abstract	Conventional approaches to image registration consist of time consuming iterative methods. Most current deep learning (DL) based registration methods extract deep features to use in an iterative setting. We propose an end-to-end DL method for registering multimodal images. Our approach uses generative adversarial networks (GANs) that eliminates the need for time consuming iterative methods, and directly generates the registered image with the deformation field. Appropriate constraints in the GAN cost function produce accurately registered images in less than a second. Experiments demonstrate their accuracy for multimodal retinal and cardiac MR image registration.
Tasks	Image Registration, Medical Image Registration
Published	2018-05-07
URL	https://arxiv.org/abs/1805.02369v4
PDF	https://arxiv.org/pdf/1805.02369v4.pdf
PWC	https://paperswithcode.com/paper/elastic-registration-of-medical-images-with
Repo
Framework

Search for Common Minima in Joint Optimization of Multiple Cost Functions


Title	Search for Common Minima in Joint Optimization of Multiple Cost Functions
Authors	Daiki Adachi, Naoto Tsujimoto, Ryosuke Akashi, Synge Todo, Shinji Tsuneyuki
Abstract	We present a novel optimization method, named the Combined Optimization Method (COM), for the joint optimization of two or more cost functions. Unlike the conventional joint optimization schemes, which try to find minima in a weighted sum of cost functions, the COM explores search space for common minima shared by all the cost functions. Given a set of multiple cost functions that have qualitatively different distributions of local minima with each other, the proposed method finds the common minima with a high success rate without the help of any metaheuristics. As a demonstration, we apply the COM to the crystal structure prediction in materials science. By introducing the concept of data assimilation, i.e., adopting the theoretical potential energy of the crystal and the crystallinity, which characterizes the agreement with the theoretical and experimental X-ray diffraction patterns, as cost functions, we show that the correct crystal structures of Si diamond, low quartz, and low cristobalite can be predicted with significantly higher success rates than the previous methods.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06846v1
PDF	http://arxiv.org/pdf/1808.06846v1.pdf
PWC	https://paperswithcode.com/paper/search-for-common-minima-in-joint
Repo
Framework

Lifelong Testing of Smart Autonomous Systems by Shepherding a Swarm of Watchdog Artificial Intelligence Agents


Title	Lifelong Testing of Smart Autonomous Systems by Shepherding a Swarm of Watchdog Artificial Intelligence Agents
Authors	Hussein Abbass, John Harvey, Kate Yaxley
Abstract	Artificial Intelligence (AI) technologies could be broadly categorised into Analytics and Autonomy. Analytics focuses on algorithms offering perception, comprehension, and projection of knowledge gleaned from sensorial data. Autonomy revolves around decision making, and influencing and shaping the environment through action production. A smart autonomous system (SAS) combines analytics and autonomy to understand, learn, decide and act autonomously. To be useful, SAS must be trusted and that requires testing. Lifelong learning of a SAS compounds the testing process. In the remote chance that it is possible to fully test and certify the system pre-release, which is theoretically an undecidable problem, it is near impossible to predict the future behaviours that these systems, alone or collectively, will exhibit. While it may be feasible to severely restrict such systems\textquoteright \ learning abilities to limit the potential unpredictability of their behaviours, an undesirable consequence may be severely limiting their utility. In this paper, we propose the architecture for a watchdog AI (WAI) agent dedicated to lifelong functional testing of SAS. We further propose system specifications including a level of abstraction whereby humans shepherd a swarm of WAI agents to oversee an ecosystem made of humans and SAS. The discussion extends to the challenges, pros, and cons of the proposed concept.
Tasks	Decision Making
Published	2018-12-21
URL	http://arxiv.org/abs/1812.08960v1
PDF	http://arxiv.org/pdf/1812.08960v1.pdf
PWC	https://paperswithcode.com/paper/lifelong-testing-of-smart-autonomous-systems
Repo
Framework

A Distance Oriented Kalman Filter Particle Swarm Optimizer Applied to Multi-Modality Image Registration


Title	A Distance Oriented Kalman Filter Particle Swarm Optimizer Applied to Multi-Modality Image Registration
Authors	Chengjia Wang, Keith A. Goatman, James Boardman, Erin Beveridge, David Newby, Scott Semple
Abstract	In this paper we describe improvements to the particle swarm optimizer (PSO) made by inclusion of an unscented Kalman filter to guide particle motion. We demonstrate the effectiveness of the unscented Kalman filter PSO by comparing it with the original PSO algorithm and its variants designed to improve performance. The PSOs were tested firstly on a number of common synthetic benchmarking functions, and secondly applied to a practical three-dimensional image registration problem. The proposed methods displayed better performances for 4 out of 8 benchmark functions, and reduced the target registration errors by at least 2mm when registering down-sampled benchmark brain images. Our methods also demonstrated an ability to align images featuring motion related artefacts which all other methods failed to register. These new PSO methods provide a novel, efficient mechanism to integrate prior knowledge into each iteration of the optimization process, which can enhance the accuracy and speed of convergence in the application of medical image registration.
Tasks	Image Registration, Medical Image Registration
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07423v1
PDF	http://arxiv.org/pdf/1803.07423v1.pdf
PWC	https://paperswithcode.com/paper/a-distance-oriented-kalman-filter-particle
Repo
Framework

Machine Learning on Electronic Health Records: Models and Features Usages to predict Medication Non-Adherence


Title	Machine Learning on Electronic Health Records: Models and Features Usages to predict Medication Non-Adherence
Authors	Thomas Janssoone, Clémence Bic, Dorra Kanoun, Pierre Hornus, Pierre Rinder
Abstract	Adherence can be defined as “the extent to which patients take their medications as prescribed by their healthcare providers”[Osterberg and Blaschke, 2005]. World Health Organization’s reports point out that, in developed countries, only about 50% of patients with chronic diseases correctly follow their treatments. This severely compromises the efficiency of long-term therapy and increases the cost of health services. We propose in this paper different models of patient drug consumption in breast cancer treatments. The aim of these different approaches is to predict medication non-adherence while giving insights to doctors of the underlying reasons of these illegitimate drop-outs. Working with oncologists, we show the interest of Machine- Learning algorithms fined tune by the feedback of experts to estimate a risk score of a patient’s non-adherence and thus improve support throughout their care path.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12234v1
PDF	http://arxiv.org/pdf/1811.12234v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-on-electronic-health-records
Repo
Framework

Towards Distributed Energy Services: Decentralizing Optimal Power Flow with Machine Learning


Title	Towards Distributed Energy Services: Decentralizing Optimal Power Flow with Machine Learning
Authors	Roel Dobbe, Oscar Sondermeijer, David Fridovich-Keil, Daniel Arnold, Duncan Callaway, Claire Tomlin
Abstract	The implementation of optimal power flow (OPF) methods to perform voltage and power flow regulation in electric networks is generally believed to require extensive communication. We consider distribution systems with multiple controllable Distributed Energy Resources (DERs) and present a data-driven approach to learn control policies for each DER to reconstruct and mimic the solution to a centralized OPF problem from solely locally available information. Collectively, all local controllers closely match the centralized OPF solution, providing near optimal performance and satisfaction of system constraints. A rate distortion framework enables the analysis of how well the resulting fully decentralized control policies are able to reconstruct the OPF solution. The methodology provides a natural extension to decide what nodes a DER should communicate with to improve the reconstruction of its individual policy. The method is applied on both single- and three-phase test feeder networks using data from real loads and distributed generators, focusing on DERs that do not exhibit inter-temporal dependencies. It provides a framework for Distribution System Operators to efficiently plan and operate the contributions of DERs to achieve Distributed Energy Services in distribution networks.
Tasks
Published	2018-06-14
URL	https://arxiv.org/abs/1806.06790v3
PDF	https://arxiv.org/pdf/1806.06790v3.pdf
PWC	https://paperswithcode.com/paper/data-driven-decentralized-optimal-power-flow
Repo
Framework

Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?


Title	Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?
Authors	Mingyue Shang, Zhenxin Fu, Hongzhi Yin, Bo Tang, Dongyan Zhao, Rui Yan
Abstract	Natural language understanding is a challenging problem that covers a wide range of tasks. While previous methods generally train each task separately, we consider combining the cross-task features to enhance the task performance. In this paper, we incorporate the logic information with the help of the Natural Language Inference (NLI) task to the Story Cloze Test (SCT). Previous work on SCT considered various semantic information, such as sentiment and topic, but lack the logic information between sentences which is an essential element of stories. Thus we propose to extract the logic information during the course of the story to improve the understanding of the whole story. The logic information is modeled with the help of the NLI task. Experimental results prove the strength of the logic information.
Tasks	Natural Language Inference
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05411v1
PDF	http://arxiv.org/pdf/1812.05411v1.pdf
PWC	https://paperswithcode.com/paper/find-a-reasonable-ending-for-stories-does
Repo
Framework

A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing


Title	A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing
Authors	Dat Quoc Nguyen
Abstract	We propose the first multi-task learning model for joint Vietnamese word segmentation, part-of-speech (POS) tagging and dependency parsing. In particular, our model extends the BIST graph-based dependency parser (Kiperwasser and Goldberg, 2016) with BiLSTM-CRF-based neural layers (Huang et al., 2015) for word segmentation and POS tagging. On Vietnamese benchmark datasets, experimental results show that our joint model obtains state-of-the-art or competitive performances.
Tasks	Dependency Parsing, Multi-Task Learning, Part-Of-Speech Tagging
Published	2018-12-30
URL	https://arxiv.org/abs/1812.11459v3
PDF	https://arxiv.org/pdf/1812.11459v3.pdf
PWC	https://paperswithcode.com/paper/a-neural-joint-model-for-vietnamese-word
Repo
Framework

Layer-wise Relevance Propagation for Explainable Recommendations


Title	Layer-wise Relevance Propagation for Explainable Recommendations
Authors	Homanga Bharadhwaj
Abstract	In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in feature space. Relationships between the images are identified by the model and layer-wise relevance propagation is used to infer pixel-level details of the images that may have significantly informed the model’s choice. We evaluate our method on an Amazon products dataset and demonstrate the efficacy of our approach.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06160v1
PDF	http://arxiv.org/pdf/1807.06160v1.pdf
PWC	https://paperswithcode.com/paper/layer-wise-relevance-propagation-for
Repo
Framework

Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systems


Title	Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systems
Authors	Yuqian Jiang, Shiqi Zhang, Piyush Khandelwal, Peter Stone
Abstract	Robots need task planning algorithms to sequence actions toward accomplishing goals that are impossible through individual actions. Off-the-shelf task planners can be used by intelligent robotics practitioners to solve a variety of planning problems. However, many different planners exist, each with different strengths and weaknesses, and there are no general rules for which planner would be best to apply to a given problem. In this article, we empirically compare the performance of state-of-the-art planners that use either the Planning Domain Description Language (PDDL), or Answer Set Programming (ASP) as the underlying action language. PDDL is designed for task planning, and PDDL-based planners are widely used for a variety of planning problems. ASP is designed for knowledge-intensive reasoning, but can also be used for solving task planning problems. Given domain encodings that are as similar as possible, we find that PDDL-based planners perform better on problems with longer solutions, and ASP-based planners are better on tasks with a large number of objects or in which complex reasoning is required to reason about action preconditions and effects. The resulting analysis can inform selection among general purpose planning systems for particular robot task planning domains.
Tasks	Robot Task Planning
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08229v3
PDF	http://arxiv.org/pdf/1804.08229v3.pdf
PWC	https://paperswithcode.com/paper/task-planning-in-robotics-an-empirical
Repo
Framework