October 19, 2019

3082 words 15 mins read

Paper Group ANR 243

YouTube for Patient Education: A Deep Learning Approach for Understanding Medical Knowledge from User-Generated Videos. Counterfactual equivalence for POMDPs, and underlying deterministic environments. MIWAE: Deep Generative Modelling and Imputation of Incomplete Data. A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scal …

YouTube for Patient Education: A Deep Learning Approach for Understanding Medical Knowledge from User-Generated Videos


Title	YouTube for Patient Education: A Deep Learning Approach for Understanding Medical Knowledge from User-Generated Videos
Authors	Xiao Liu, Bin Zhang, Anjana Susarla, Rema Padman
Abstract	YouTube presents an unprecedented opportunity to explore how machine learning methods can improve healthcare information dissemination. We propose an interdisciplinary lens that synthesizes machine learning methods with healthcare informatics themes to address the critical issue of developing a scalable algorithmic solution to evaluate videos from a health literacy and patient education perspective. We develop a deep learning method to understand the level of medical knowledge encoded in YouTube videos. Preliminary results suggest that we can extract medical knowledge from YouTube videos and classify videos according to the embedded knowledge with satisfying performance. Deep learning methods show great promise in knowledge extraction, natural language understanding, and image classification, especially in an era of patient-centric care and precision medicine.
Tasks	Image Classification
Published	2018-07-06
URL	http://arxiv.org/abs/1807.03179v1
PDF	http://arxiv.org/pdf/1807.03179v1.pdf
PWC	https://paperswithcode.com/paper/youtube-for-patient-education-a-deep-learning
Repo
Framework

Counterfactual equivalence for POMDPs, and underlying deterministic environments


Title	Counterfactual equivalence for POMDPs, and underlying deterministic environments
Authors	Stuart Armstrong
Abstract	Partially Observable Markov Decision Processes (POMDPs) are rich environments often used in machine learning. But the issue of information and causal structures in POMDPs has been relatively little studied. This paper presents the concepts of equivalent and counterfactually equivalent POMDPs, where agents cannot distinguish which environment they are in though any observations and actions. It shows that any POMDP is counterfactually equivalent, for any finite number of turns, to a deterministic POMDP with all uncertainty concentrated into the initial state. This allows a better understanding of POMDP uncertainty, information, and learning.
Tasks
Published	2018-01-11
URL	http://arxiv.org/abs/1801.03737v2
PDF	http://arxiv.org/pdf/1801.03737v2.pdf
PWC	https://paperswithcode.com/paper/counterfactual-equivalence-for-pomdps-and
Repo
Framework

MIWAE: Deep Generative Modelling and Imputation of Incomplete Data


Title	MIWAE: Deep Generative Modelling and Imputation of Incomplete Data
Authors	Pierre-Alexandre Mattei, Jes Frellsen
Abstract	We consider the problem of handling missing data with deep latent variable models (DLVMs). First, we present a simple technique to train DLVMs when the training set contains missing-at-random data. Our approach, called MIWAE, is based on the importance-weighted autoencoder (IWAE), and maximises a potentially tight lower bound of the log-likelihood of the observed data. Compared to the original IWAE, our algorithm does not induce any additional computational overhead due to the missing data. We also develop Monte Carlo techniques for single and multiple imputation using a DLVM trained on an incomplete data set. We illustrate our approach by training a convolutional DLVM on a static binarisation of MNIST that contains 50% of missing pixels. Leveraging multiple imputation, a convolutional network trained on these incomplete digits has a test performance similar to one trained on complete data. On various continuous and binary data sets, we also show that MIWAE provides accurate single imputations, and is highly competitive with state-of-the-art methods.
Tasks	Imputation, Latent Variable Models
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02633v2
PDF	http://arxiv.org/pdf/1812.02633v2.pdf
PWC	https://paperswithcode.com/paper/miwae-deep-generative-modelling-and
Repo
Framework

A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations


Title	A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations
Authors	Biswajit Paria, Kirthevasan Kandasamy, Barnabás Póczos
Abstract	Many real world applications can be framed as multi-objective optimization problems, where we wish to simultaneously optimize for multiple criteria. Bayesian optimization techniques for the multi-objective setting are pertinent when the evaluation of the functions in question are expensive. Traditional methods for multi-objective optimization, both Bayesian and otherwise, are aimed at recovering the Pareto front of these objectives. However, in certain cases a practitioner might desire to identify Pareto optimal points only in a subset of the Pareto front due to external considerations. In this work, we propose a strategy based on random scalarizations of the objectives that addresses this problem. Our approach is able to flexibly sample from desired regions of the Pareto front and, computationally, is considerably cheaper than most approaches for MOO. We also study a notion of regret in the multi-objective setting and show that our strategy achieves sublinear regret. We experiment with both synthetic and real-life problems, and demonstrate superior performance of our proposed algorithm in terms of the flexibility and regret.
Tasks
Published	2018-05-30
URL	https://arxiv.org/abs/1805.12168v3
PDF	https://arxiv.org/pdf/1805.12168v3.pdf
PWC	https://paperswithcode.com/paper/a-flexible-framework-for-multi-objective
Repo
Framework

Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment


Title	Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment
Authors	Daniel Cullina, Negar Kiyavash, Prateek Mittal, H. Vincent Poor
Abstract	We determine information theoretic conditions under which it is possible to partially recover the alignment used to generate a pair of sparse, correlated Erd\H{o}s-R'enyi graphs. To prove our achievability result, we introduce the $k$-core alignment estimator. This estimator searches for an alignment in which the intersection of the correlated graphs using this alignment has a minimum degree of $k$. We prove a matching converse bound. As the number of vertices grows, recovery of the alignment for a fraction of the vertices tending to one is possible when the average degree of the intersection of the graph pair tends to infinity. It was previously known that exact alignment is possible when this average degree grows faster than the logarithm of the number of vertices.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03553v2
PDF	http://arxiv.org/pdf/1809.03553v2.pdf
PWC	https://paperswithcode.com/paper/partial-recovery-of-erdos-renyi-graph
Repo
Framework

Human and Smart Machine Co-Learning with Brain Computer Interface


Title	Human and Smart Machine Co-Learning with Brain Computer Interface
Authors	Chang-Shing Lee, Mei-Hui Wang, Li-Wei Ko, Naoyuki Kubota, Lu-An Lin, Shinya Kitaoka, Yu-Te Wang, Shun-Feng Su
Abstract	Machine learning has become a very popular approach for cybernetics systems, and it has always been considered important research in the Computational Intelligence area. Nevertheless, when it comes to smart machines, it is not just about the methodologies. We need to consider systems and cybernetics as well as include human in the loop. The purpose of this article is as follows: (1) To integrate the open source Facebook AI Research (FAIR) DarkForest program of Facebook with Item Response Theory (IRT), to the new open learning system, namely, DDF learning system; (2) To integrate DDF Go with Robot namely Robotic DDF Go system; (3) To invite the professional Go players to attend the activity to play Go games on site with a smart machine. The research team will apply this technology to education, such as, playing games to enhance the children concentration on learning mathematics, languages, and other topics. With the detected brainwaves, the robot will be able to speak some words that are very much to the point for the students and to assist the teachers in classroom in the future.
Tasks
Published	2018-02-19
URL	http://arxiv.org/abs/1802.06521v1
PDF	http://arxiv.org/pdf/1802.06521v1.pdf
PWC	https://paperswithcode.com/paper/human-and-smart-machine-co-learning-with
Repo
Framework

Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy


Title	Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy
Authors	Ognjen Rudovic, Jaeryoung Lee, Miles Dai, Bjorn Schuller, Rosalind Picard
Abstract	Robots have great potential to facilitate future therapies for children on the autism spectrum. However, existing robots lack the ability to automatically perceive and respond to human affect, which is necessary for establishing and maintaining engaging interactions. Moreover, their inference challenge is made harder by the fact that many individuals with autism have atypical and unusually diverse styles of expressing their affective-cognitive states. To tackle the heterogeneity in behavioral cues of children with autism, we use the latest advances in deep learning to formulate a personalized machine learning (ML) framework for automatic perception of the childrens affective states and engagement during robot-assisted autism therapy. The key to our approach is a novel shift from the traditional ML paradigm - instead of using ‘one-size-fits-all’ ML models, our personalized ML framework is optimized for each child by leveraging relevant contextual information (demographics and behavioral assessment scores) and individual characteristics of each child. We designed and evaluated this framework using a dataset of multi-modal audio, video and autonomic physiology data of 35 children with autism (age 3-13) and from 2 cultures (Asia and Europe), participating in a 25-minute child-robot interaction (~500k datapoints). Our experiments confirm the feasibility of the robot perception of affect and engagement, showing clear improvements due to the model personalization. The proposed approach has potential to improve existing therapies for autism by offering more efficient monitoring and summarization of the therapy progress.
Tasks
Published	2018-02-04
URL	http://arxiv.org/abs/1802.01186v2
PDF	http://arxiv.org/pdf/1802.01186v2.pdf
PWC	https://paperswithcode.com/paper/personalized-machine-learning-for-robot
Repo
Framework

ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting


Title	ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting
Authors	Srayanta Mukherjee, Devashish Shankar, Atin Ghosh, Nilam Tathawadekar, Pramod Kompalli, Sunita Sarawagi, Krishnendu Chaudhury
Abstract	Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes. The challenge, however, is the large number of associative factors that result in large, non-stationary shifts in demand, which traditional time series and regression approaches fail to model. In this paper, we propose a Neural Network architecture called AR-MDN, that simultaneously models associative factors, time-series trends and the variance in the demand. We first identify several causal features and use a combination of feature embeddings, MLP and LSTM to represent them. We then model the output density as a learned mixture of Gaussian distributions. The AR-MDN can be trained end-to-end without the need for additional supervision. We experiment on a dataset of an year’s worth of data over tens-of-thousands of products from Flipkart. The proposed architecture yields a significant improvement in forecasting accuracy when compared with existing alternatives.
Tasks	Time Series
Published	2018-03-10
URL	http://arxiv.org/abs/1803.03800v2
PDF	http://arxiv.org/pdf/1803.03800v2.pdf
PWC	https://paperswithcode.com/paper/armdn-associative-and-recurrent-mixture
Repo
Framework

Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation


Title	Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation
Authors	Wei He, Naoto Yokoya
Abstract	In this paper, we present the optical image simulation from a synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SARoptical data, are proposed to testify the possibilities. The deep learning based methods that we chose to achieve the models are a convolutional neural network (CNN) with a residual architecture and a conditional generative adversarial network (cGAN). We validate our models using the Sentinel-1 and -2 datasets. The experiments demonstrate that the model with multi-temporal SAR-optical data can successfully simulate the optical image, meanwhile, the model with simple SAR data as input failed. The optical image simulation results indicate the possibility of SARoptical information blending for the subsequent applications such as large-scale cloud removal, and optical data temporal superresolution. We also investigate the sensitivity of the proposed models against the training samples, and reveal possible future directions.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09954v1
PDF	http://arxiv.org/pdf/1807.09954v1.pdf
PWC	https://paperswithcode.com/paper/multi-temporal-sentinel-1-and-2-data-fusion
Repo
Framework

The ORCA Hub: Explainable Offshore Robotics through Intelligent Interfaces


Title	The ORCA Hub: Explainable Offshore Robotics through Intelligent Interfaces
Authors	Helen Hastie, Katrin Lohan, Mike Chantler, David A. Robb, Subramanian Ramamoorthy, Ron Petrick, Sethu Vijayakumar, David Lane
Abstract	We present the UK Robotics and Artificial Intelligence Hub for Offshore Robotics for Certification of Assets (ORCA Hub), a 3.5 year EPSRC funded, multi-site project. The ORCA Hub vision is to use teams of robots and autonomous intelligent systems (AIS) to work on offshore energy platforms to enable cheaper, safer and more efficient working practices. The ORCA Hub will research, integrate, validate and deploy remote AIS solutions that can operate with existing and future offshore energy assets and sensors, interacting safely in autonomous or semi-autonomous modes in complex and cluttered environments, co-operating with remote operators. The goal is that through the use of such robotic systems offshore, the need for personnel will decrease. To enable this to happen, the remote operator will need a high level of situation awareness and key to this is the transparency of what the autonomous systems are doing and why. This increased transparency will facilitate a trusting relationship, which is particularly key in high-stakes, hazardous situations.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02100v1
PDF	http://arxiv.org/pdf/1803.02100v1.pdf
PWC	https://paperswithcode.com/paper/the-orca-hub-explainable-offshore-robotics
Repo
Framework

Classification of volcanic ash particles using a convolutional neural network and probability


Title	Classification of volcanic ash particles using a convolutional neural network and probability
Authors	Daigo Shoji, Rina Noguchi, Shizuka Otsuki, Hideitsu Hino
Abstract	Analyses of volcanic ash are typically performed either by qualitatively classifying ash particles by eye or by quantitatively parameterizing its shape and texture. While complex shapes can be classified through qualitative analyses, the results are subjective due to the difficulty of categorizing complex shapes into a single class. Although quantitative analyses are objective, selection of shape parameters is required. Here, we applied a convolutional neural network (CNN) for the classification of volcanic ash. First, we defined four basal particle shapes (blocky, vesicular, elongated, rounded) generated by different eruption mechanisms (e.g., brittle fragmentation), and then trained the CNN using particles composed of only one basal shape. The CNN could recognize the basal shapes with over 90% accuracy. Using the trained network, we classified ash particles composed of multiple basal shapes based on the output of the network, which can be interpreted as a mixing ratio of the four basal shapes. Clustering of samples by the averaged probabilities and the intensity is consistent with the eruption type. The mixing ratio output by the CNN can be used to quantitatively classify complex shapes in nature without categorizing forcibly and without the need for shape parameters, which may lead to a new taxonomy.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12353v1
PDF	http://arxiv.org/pdf/1805.12353v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-volcanic-ash-particles
Repo
Framework

Switch-LSTMs for Multi-Criteria Chinese Word Segmentation


Title	Switch-LSTMs for Multi-Criteria Chinese Word Segmentation
Authors	Jingjing Gong, Xinchi Chen, Tao Gui, Xipeng Qiu
Abstract	Multi-criteria Chinese word segmentation is a promising but challenging task, which exploits several different segmentation criteria and mines their common underlying knowledge. In this paper, we propose a flexible multi-criteria learning for Chinese word segmentation. Usually, a segmentation criterion could be decomposed into multiple sub-criteria, which are shareable with other segmentation criteria. The process of word segmentation is a routing among these sub-criteria. From this perspective, we present Switch-LSTMs to segment words, which consist of several long short-term memory neural networks (LSTM), and a switcher to automatically switch the routing among these LSTMs. With these auto-switched LSTMs, our model provides a more flexible solution for multi-criteria CWS, which is also easy to transfer the learned knowledge to new criteria. Experiments show that our model obtains significant improvements on eight corpora with heterogeneous segmentation criteria, compared to the previous method and single-criterion learning.
Tasks	Chinese Word Segmentation
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08033v1
PDF	http://arxiv.org/pdf/1812.08033v1.pdf
PWC	https://paperswithcode.com/paper/switch-lstms-for-multi-criteria-chinese-word
Repo
Framework

Analyzing Compositionality-Sensitivity of NLI Models


Title	Analyzing Compositionality-Sensitivity of NLI Models
Authors	Yixin Nie, Yicheng Wang, Mohit Bansal
Abstract	Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are over-relying on the former and fail to use the latter. Further, this compositionality unawareness is not reflected via standard evaluation on current datasets. We show that removing RNNs in existing models or shuffling input words during training does not induce large performance loss despite the explicit removal of compositional information. Therefore, we propose a compositionality-sensitivity testing setup that analyzes models on natural examples from existing datasets that cannot be solved via lexical features alone (i.e., on which a bag-of-words model gives a high probability to one wrong label), hence revealing the models’ actual compositionality awareness. We show that this setup not only highlights the limited compositional ability of current NLI models, but also differentiates model performance based on design, e.g., separating shallow bag-of-words models from deeper, linguistically-grounded tree-based models. Our evaluation setup is an important analysis tool: complementing currently existing adversarial and linguistically driven diagnostic evaluations, and exposing opportunities for future work on evaluating models’ compositional understanding.
Tasks	Natural Language Inference
Published	2018-11-16
URL	http://arxiv.org/abs/1811.07033v1
PDF	http://arxiv.org/pdf/1811.07033v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-compositionality-sensitivity-of-nli
Repo
Framework

Solution Dominance over Constraint Satisfaction Problems


Title	Solution Dominance over Constraint Satisfaction Problems
Authors	Tias Guns, Peter J. Stuckey, Guido Tack
Abstract	Constraint Satisfaction Problems (CSPs) typically have many solutions that satisfy all constraints. Often though, some solutions are preferred over others, that is, some solutions dominate other solutions. We present solution dominance as a formal framework to reason about such settings. We define Constraint Dominance Problems (CDPs) as CSPs with a dominance relation, that is, a preorder over the solutions of the CSP. This framework captures many well-known variants of constraint satisfaction, including optimization, multi-objective optimization, Max-CSP, minimal models, minimum correction subsets as well as optimization over CP-nets and arbitrary dominance relations. We extend MiniZinc, a declarative language for modeling CSPs, to CDPs by introducing dominance nogoods; these can be derived from dominance relations in a principled way. A generic method for solving arbitrary CDPs incrementally calls a CSP solver and is compatible with any existing solver that supports MiniZinc. This encourages experimenting with different solution dominance relations for a problem, as well as comparing different solvers without having to modify their implementations.
Tasks
Published	2018-12-21
URL	http://arxiv.org/abs/1812.09207v1
PDF	http://arxiv.org/pdf/1812.09207v1.pdf
PWC	https://paperswithcode.com/paper/solution-dominance-over-constraint
Repo
Framework

A Neural-Network-Based Optimal Control of Ultra-Capacitors with System Uncertainties


Title	A Neural-Network-Based Optimal Control of Ultra-Capacitors with System Uncertainties
Authors	Jiajun Duan, Zhehan Yi, Di Shi, Hao Xu, Zhiwei Wang
Abstract	In this paper, a neural-network (NN)-based online optimal control method (NN-OPT) is proposed for ultra-capacitors (UCs) energy storage system (ESS) in hybrid AC/DC microgrids involving multiple distributed generations (e.g., Photovoltaic (PV) system, battery storage, diesel generator). Conventional control strategies usually produce large disturbances to buses during charging and discharging (C&D) processes of UCs, which significantly degrades the power quality and system performance, especially under fast C&D modes. Therefore, the optimal control theory is adopted to optimize the C&D profile as well as to suppress the disturbances caused by UCs implementation. Specifically, an NN-based intelligent algorithm is developed to learn the optimal control policy for bidirectional-converter-interfaced UCs. The inaccuracies of system modeling are also considered in the control design. Since the designed NN-OPT method is decentralized that only requires the local measurements, plug & play of UCs can be easily realized with minimal communication efforts. In addition, the PV system is under the maximum power point tracking (MPPT) control to extract the maximum benefit. Both islanded and grid-tied modes are considered during the controller design. Extensive case studies have been conducted to evaluate the effectiveness of the proposed method.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12539v2
PDF	http://arxiv.org/pdf/1811.12539v2.pdf
PWC	https://paperswithcode.com/paper/a-neuron-network-based-optimal-control-of
Repo
Framework