May 6, 2019

3031 words 15 mins read

Paper Group ANR 188

Proactive Decision Support using Automated Planning. Responses to Critiques on Machine Learning of Criminality Perceptions (Addendum of arXiv:1611.04135). Characterization of neighborhood behaviours in a multi-neighborhood local search algorithm. Optimal Rates of Statistical Seriation. Full Flow: Optical Flow Estimation By Global Optimization over …

Proactive Decision Support using Automated Planning


Title	Proactive Decision Support using Automated Planning
Authors	Satya Gautam Vadlamudi, Tathagata Chakraborti, Yu Zhang, Subbarao Kambhampati
Abstract	Proactive decision support (PDS) helps in improving the decision making experience of human decision makers in human-in-the-loop planning environments. Here both the quality of the decisions and the ease of making them are enhanced. In this regard, we propose a PDS framework, named RADAR, based on the research in Automated Planning in AI, that aids the human decision maker with her plan to achieve her goals by providing alerts on: whether such a plan can succeed at all, whether there exist any resource constraints that may foil her plan, etc. This is achieved by generating and analyzing the landmarks that must be accomplished by any successful plan on the way to achieving the goals. Note that, this approach also supports naturalistic decision making which is being acknowledged as a necessary element in proactive decision support, since it only aids the human decision maker through suggestions and alerts rather than enforcing fixed plans or decisions. We demonstrate the utility of the proposed framework through search-and-rescue examples in a fire-fighting domain.
Tasks	Decision Making
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07841v1
PDF	http://arxiv.org/pdf/1606.07841v1.pdf
PWC	https://paperswithcode.com/paper/proactive-decision-support-using-automated
Repo
Framework

Responses to Critiques on Machine Learning of Criminality Perceptions (Addendum of arXiv:1611.04135)


Title	Responses to Critiques on Machine Learning of Criminality Perceptions (Addendum of arXiv:1611.04135)
Authors	Xiaolin Wu, Xi Zhang
Abstract	In November 2016 we submitted to arXiv our paper “Automated Inference on Criminality Using Face Images”. It generated a great deal of discussions in the Internet and some media outlets. Our work is only intended for pure academic discussions; how it has become a media consumption is a total surprise to us. Although in agreement with our critics on the need and importance of policing AI research for the general good of the society, we are deeply baffled by the ways some of them mispresented our work, in particular the motive and objective of our research.
Tasks
Published	2016-11-13
URL	http://arxiv.org/abs/1611.04135v3
PDF	http://arxiv.org/pdf/1611.04135v3.pdf
PWC	https://paperswithcode.com/paper/responses-to-critiques-on-machine-learning-of
Repo
Framework

Characterization of neighborhood behaviours in a multi-neighborhood local search algorithm


Title	Characterization of neighborhood behaviours in a multi-neighborhood local search algorithm
Authors	Nguyen Thi Thanh Dang, Patrick De Causmaecker
Abstract	We consider a multi-neighborhood local search algorithm with a large number of possible neighborhoods. Each neighborhood is accompanied by a weight value which represents the probability of being chosen at each iteration. These weights are fixed before the algorithm runs, and are considered as parameters of the algorithm. Given a set of instances, off-line tuning of the algorithm’s parameters can be done by automated algorithm configuration tools (e.g., SMAC). However, the large number of neighborhoods can make the tuning expensive and difficult even when the number of parameters has been reduced by some intuition. In this work, we propose a systematic method to characterize each neighborhood’s behaviours, representing them as a feature vector, and using cluster analysis to form similar groups of neighborhoods. The novelty of our characterization method is the ability of reflecting changes of behaviours according to hardness of different solution quality regions. We show that using neighborhood clusters instead of individual neighborhoods helps to reduce the parameter configuration space without misleading the search of the tuning procedure. Moreover, this method is problem-independent and potentially can be applied in similar contexts.
Tasks
Published	2016-03-12
URL	http://arxiv.org/abs/1603.06459v1
PDF	http://arxiv.org/pdf/1603.06459v1.pdf
PWC	https://paperswithcode.com/paper/characterization-of-neighborhood-behaviours
Repo
Framework

Optimal Rates of Statistical Seriation


Title	Optimal Rates of Statistical Seriation
Authors	Nicolas Flammarion, Cheng Mao, Philippe Rigollet
Abstract	Given a matrix the seriation problem consists in permuting its rows in such way that all its columns have the same shape, for example, they are monotone increasing. We propose a statistical approach to this problem where the matrix of interest is observed with noise and study the corresponding minimax rate of estimation of the matrices. Specifically, when the columns are either unimodal or monotone, we show that the least squares estimator is optimal up to logarithmic factors and adapts to matrices with a certain natural structure. Finally, we propose a computationally efficient estimator in the monotonic case and study its performance both theoretically and experimentally. Our work is at the intersection of shape constrained estimation and recent work that involves permutation learning, such as graph denoising and ranking.
Tasks	Denoising
Published	2016-07-08
URL	http://arxiv.org/abs/1607.02435v3
PDF	http://arxiv.org/pdf/1607.02435v3.pdf
PWC	https://paperswithcode.com/paper/optimal-rates-of-statistical-seriation
Repo
Framework

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids


Title	Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids
Authors	Qifeng Chen, Vladlen Koltun
Abstract	We present a global optimization approach to optical flow estimation. The approach optimizes a classical optical flow objective over the full space of mappings between discrete grids. No descriptor matching is used. The highly regular structure of the space of mappings enables optimizations that reduce the computational complexity of the algorithm’s inner loop from quadratic to linear and support efficient matching of tens of thousands of nodes to tens of thousands of displacements. We show that one-shot global optimization of a classical Horn-Schunck-type objective over regular grids at a single resolution is sufficient to initialize continuous interpolation and achieve state-of-the-art performance on challenging modern benchmarks.
Tasks	Optical Flow Estimation
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03513v1
PDF	http://arxiv.org/pdf/1604.03513v1.pdf
PWC	https://paperswithcode.com/paper/full-flow-optical-flow-estimation-by-global
Repo
Framework

Multi-Label Classification Method Based on Extreme Learning Machines


Title	Multi-Label Classification Method Based on Extreme Learning Machines
Authors	Rajasekar Venkatesan, Meng Joo Er
Abstract	In this paper, an Extreme Learning Machine (ELM) based technique for Multi-label classification problems is proposed and discussed. In multi-label classification, each of the input data samples belongs to one or more than one class labels. The traditional binary and multi-class classification problems are the subset of the multi-label problem with the number of labels corresponding to each sample limited to one. The proposed ELM based multi-label classification technique is evaluated with six different benchmark multi-label datasets from different domains such as multimedia, text and biology. A detailed comparison of the results is made by comparing the proposed method with the results from nine state of the arts techniques for five different evaluation metrics. The nine methods are chosen from different categories of multi-label methods. The comparative results shows that the proposed Extreme Learning Machine based multi-label classification technique is a better alternative than the existing state of the art methods for multi-label problems.
Tasks	Multi-Label Classification
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08435v1
PDF	http://arxiv.org/pdf/1608.08435v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-classification-method-based-on
Repo
Framework

Generalized Direct Change Estimation in Ising Model Structure


Title	Generalized Direct Change Estimation in Ising Model Structure
Authors	Farideh Fazayeli, Arindam Banerjee
Abstract	We consider the problem of estimating change in the dependency structure between two $p$-dimensional Ising models, based on respectively $n_1$ and $n_2$ samples drawn from the models. The change is assumed to be structured, e.g., sparse, block sparse, node-perturbed sparse, etc., such that it can be characterized by a suitable (atomic) norm. We present and analyze a norm-regularized estimator for directly estimating the change in structure, without having to estimate the structures of the individual Ising models. The estimator can work with any norm, and can be generalized to other graphical models under mild assumptions. We show that only one set of samples, say $n_2$, needs to satisfy the sample complexity requirement for the estimator to work, and the estimation error decreases as $\frac{c}{\sqrt{\min(n_1,n_2)}}$, where $c$ depends on the Gaussian width of the unit norm ball. For example, for $\ell_1$ norm applied to $s$-sparse change, the change can be accurately estimated with $\min(n_1,n_2)=O(s \log p)$ which is sharper than an existing result $n_1= O(s^2 \log p)$ and $n_2 = O(n_1^2)$. Experimental results illustrating the effectiveness of the proposed estimator are presented.
Tasks
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05302v1
PDF	http://arxiv.org/pdf/1606.05302v1.pdf
PWC	https://paperswithcode.com/paper/generalized-direct-change-estimation-in-ising
Repo
Framework

Safe Policy Improvement by Minimizing Robust Baseline Regret


Title	Safe Policy Improvement by Minimizing Robust Baseline Regret
Authors	Marek Petrik, Yinlam Chow, Mohammad Ghavamzadeh
Abstract	An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and analyze a new model-based approach to compute a safe policy when we have access to an inaccurate dynamics model of the system with known accuracy guarantees. Our proposed robust method uses this (inaccurate) model to directly minimize the (negative) regret w.r.t. the baseline policy. Contrary to the existing approaches, minimizing the regret allows one to improve the baseline policy in states with accurate dynamics and seamlessly fall back to the baseline policy, otherwise. We show that our formulation is NP-hard and propose an approximate algorithm. Our empirical results on several domains show that even this relatively simple approximate algorithm can significantly outperform standard approaches.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03842v1
PDF	http://arxiv.org/pdf/1607.03842v1.pdf
PWC	https://paperswithcode.com/paper/safe-policy-improvement-by-minimizing-robust
Repo
Framework

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature


Title	POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
Authors	Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan
Abstract	Detection and learning based appearance feature play the central role in data association based multiple object tracking (MOT), but most recent MOT works usually ignore them and only focus on the hand-crafted feature and association algorithms. In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting. We make our detection and appearance feature publicly available. In the following part, we first summarize the detection and appearance feature, and then introduce our tracker named Person of Interest (POI), which has both online and offline version.
Tasks	Multiple Object Tracking, Object Tracking
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06136v1
PDF	http://arxiv.org/pdf/1610.06136v1.pdf
PWC	https://paperswithcode.com/paper/poi-multiple-object-tracking-with-high
Repo
Framework

Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images


Title	Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images
Authors	Hao Chen, Yefeng Zheng, Jin-Hyeong Park, Pheng-Ann Heng, S. Kevin Zhou
Abstract	Accurate detection and segmentation of anatomical structures from ultrasound images are crucial for clinical diagnosis and biometric measurements. Although ultrasound imaging has been widely used with superiorities such as low cost and portability, the fuzzy border definition and existence of abounding artifacts pose great challenges for automatically detecting and segmenting the complex anatomical structures. In this paper, we propose a multi-domain regularized deep learning method to address this challenging problem. By leveraging the transfer learning from cross domains, the feature representations are effectively enhanced. The results are further improved by the iterative refinement. Moreover, our method is quite efficient by taking advantage of a fully convolutional network, which is formulated as an end-to-end learning framework of detection and segmentation. Extensive experimental results on a large-scale database corroborated that our method achieved a superior detection and segmentation accuracy, outperforming other methods by a significant margin and demonstrating competitive capability even compared to human performance.
Tasks	Transfer Learning
Published	2016-07-07
URL	http://arxiv.org/abs/1607.01855v1
PDF	http://arxiv.org/pdf/1607.01855v1.pdf
PWC	https://paperswithcode.com/paper/iterative-multi-domain-regularized-deep
Repo
Framework


Title	End-to-End Goal-Driven Web Navigation
Authors	Rodrigo Nogueira, Kyunghyun Cho
Abstract	We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments. In this challenging task, an agent navigates through a website, which is represented as a graph consisting of web pages as nodes and hyperlinks as directed edges, to find a web page in which a query appears. The agent is required to have sophisticated high-level reasoning based on natural languages and efficient sequential decision-making capability to succeed. We release a software tool, called WebNav, that automatically transforms a website into this goal-driven web navigation task, and as an example, we make WikiNav, a dataset constructed from the English Wikipedia. We extensively evaluate different variants of neural net based artificial agents on WikiNav and observe that the proposed goal-driven web navigation well reflects the advances in models, making it a suitable benchmark for evaluating future progress. Furthermore, we extend the WikiNav with question-answer pairs from Jeopardy! and test the proposed agent based on recurrent neural networks against strong inverted index based search engines. The artificial agents trained on WikiNav outperforms the engined based approaches, demonstrating the capability of the proposed goal-driven navigation as a good proxy for measuring the progress in real-world tasks such as focused crawling and question-answering.
Tasks	Decision Making, Question Answering
Published	2016-02-06
URL	http://arxiv.org/abs/1602.02261v2
PDF	http://arxiv.org/pdf/1602.02261v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-goal-driven-web-navigation
Repo
Framework

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (Short Version)


Title	Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (Short Version)
Authors	Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, Ni Lao
Abstract	Extending the success of deep neural networks to natural language understanding and symbolic reasoning requires complex operations and external memory. Recent neural program induction approaches have attempted to address this problem, but are typically limited to differentiable memory, and consequently cannot scale beyond small synthetic tasks. In this work, we propose the Manager-Programmer-Computer framework, which integrates neural networks with non-differentiable memory to support abstract, scalable and precise operations through a friendly neural computer interface. Specifically, we introduce a Neural Symbolic Machine, which contains a sequence-to-sequence neural “programmer”, and a non-differentiable “computer” that is a Lisp interpreter with code assist. To successfully apply REINFORCE for training, we augment it with approximate gold programs found by an iterative maximum likelihood training process. NSM is able to learn a semantic parser from weak supervision over a large knowledge base. It achieves new state-of-the-art performance on WebQuestionsSP, a challenging semantic parsing dataset, with weak supervision. Compared to previous approaches, NSM is end-to-end, therefore does not rely on feature engineering or domain specific knowledge.
Tasks	Feature Engineering, Semantic Parsing
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01197v1
PDF	http://arxiv.org/pdf/1612.01197v1.pdf
PWC	https://paperswithcode.com/paper/neural-symbolic-machines-learning-semantic
Repo
Framework

Estimacion de carga muscular mediante imagenes


Title	Estimacion de carga muscular mediante imagenes
Authors	Leandro Abraham, Facundo Bromberg, Raymundo Forradellas
Abstract	Un problema de gran interes en disciplinas como la ocupacional, ergonomica y deportiva, es la medicion de variables biomecanicas involucradas en el movimiento humano (como las fuerzas musculares internas y torque de articulaciones). Actualmente este problema se resuelve en un proceso de dos pasos. Primero capturando datos con dispositivos poco pr'acticos, intrusivos y costosos. Luego estos datos son usados como entrada en modelos complejos para obtener las variables biomecanicas como salida. El presente trabajo representa una alternativa automatizada, no intrusiva y economica al primer paso, proponiendo la captura de estos datos a traves de imagenes. En trabajos futuros la idea es automatizar todo el proceso de calculo de esas variables. En este trabajo elegimos un caso particular de medicion de variables biomecanicas: el problema de estimar el nivel discreto de carga muscular que estan ejerciendo los musculos de un brazo. Para estimar a partir de imagenes estaticas del brazo ejerciendo la fuerza de sostener la carga, el nivel de la misma, realizamos un proceso de clasificacion. Nuestro enfoque utiliza Support Vector Machines para clasificacion, combinada con una etapa de pre-procesamiento que extrae caracter{\i}sticas visuales utilizando variadas tecnicas (Bag of Keypoints, Local Binary Patterns, Histogramas de Color, Momentos de Contornos) En los mejores casos (Local Binary Patterns y Momentos de Contornos) obtenemos medidas de performance en la clasificacion (Precision, Recall, F-Measure y Accuracy) superiores al 90 %.
Tasks
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02783v2
PDF	http://arxiv.org/pdf/1605.02783v2.pdf
PWC	https://paperswithcode.com/paper/estimacion-de-carga-muscular-mediante
Repo
Framework

Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling


Title	Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling
Authors	Sebastian Ramos, Stefan Gehrig, Peter Pinggera, Uwe Franke, Carsten Rother
Abstract	The detection of small road hazards, such as lost cargo, is a vital capability for self-driving cars. We tackle this challenging and rarely addressed problem with a vision system that leverages appearance, contextual as well as geometric cues. To utilize the appearance and contextual cues, we propose a new deep learning-based obstacle detection framework. Here a variant of a fully convolutional network is used to predict a pixel-wise semantic labeling of (i) free-space, (ii) on-road unexpected obstacles, and (iii) background. The geometric cues are exploited using a state-of-the-art detection approach that predicts obstacles from stereo input images via model-based statistical hypothesis tests. We present a principled Bayesian framework to fuse the semantic and stereo-based detection results. The mid-level Stixel representation is used to describe obstacles in a flexible, compact and robust manner. We evaluate our new obstacle detection system on the Lost and Found dataset, which includes very challenging scenes with obstacles of only 5 cm height. Overall, we report a major improvement over the state-of-the-art, with relative performance gains of up to 50%. In particular, we achieve a detection rate of over 90% for distances of up to 50 m. Our system operates at 22 Hz on our self-driving platform.
Tasks	Self-Driving Cars
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06573v1
PDF	http://arxiv.org/pdf/1612.06573v1.pdf
PWC	https://paperswithcode.com/paper/detecting-unexpected-obstacles-for-self
Repo
Framework

Easy Monotonic Policy Iteration


Title	Easy Monotonic Policy Iteration
Authors	Joshua Achiam
Abstract	A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or $Q$-function may fail to improve performance—or worse, actually cause the policy performance to degrade. Prior work has addressed this for policy iteration by deriving tight policy improvement bounds; by optimizing the lower bound on policy improvement, a better policy is guaranteed. However, existing approaches suffer from bounds that are hard to optimize in practice because they include sup norm terms which cannot be efficiently estimated or differentiated. In this work, we derive a better policy improvement bound where the sup norm of the policy divergence has been replaced with an average divergence; this leads to an algorithm, Easy Monotonic Policy Iteration, that generates sequences of policies with guaranteed non-decreasing returns and is easy to implement in a sample-based framework.
Tasks
Published	2016-02-29
URL	http://arxiv.org/abs/1602.09118v1
PDF	http://arxiv.org/pdf/1602.09118v1.pdf
PWC	https://paperswithcode.com/paper/easy-monotonic-policy-iteration
Repo
Framework