Paper Group ANR 1030
Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning. More Robust Doubly Robust Off-policy Evaluation. DeepPos: Deep Supervised Autoencoder Network for CSI Based Indoor Localization. The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data. Finding Minimal Cost Herbrand …
Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning
Title | Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning |
Authors | M Ferguson, K. H. Law |
Abstract | We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally across a set of similar environments, each with dynamics drawn from a prior distribution. We propose that the agent is able to adjust its actions almost immediately, based on small set of observations. This robust and adaptive behavior is enabled by using a policy gradient algorithm with an Long Short Term Memory (LSTM) function approximation. Finally, we train an agent to navigate a two-dimensional environment with uncertain dynamics and noisy observations. We demonstrate that this agent has good zero-shot performance in a real physical environment. Our preliminary results indicate that the agent is able to infer the environmental dynamics after only a few timesteps, and adjust its actions accordingly. |
Tasks | Continuous Control, Transfer Learning |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04520v2 |
http://arxiv.org/pdf/1802.04520v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-robust-and-adaptive-real-world |
Repo | |
Framework | |
More Robust Doubly Robust Off-policy Evaluation
Title | More Robust Doubly Robust Off-policy Evaluation |
Authors | Mehrdad Farajtabar, Yinlam Chow, Mohammad Ghavamzadeh |
Abstract | We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, and not much on how to learn the model. In this paper, we propose alternative DR estimators, called more robust doubly robust (MRDR), that learn the model parameter by minimizing the variance of the DR estimator. We first present a formulation for learning the DR model in RL. We then derive formulas for the variance of the DR estimator in both contextual bandits and RL, such that their gradients w.r.t.~the model parameters can be estimated from the samples, and propose methods to efficiently minimize the variance. We prove that the MRDR estimators are strongly consistent and asymptotically optimal. Finally, we evaluate MRDR in bandits and RL benchmark problems, and compare its performance with the existing methods. |
Tasks | Multi-Armed Bandits |
Published | 2018-02-10 |
URL | http://arxiv.org/abs/1802.03493v2 |
http://arxiv.org/pdf/1802.03493v2.pdf | |
PWC | https://paperswithcode.com/paper/more-robust-doubly-robust-off-policy |
Repo | |
Framework | |
DeepPos: Deep Supervised Autoencoder Network for CSI Based Indoor Localization
Title | DeepPos: Deep Supervised Autoencoder Network for CSI Based Indoor Localization |
Authors | Peyman Yazdanian, Vahid Pourahmadi |
Abstract | The widespread mobile devices facilitated the emergence of many new applications and services. Among them are location-based services (LBS) that provide services based on user’s location. Several techniques have been presented to enable LBS even in indoor environments where Global Positioning System (GPS) has low localization accuracy. These methods use some environment measurements (like Channel State Information (CSI) or Received Signal Strength (RSS)) for user localization. In this paper, we will use CSI and a novel deep learning algorithm to design a robust and efficient system for indoor localization. More precisely, we use supervised autoencoder (SAE) to model the environment using the data collected during the training phase. Then, during the testing phase, we use the trained model and estimate the coordinates of the unknown point by checking different possible labels. Unlike the previous fingerprinting approaches, in this work, we do not store the {CSI/RSS} of fingerprints and instead we model the environment only with a single SAE. The performance of the proposed scheme is then evaluated in two indoor environments and compared with that of similar approaches. |
Tasks | |
Published | 2018-11-27 |
URL | http://arxiv.org/abs/1811.12182v1 |
http://arxiv.org/pdf/1811.12182v1.pdf | |
PWC | https://paperswithcode.com/paper/deeppos-deep-supervised-autoencoder-network |
Repo | |
Framework | |
The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data
Title | The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data |
Authors | Daisy Yi Ding, Chloé Simpson, Stephen Pfohl, Dave C. Kale, Kenneth Jung, Nigam H. Shah |
Abstract | Electronic phenotyping is the task of ascertaining whether an individual has a medical condition of interest by analyzing their medical record and is foundational in clinical informatics. Increasingly, electronic phenotyping is performed via supervised learning. We investigate the effectiveness of multitask learning for phenotyping using electronic health records (EHR) data. Multitask learning aims to improve model performance on a target task by jointly learning additional auxiliary tasks and has been used in disparate areas of machine learning. However, its utility when applied to EHR data has not been established, and prior work suggests that its benefits are inconsistent. We present experiments that elucidate when multitask learning with neural nets improves performance for phenotyping using EHR data relative to neural nets trained for a single phenotype and to well-tuned logistic regression baselines. We find that multitask neural nets consistently outperform single-task neural nets for rare phenotypes but underperform for relatively more common phenotypes. The effect size increases as more auxiliary tasks are added. Moreover, multitask learning reduces the sensitivity of neural nets to hyperparameter settings for rare phenotypes. Last, we quantify phenotype complexity and find that neural nets trained with or without multitask learning do not improve on simple baselines unless the phenotypes are sufficiently complex. |
Tasks | |
Published | 2018-08-09 |
URL | http://arxiv.org/abs/1808.03331v3 |
http://arxiv.org/pdf/1808.03331v3.pdf | |
PWC | https://paperswithcode.com/paper/the-effectiveness-of-multitask-learning-for |
Repo | |
Framework | |
Finding Minimal Cost Herbrand Models with Branch-Cut-and-Price
Title | Finding Minimal Cost Herbrand Models with Branch-Cut-and-Price |
Authors | James Cussens |
Abstract | Given (1) a set of clauses $T$ in some first-order language $\cal L$ and (2) a cost function $c : B_{{\cal L}} \rightarrow \mathbb{R}_{+}$, mapping each ground atom in the Herbrand base $B_{{\cal L}}$ to a non-negative real, then the problem of finding a minimal cost Herbrand model is to either find a Herbrand model $\cal I$ of $T$ which is guaranteed to minimise the sum of the costs of true ground atoms, or establish that there is no Herbrand model for $T$. A branch-cut-and-price integer programming (IP) approach to solving this problem is presented. Since the number of ground instantiations of clauses and the size of the Herbrand base are both infinite in general, we add the corresponding IP constraints and IP variables on the fly' via cutting’ and `pricing’ respectively. In the special case of a finite Herbrand base we show that adding all IP variables and constraints from the outset can be advantageous, showing that a challenging Markov logic network MAP problem can be solved in this way if encoded appropriately. | |
Tasks | |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04758v1 |
http://arxiv.org/pdf/1808.04758v1.pdf | |
PWC | https://paperswithcode.com/paper/finding-minimal-cost-herbrand-models-with |
Repo | |
Framework | |
A comparative study of texture attributes for characterizing subsurface structures in seismic volumes
Title | A comparative study of texture attributes for characterizing subsurface structures in seismic volumes |
Authors | Zhiling Long, Yazeed Alaudah, Muhammad Ali Qureshi, Yuting Hu, Zhen Wang, Motaz Alfarraj, Ghassan AlRegib, Asjad Amin, Mohamed Deriche, Suhail Al-Dharrab, Haibin Di |
Abstract | In this paper, we explore how to computationally characterize subsurface geological structures presented in seismic volumes using texture attributes. For this purpose, we conduct a comparative study of typical texture attributes presented in the image processing literature. We focus on spatial attributes in this study and examine them in a new application for seismic interpretation, i.e., seismic volume labeling. For this application, a data volume is automatically segmented into various structures, each assigned with its corresponding label. If the labels are assigned with reasonable accuracy, such volume labeling will help initiate an interpretation process in a more effective manner. Our investigation proves the feasibility of accomplishing this task using texture attributes. Through the study, we also identify advantages and disadvantages associated with each attribute. |
Tasks | Seismic Interpretation |
Published | 2018-12-19 |
URL | http://arxiv.org/abs/1812.08263v1 |
http://arxiv.org/pdf/1812.08263v1.pdf | |
PWC | https://paperswithcode.com/paper/a-comparative-study-of-texture-attributes-for |
Repo | |
Framework | |
Understanding Image Quality and Trust in Peer-to-Peer Marketplaces
Title | Understanding Image Quality and Trust in Peer-to-Peer Marketplaces |
Authors | Xiao Ma, Lina Mezghani, Kimberly Wilber, Hui Hong, Robinson Piramuthu, Mor Naaman, Serge Belongie |
Abstract | As any savvy online shopper knows, second-hand peer-to-peer marketplaces are filled with images of mixed quality. How does image quality impact marketplace outcomes, and can quality be automatically predicted? In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces. By gathering a dataset of common second-hand products (~75,000 images) and annotating a subset with human-labeled quality judgments, we were able to model and predict image quality with decent accuracy (~87%). We then conducted two studies focused on understanding the relationship between these image quality scores and two marketplace outcomes: sales and perceived trustworthiness. We show that image quality is associated with higher likelihood that an item will be sold, though other factors such as view count were better predictors of sales. Nonetheless, we show that high quality user-generated images selected by our models outperform stock imagery in eliciting perceptions of trust from users. Our findings can inform the design of future marketplaces and guide potential sellers to take better product images. |
Tasks | |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10648v1 |
http://arxiv.org/pdf/1811.10648v1.pdf | |
PWC | https://paperswithcode.com/paper/understanding-image-quality-and-trust-in-peer |
Repo | |
Framework | |
Emoji Sentiment Scores of Writers using Odds Ratio and Fisher Exact Test
Title | Emoji Sentiment Scores of Writers using Odds Ratio and Fisher Exact Test |
Authors | Jose Berengueres |
Abstract | The sentiment of a given emoji is traditionally calculated by averaging the ratings {-1, 0 or +1} given by various users to a given context where the emoji appears. However, using such formula complicates the statistical significance analysis particularly for low sample sizes. Here, we provide sentiment scores using odds and a sentiment mapping to a 4-icon scale. We show how odds ratio statistics leads to simpler sentiment analysis. Finally, we provide a list of sentiment scores with the often-missing exact p-values and CI for the most common emoji. |
Tasks | Sentiment Analysis |
Published | 2018-08-18 |
URL | http://arxiv.org/abs/1808.06110v2 |
http://arxiv.org/pdf/1808.06110v2.pdf | |
PWC | https://paperswithcode.com/paper/emoji-sentiment-scores-of-writers-using-odds |
Repo | |
Framework | |
Neural Probabilistic System for Text Recognition
Title | Neural Probabilistic System for Text Recognition |
Authors | Najoua Rahal, Maroua Tounsi, Adel M. Alimi |
Abstract | Unconstrained text recognition is a stimulating field in the branch of pattern recognition. This field is still an open search due to the unlimited vocabulary, multi styles, mixed-font and their great morphological variability. Recent trends show a potential improvement of recognition by adoption a novel representation of extracted features. In the present paper, we propose a novel feature extraction model by learning a Bag of Features Framework for text recognition based on Sparse Auto-Encoder. The Hidden Markov Models are then used for sequences modeling. For features learned quality evaluation, our proposed system was tested on two printed text datasets PKHATT text line images and APTI word images benchmark. Our method achieves promising recognition on both datasets. |
Tasks | Optical Character Recognition |
Published | 2018-12-10 |
URL | https://arxiv.org/abs/1812.03680v6 |
https://arxiv.org/pdf/1812.03680v6.pdf | |
PWC | https://paperswithcode.com/paper/auto-encoder-bofhmm-system-for-arabic-text |
Repo | |
Framework | |
Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
Title | Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice |
Authors | Amir Rasouli, John K. Tsotsos |
Abstract | Today, one of the major challenges that autonomous vehicles are facing is the ability to drive in urban environments. Such a task requires communication between autonomous vehicles and other road users in order to resolve various traffic ambiguities. The interaction between road users is a form of negotiation in which the parties involved have to share their attention regarding a common objective or a goal (e.g. crossing an intersection), and coordinate their actions in order to accomplish it. In this literature review we aim to address the interaction problem between pedestrians and drivers (or vehicles) from joint attention point of view. More specifically, we will discuss the theoretical background behind joint attention, its application to traffic interaction and practical approaches to implementing joint attention for autonomous vehicles. |
Tasks | Autonomous Vehicles |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02522v2 |
http://arxiv.org/pdf/1802.02522v2.pdf | |
PWC | https://paperswithcode.com/paper/joint-attention-in-driver-pedestrian |
Repo | |
Framework | |
Small Sample Learning in Big Data Era
Title | Small Sample Learning in Big Data Era |
Authors | Jun Shu, Zongben Xu, Deyu Meng |
Abstract | As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. In this paper, we aim to present a survey to comprehensively introduce the current techniques proposed on this topic. Specifically, current SSL techniques can be mainly divided into two categories. The first category of SSL approaches can be called “concept learning”, which emphasizes learning new concepts from only few related observations. The purpose is mainly to simulate human learning behaviors like recognition, generation, imagination, synthesis and analysis. The second category is called “experience learning”, which usually co-exists with the large sample learning manner of conventional machine learning. This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures. More extensive surveys on both categories of SSL techniques are introduced and some neuroscience evidences are provided to clarify the rationality of the entire SSL regime, and the relationship with human learning process. Some discussions on the main challenges and possible future research directions along this line are also presented. |
Tasks | |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04572v3 |
http://arxiv.org/pdf/1808.04572v3.pdf | |
PWC | https://paperswithcode.com/paper/small-sample-learning-in-big-data-era |
Repo | |
Framework | |
Understanding the Meaning of Understanding
Title | Understanding the Meaning of Understanding |
Authors | Daniele Funaro |
Abstract | Can we train a machine to detect if another machine has understood a concept? In principle, this is possible by conducting tests on the subject of that concept. However we want this procedure to be done by avoiding direct questions. In other words, we would like to isolate the absolute meaning of an abstract idea by putting it into a class of equivalence, hence without adopting straight definitions or showing how this idea “works” in practice. We discuss the metaphysical implications hidden in the above question, with the aim of providing a plausible reference framework. |
Tasks | |
Published | 2018-06-13 |
URL | http://arxiv.org/abs/1806.05234v2 |
http://arxiv.org/pdf/1806.05234v2.pdf | |
PWC | https://paperswithcode.com/paper/understanding-the-meaning-of-understanding |
Repo | |
Framework | |
PanoRoom: From the Sphere to the 3D Layout
Title | PanoRoom: From the Sphere to the 3D Layout |
Authors | Clara Fernandez-Labrador, Jose M. Facil, Alejandro Perez-Yus, Cedric Demonceaux, Jose J. Guerrero |
Abstract | We propose a novel FCN able to work with omnidirectional images that outputs accurate probability maps representing the main structure of indoor scenes, which is able to generalize on different data. Our approach handles occlusions and recovers complex shaped rooms more faithful to the actual shape of the real scenes. We outperform the state of the art not only in accuracy of the 3D models but also in speed. |
Tasks | |
Published | 2018-08-29 |
URL | http://arxiv.org/abs/1808.09879v1 |
http://arxiv.org/pdf/1808.09879v1.pdf | |
PWC | https://paperswithcode.com/paper/panoroom-from-the-sphere-to-the-3d-layout |
Repo | |
Framework | |
Compressively Sensed Image Recognition
Title | Compressively Sensed Image Recognition |
Authors | Aysen Degerli, Sinem Aslan, Mehmet Yamac, Bulent Sankur, Moncef Gabbouj |
Abstract | Compressive Sensing (CS) theory asserts that sparse signal reconstruction is possible from a small number of linear measurements. Although CS enables low-cost linear sampling, it requires non-linear and costly reconstruction. Recent literature works show that compressive image classification is possible in CS domain without reconstruction of the signal. In this work, we introduce a DCT base method that extracts binary discriminative features directly from CS measurements. These CS measurements can be obtained by using (i) a random or a pseudo-random measurement matrix, or (ii) a measurement matrix whose elements are learned from the training data to optimize the given classification task. We further introduce feature fusion by concatenating Bag of Words (BoW) representation of our binary features with one of the two state-of-the-art CNN-based feature vectors. We show that our fused feature outperforms the state-of-the-art in both cases. |
Tasks | Compressive Sensing, Image Classification |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06323v1 |
http://arxiv.org/pdf/1810.06323v1.pdf | |
PWC | https://paperswithcode.com/paper/compressively-sensed-image-recognition |
Repo | |
Framework | |
Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan?
Title | Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan? |
Authors | Bilwaj Gaonkar, Matthew Edwards, Alex Bui, Matthew Brown, Luke Macyszyn |
Abstract | Yes, it can. Data augmentation is perhaps the oldest preprocessing step in computer vision literature. Almost every computer vision model trained on imaging data uses some form of augmentation. In this paper, we use the inter-vertebral disk segmentation task alongside a deep residual U-Net as the learning model, to explore the effectiveness of augmentation. In the extreme, we observed that a model trained on patches extracted from just one scan, with each patch augmented 50 times; achieved a Dice score of 0.73 in a validation set of 40 cases. Qualitative evaluation indicated a clinically usable segmentation algorithm, which appropriately segments regions of interest, alongside limited false positive specks. When the initial patches are extracted from nine scans the average Dice coefficient jumps to 0.86 and most of the false positives disappear. While this still falls short of state-of-the-art deep learning based segmentation of discs reported in literature, qualitative examination reveals that it does yield segmentation, which can be amended by expert clinicians with minimal effort to generate additional data for training improved deep models. Extreme augmentation of training data, should thus be construed as a strategy for training deep learning based algorithms, when very little manually annotated data is available to work with. Models trained with extreme augmentation can then be used to accelerate the generation of manually labelled data. Hence, we show that extreme augmentation can be a valuable tool in addressing scaling up small imaging data sets to address medical image segmentation tasks. |
Tasks | Data Augmentation, Medical Image Segmentation, Semantic Segmentation |
Published | 2018-10-03 |
URL | https://arxiv.org/abs/1810.01621v3 |
https://arxiv.org/pdf/1810.01621v3.pdf | |
PWC | https://paperswithcode.com/paper/extreme-augmentation-can-deep-learning-based |
Repo | |
Framework | |