January 28, 2020

3063 words 15 mins read

Paper Group ANR 1029

Generalized Maximum Causal Entropy for Inverse Reinforcement Learning. Embryo staging with weakly-supervised region selection and dynamically-decoded predictions. Mapping Areas using Computer Vision Algorithms and Drones. An Optimization Framework for Task Sequencing in Curriculum Learning. Finite-Time Error Bounds For Linear Stochastic Approximati …

Generalized Maximum Causal Entropy for Inverse Reinforcement Learning


Title	Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
Authors	Tien Mai, Kennard Chan, Patrick Jaillet
Abstract	We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL). Motivated by a limitation of the classical maximum entropy model in capturing the structure of the network of states, we propose an IRL model based on a generalized version of the causal entropy maximization problem, which allows us to generate a class of maximum entropy IRL models. Our generalized model has an advantage of being able to recover, in addition to a reward function, another expert’s function that would (partially) capture the impact of the connecting structure of the states on experts’ decisions. Empirical evaluation on a real-world dataset and a grid-world dataset shows that our generalized model outperforms the classical ones, in terms of recovering reward functions and demonstrated trajectories.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06928v1
PDF	https://arxiv.org/pdf/1911.06928v1.pdf
PWC	https://paperswithcode.com/paper/generalized-maximum-causal-entropy-for
Repo
Framework

Embryo staging with weakly-supervised region selection and dynamically-decoded predictions


Title	Embryo staging with weakly-supervised region selection and dynamically-decoded predictions
Authors	Tingfung Lau, Nathan Ng, Julian Gingold, Nina Desai, Julian McAuley, Zachary C. Lipton
Abstract	To optimize clinical outcomes, fertility clinics must strategically select which embryos to transfer. Common selection heuristics are formulas expressed in terms of the durations required to reach various developmental milestones, quantities historically annotated manually by experienced embryologists based on time-lapse EmbryoScope videos. We propose a new method for automatic embryo staging that exploits several sources of structure in this time-lapse data. First, noting that in each image the embryo occupies a small subregion, we jointly train a region proposal network with the downstream classifier to isolate the embryo. Notably, because we lack ground-truth bounding boxes, our we weakly supervise the region proposal network optimizing its parameters via reinforcement learning to improve the downstream classifier’s loss. Moreover, noting that embryos reaching the blastocyst stage progress monotonically through earlier stages, we develop a dynamic-programming-based decoder that post-processes our predictions to select the most likely monotonic sequence of developmental stages. Our methods outperform vanilla residual networks and rival the best numbers in contemporary papers, as measured by both per-frame accuracy and transition prediction error, despite operating on smaller data than many.
Tasks
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04419v1
PDF	http://arxiv.org/pdf/1904.04419v1.pdf
PWC	https://paperswithcode.com/paper/embryo-staging-with-weakly-supervised-region
Repo
Framework

Mapping Areas using Computer Vision Algorithms and Drones


Title	Mapping Areas using Computer Vision Algorithms and Drones
Authors	Bashar Alhafni, Saulo Fernando Guedes, Lays Cavalcante Ribeiro, Juhyun Park, Jeongkyu Lee
Abstract	The goal of this paper is to implement a system, titled as Drone Map Creator (DMC) using Computer Vision techniques. DMC can process visual information from an HD camera in a drone and automatically create a map by stitching together visual information captured by a drone. The proposed approach employs the Speeded up robust features (SURF) method to detect the key points for each image frame; then the corresponding points between the frames are identified by maximizing the determinant of a Hessian matrix. Finally, two images are stitched together by using the identified points. Our results show that despite some limitations from the external environment, we could have successfully stitched images together along video sequences.
Tasks
Published	2019-01-01
URL	http://arxiv.org/abs/1901.00211v1
PDF	http://arxiv.org/pdf/1901.00211v1.pdf
PWC	https://paperswithcode.com/paper/mapping-areas-using-computer-vision
Repo
Framework

An Optimization Framework for Task Sequencing in Curriculum Learning


Title	An Optimization Framework for Task Sequencing in Curriculum Learning
Authors	Francesco Foglino, Christiano Coletto Christakou, Matteo Leonetti
Abstract	Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with the objective of reducing the time to reach a given performance level. We propose novel uses of curriculum learning, which arise from choosing different objective functions. Furthermore, we define a general optimization framework for task sequencing and evaluate the performance of popular metaheuristic search methods on several tasks. We show that curriculum learning can be successfully used to: improve the initial performance, take fewer suboptimal actions during exploration, and discover better policies.
Tasks
Published	2019-01-31
URL	https://arxiv.org/abs/1901.11478v3
PDF	https://arxiv.org/pdf/1901.11478v3.pdf
PWC	https://paperswithcode.com/paper/an-optimization-framework-for-task-sequencing
Repo
Framework

Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning


Title	Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning
Authors	R. Srikant, Lei Ying
Abstract	We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an associated ordinary differential equation (ODE). We obtain finite-time bounds on the mean-square error in the case of constant step-size algorithms by considering the drift of an appropriately chosen Lyapunov function. The Lyapunov function can be interpreted either in terms of Stein’s method to obtain bounds on steady-state performance or in terms of Lyapunov stability theory for linear ODEs. We also provide a comprehensive treatment of the moments of the square of the 2-norm of the approximation error. Our analysis yields the following results: (i) for a given step-size, we show that the lower-order moments can be made small as a function of the step-size and can be upper-bounded by the moments of a Gaussian random variable; (ii) we show that the higher-order moments beyond a threshold may be infinite in steady-state; and (iii) we characterize the number of samples needed for the finite-time bounds to be of the same order as the steady-state bounds. As a by-product of our analysis, we also solve the open problem of obtaining finite-time bounds for the performance of temporal difference learning algorithms with linear function approximation and a constant step-size, without requiring a projection step or an i.i.d. noise assumption.
Tasks
Published	2019-02-03
URL	http://arxiv.org/abs/1902.00923v3
PDF	http://arxiv.org/pdf/1902.00923v3.pdf
PWC	https://paperswithcode.com/paper/finite-time-error-bounds-for-linear
Repo
Framework

Region-based Convolution Neural Network Approach for Accurate Segmentation of Pelvic Radiograph


Title	Region-based Convolution Neural Network Approach for Accurate Segmentation of Pelvic Radiograph
Authors	Ata Jodeiri, Reza A. Zoroofi, Yuta Hiasa, Masaki Takao, Nobuhiko Sugano, Yoshinobu Sato, Yoshito Otake
Abstract	With the increasing usage of radiograph images as a most common medical imaging system for diagnosis, treatment planning, and clinical studies, it is increasingly becoming a vital factor to use machine learning-based systems to provide reliable information for surgical pre-planning. Segmentation of pelvic bone in radiograph images is a critical preprocessing step for some applications such as automatic pose estimation and disease detection. However, the encoder-decoder style network known as U-Net has demonstrated limited results due to the challenging complexity of the pelvic shapes, especially in severe patients. In this paper, we propose a novel multi-task segmentation method based on Mask R-CNN architecture. For training, the network weights were initialized by large non-medical dataset and fine-tuned with radiograph images. Furthermore, in the training process, augmented data was generated to improve network performance. Our experiments show that Mask R-CNN utilizing multi-task learning, transfer learning, and data augmentation techniques achieve 0.96 DICE coefficient, which significantly outperforms the U-Net. Notably, for a fair comparison, the same transfer learning and data augmentation techniques have been used for U-net training.
Tasks	Data Augmentation, Multi-Task Learning, Pose Estimation, Transfer Learning
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13231v2
PDF	https://arxiv.org/pdf/1910.13231v2.pdf
PWC	https://paperswithcode.com/paper/region-based-convolution-neural-network
Repo
Framework

Fisher and Kernel Fisher Discriminant Analysis: Tutorial


Title	Fisher and Kernel Fisher Discriminant Analysis: Tutorial
Authors	Benyamin Ghojogh, Fakhri Karray, Mark Crowley
Abstract	This is a detailed tutorial paper which explains the Fisher discriminant Analysis (FDA) and kernel FDA. We start with projection and reconstruction. Then, one- and multi-dimensional FDA subspaces are covered. Scatters in two- and then multi-classes are explained in FDA. Then, we discuss on the rank of the scatters and the dimensionality of the subspace. A real-life example is also provided for interpreting FDA. Then, possible singularity of the scatter is discussed to introduce robust FDA. PCA and FDA directions are also compared. We also prove that FDA and linear discriminant analysis are equivalent. Fisher forest is also introduced as an ensemble of fisher subspaces useful for handling data with different features and dimensionality. Afterwards, kernel FDA is explained for both one- and multi-dimensional subspaces with both two- and multi-classes. Finally, some simulations are performed on AT&T face dataset to illustrate FDA and compare it with PCA.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09436v1
PDF	https://arxiv.org/pdf/1906.09436v1.pdf
PWC	https://paperswithcode.com/paper/fisher-and-kernel-fisher-discriminant
Repo
Framework

Open Set Medical Diagnosis


Title	Open Set Medical Diagnosis
Authors	Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso, Namit Katariya, Manish Chablani, David Sontag, Xavier Amatriain
Abstract	Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they have been trained. However, it is practically infeasible to obtain sufficient training data for every human condition, and once deployed such models will invariably face previously unseen conditions. We frame machine-learned diagnosis as an open-set learning problem, and study how state-of-the-art approaches compare. Further, we extend our study to a setting where training data is distributed across several healthcare sites that do not allow data pooling, and experiment with different strategies of building open-set diagnostic ensembles. Across both settings, we observe consistent gains from explicitly modeling unseen conditions, but find the optimal training strategy to vary across settings.
Tasks	Medical Diagnosis, Open Set Learning
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02830v1
PDF	https://arxiv.org/pdf/1910.02830v1.pdf
PWC	https://paperswithcode.com/paper/open-set-medical-diagnosis
Repo
Framework

3D Contouring for Breast Tumor in Sonography


Title	3D Contouring for Breast Tumor in Sonography
Authors	Yu-Len Huang, PhD, Dar-Ren Chen, MD, Yu-Chih Lin
Abstract	Malignant and benign breast tumors present differently in their shape and size on sonography. Morphological information provided by tumor contours are important in clinical diagnosis. However, ultrasound images contain noises and tissue texture; clinical diagnosis thus highly depends on the experience of physicians. The manual way to sketch three-dimensional (3D) contours of breast tumor is a time-consuming and complicate task. If automatic contouring could provide a precise breast tumor contour that might assist physicians in making an accurate diagnosis. This study presents an efficient method for automatically contouring breast tumors in 3D sonography. The proposed method utilizes an efficient segmentation procedure, i.e. level-set method (LSM), to automatic detect contours of breast tumors. This study evaluates 20 cases comprising ten benign and ten malignant tumors. The results of computer simulation reveal that the proposed 3D segmentation method provides robust contouring for breast tumor on ultrasound images. This approach consistently obtains contours similar to those obtained by manual contouring of the breast tumor and can save much of the time required to sketch precise contours.
Tasks
Published	2019-01-27
URL	http://arxiv.org/abs/1901.09407v1
PDF	http://arxiv.org/pdf/1901.09407v1.pdf
PWC	https://paperswithcode.com/paper/3d-contouring-for-breast-tumor-in-sonography
Repo
Framework

Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning


Title	Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning
Authors	Chu Qin, Ying Tan, Shang Ying Chen, Xian Zeng, Xingxing Qi, Tian Jin, Huan Shi, Yiwei Wan, Yu Chen, Jingfeng Li, Weidong He, Yali Wang, Peng Zhang, Feng Zhu, Hongping Zhao, Yuyang Jiang, Yuzong Chen
Abstract	Unsupervised clustering has broad applications in data stratification, pattern investigation and new discovery beyond existing knowledge. In particular, clustering of bioactive molecules facilitates chemical space mapping, structure-activity studies, and drug discovery. These tasks, conventionally conducted by similarity-based methods, are complicated by data complexity and diversity. We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1.39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space. These band-clusters, displayed by a space-navigation simulation software, band molecules of selected bioactivity classes into individual band-clusters possessing unique sets of common sub-structural features beyond structural similarity. These sub-structural features form the frameworks of the literature-reported pharmacophores and privileged fragments. Within each band-cluster, molecules are further banded into selected sub-regions with respect to their bioactivity target, sub-structural features and molecular scaffolds. Our method is potentially applicable for big data clustering tasks of different fields.
Tasks	Drug Discovery
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03429v1
PDF	http://arxiv.org/pdf/1902.03429v1.pdf
PWC	https://paperswithcode.com/paper/clustering-bioactive-molecules-in-3d-chemical
Repo
Framework

Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning


Title	Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
Authors	Yao Zhang, Alpha A. Lee
Abstract	Predicting bioactivity and physical properties of small molecules is a central challenge in drug discovery. Deep learning is becoming the method of choice but studies to date focus on mean accuracy as the main metric. However, to replace costly and mission-critical experiments by models, a high mean accuracy is not enough: Outliers can derail a discovery campaign, thus models need reliably predict when it will fail, even when the training data is biased; experiments are expensive, thus models need to be data-efficient and suggest informative training sets using active learning. We show that uncertainty quantification and active learning can be achieved by Bayesian semi-supervised graph convolutional neural networks. The Bayesian approach estimates uncertainty in a statistically principled way through sampling from the posterior distribution. Semi-supervised learning disentangles representation learning and regression, keeping uncertainty estimates accurate in the low data limit and allowing the model to start active learning from a small initial pool of training data. Our study highlights the promise of Bayesian deep learning for chemistry.
Tasks	Active Learning, Drug Discovery, Representation Learning
Published	2019-02-03
URL	https://arxiv.org/abs/1902.00925v2
PDF	https://arxiv.org/pdf/1902.00925v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-semi-supervised-learning-for
Repo
Framework

Generating Sentences from Disentangled Syntactic and Semantic Spaces


Title	Generating Sentences from Disentangled Syntactic and Semantic Spaces
Authors	Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xinyu Dai, Jiajun Chen
Abstract	Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces. Our proposed method explicitly models syntactic information in the VAE’s latent space by using the linearized tree sequence, leading to better performance of language generation. Additionally, the advantage of sampling in the disentangled syntactic and semantic latent spaces enables us to perform novel applications, such as the unsupervised paraphrase generation and syntax-transfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.
Tasks	Paraphrase Generation, Text Generation
Published	2019-07-06
URL	https://arxiv.org/abs/1907.05789v1
PDF	https://arxiv.org/pdf/1907.05789v1.pdf
PWC	https://paperswithcode.com/paper/generating-sentences-from-disentangled
Repo
Framework

Assessing the Efficacy of Clinical Sentiment Analysis and Topic Extraction in Psychiatric Readmission Risk Prediction


Title	Assessing the Efficacy of Clinical Sentiment Analysis and Topic Extraction in Psychiatric Readmission Risk Prediction
Authors	Elena Alvarez-Mellado, Eben Holderness, Nicholas Miller, Fyonn Dhang, Philip Cawkwell, Kirsten Bolton, James Pustejovsky, Mei-Hua Hall
Abstract	Predicting which patients are more likely to be readmitted to a hospital within 30 days after discharge is a valuable piece of information in clinical decision-making. Building a successful readmission risk classifier based on the content of Electronic Health Records (EHRs) has proved, however, to be a challenging task. Previously explored features include mainly structured information, such as sociodemographic data, comorbidity codes and physiological variables. In this paper we assess incorporating additional clinically interpretable NLP-based features such as topic extraction and clinical sentiment analysis to predict early readmission risk in psychiatry patients.
Tasks	Decision Making, Sentiment Analysis
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04006v1
PDF	https://arxiv.org/pdf/1910.04006v1.pdf
PWC	https://paperswithcode.com/paper/assessing-the-efficacy-of-clinical-sentiment
Repo
Framework

Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution


Title	Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution
Authors	Manuel Herzog, Klaus Dietmayer
Abstract	In this paper, we describe a strategy for training neural networks for object detection in range images obtained from one type of LiDAR sensor using labeled data from a different type of LiDAR sensor. Additionally, an efficient model for object detection in range images for use in self-driving cars is presented. Currently, the highest performing algorithms for object detection from LiDAR measurements are based on neural networks. Training these networks using supervised learning requires large annotated datasets. Therefore, most research using neural networks for object detection from LiDAR point clouds is conducted on a very small number of publicly available datasets. Consequently, only a small number of sensor types are used. We use an existing annotated dataset to train a neural network that can be used with a LiDAR sensor that has a lower resolution than the one used for recording the annotated dataset. This is done by simulating data from the lower resolution LiDAR sensor based on the higher resolution dataset. Furthermore, improvements to models that use LiDAR range images for object detection are presented. The results are validated using both simulated sensor data and data from an actual lower resolution sensor mounted to a research vehicle. It is shown that the model can detect objects from 360{\deg} range images in real time.
Tasks	Object Detection, Self-Driving Cars
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03066v3
PDF	https://arxiv.org/pdf/1905.03066v3.pdf
PWC	https://paperswithcode.com/paper/training-a-fast-object-detector-for-lidar
Repo
Framework

Asymptotic Consistency of $α-$Rényi-Approximate Posteriors


Title	Asymptotic Consistency of $α-$Rényi-Approximate Posteriors
Authors	Prateek Jaiswal, Vinayak A. Rao, Harsha Honnappa
Abstract	We study the asymptotic consistency properties of $\alpha$-R'enyi approximate posteriors, a class of variational Bayesian methods that approximate an intractable Bayesian posterior with a member of a tractable family of distributions, the member chosen to minimize the $\alpha$-R'enyi divergence from the true posterior. Unique to our work is that we consider settings with $\alpha > 1$, resulting in approximations that upperbound the log-likelihood, and consequently have wider spread than traditional variational approaches that minimize the Kullback-Liebler (KL) divergence from the posterior. Our primary result identifies sufficient conditions under which consistency holds, centering around the existence of a `good’ sequence of distributions in the approximating family that possesses, among other properties, the right rate of convergence to a limit distribution. We also further characterize the good sequence by demonstrating that a sequence of distributions that converges too quickly cannot be a good sequence. We also illustrate the existence of good sequence with a number of examples. As an auxiliary result of our main theorems, we also recover the consistency of the idealized expectation propagation (EP) approximate posterior that minimizes the KL divergence from the posterior. Our results complement a growing body of work focused on the frequentist properties of variational Bayesian methods. \|
Tasks
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01902v2
PDF	http://arxiv.org/pdf/1902.01902v2.pdf
PWC	https://paperswithcode.com/paper/asymptotic-consistency-of-renyi-approximate
Repo
Framework