Paper Group ANR 1520
von Neumann-Morgenstern and Savage Theorems for Causal Decision Making. Deep Learning Based Automatic Video Annotation Tool for Self-Driving Car. Robo-PlaNet: Learning to Poke in a Day. Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation. Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerat …
von Neumann-Morgenstern and Savage Theorems for Causal Decision Making
| Title | von Neumann-Morgenstern and Savage Theorems for Causal Decision Making |
| Authors | Mauricio Gonzalez-Soto, Luis E. Sucar, Hugo J. Escalante |
| Abstract | Decision making under uncertain conditions has been well studied when uncertainty can only be considered at the associative level of information. The classical Theorems of von Neumann-Morgenstern and Savage provide a formal criterion for rationally making choices using associative information. We provide here a previous result from Pearl and show that it can be considered as a causal version of the von Neumann-Morgenstern Theorem; furthermore, we consider the case when the true causal mechanism that controls the environment is unknown to the decision maker and propose a causal version of the Savage Theorem. As applications, we argue how previous optimal action learning methods for causal environments fit within the Causal Savage Theorem we present thus showing the utility of our result in the justification and design of learning algorithms; furthermore, we define a Causal Nash Equilibria for a strategic game in a causal environment in terms of the preferences induced by our Causal Decision Making Theorem. |
| Tasks | Decision Making |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11752v2 |
| https://arxiv.org/pdf/1907.11752v2.pdf | |
| PWC | https://paperswithcode.com/paper/von-neumann-morgenstern-and-savage-theorems |
| Repo | |
| Framework | |
Deep Learning Based Automatic Video Annotation Tool for Self-Driving Car
| Title | Deep Learning Based Automatic Video Annotation Tool for Self-Driving Car |
| Authors | N. S. Manikandan, K. Ganesan |
| Abstract | In a self-driving car, objection detection, object classification, lane detection and object tracking are considered to be the crucial modules. In recent times, using the real time video one wants to narrate the scene captured by the camera fitted in our vehicle. To effectively implement this task, deep learning techniques and automatic video annotation tools are widely used. In the present paper, we compare the various techniques that are available for each module and choose the best algorithm among them by using appropriate metrics. For object detection, YOLO and Retinanet-50 are considered and the best one is chosen based on mean Average Precision (mAP). For object classification, we consider VGG-19 and Resnet-50 and select the best algorithm based on low error rate and good accuracy. For lane detection, Udacity’s ‘Finding Lane Line’ and deep learning based LaneNet algorithms are compared and the best one that can accurately identify the given lane is chosen for implementation. As far as object tracking is concerned, we compare Udacity’s ‘Object Detection and Tracking’ algorithm and deep learning based Deep Sort algorithm. Based on the accuracy of tracking the same object in many frames and predicting the movement of objects, the best algorithm is chosen. Our automatic video annotation tool is found to be 83% accurate when compared with a human annotator. We considered a video with 530 frames each of resolution 1035 x 1800 pixels. At an average each frame had about 15 objects. Our annotation tool consumed 43 minutes in a CPU based system and 2.58 minutes in a mid-level GPU based system to process all four modules. But the same video took nearly 3060 minutes for one human annotator to narrate the scene in the given video. Thus we claim that our proposed automatic video annotation tool is reasonably fast (about 1200 times in a GPU system) and accurate. |
| Tasks | Lane Detection, Object Classification, Object Detection, Object Tracking |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.12618v1 |
| http://arxiv.org/pdf/1904.12618v1.pdf | |
| PWC | https://paperswithcode.com/paper/190412618 |
| Repo | |
| Framework | |
Robo-PlaNet: Learning to Poke in a Day
| Title | Robo-PlaNet: Learning to Poke in a Day |
| Authors | Maxime Chevalier-Boisvert, Guillaume Alain, Florian Golemo, Derek Nowrouzezahrai |
| Abstract | Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations. This architecture is useful for learning tasks in which either the agent does not have access to meaningful states (like position/velocity of robotic joints) or where the observed states significantly deviate from the physical state of the agent (which is commonly the case in low-cost robots in the form of backlash or noisy joint readings). PlaNet, by design, interleaves phases of training the dynamics model with phases of collecting more data on the target environment, leading to long training times. In this work, we introduce Robo-PlaNet, an asynchronous version of PlaNet. This algorithm consistently reaches higher performance in the same amount of time, which we demonstrate in both a simulated and a real robotic experiment. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03594v2 |
| https://arxiv.org/pdf/1911.03594v2.pdf | |
| PWC | https://paperswithcode.com/paper/robo-planet-learning-to-poke-in-a-day |
| Repo | |
| Framework | |
Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation
| Title | Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation |
| Authors | Cheng Li, Hui Sun, Zaiyi Liu, Meiyun Wang, Hairong Zheng, Shanshan Wang |
| Abstract | Multi-modal magnetic resonance imaging (MRI) is essential in clinics for comprehensive diagnosis and surgical planning. Nevertheless, the segmentation of multi-modal MR images tends to be time-consuming and challenging. Convolutional neural network (CNN)-based multi-modal MR image analysis commonly proceeds with multiple down-sampling streams fused at one or several layers. Although inspiring performance has been achieved, the feature fusion is usually conducted through simple summation or concatenation without optimization. In this work, we propose a supervised image fusion method to selectively fuse the useful information from different modalities and suppress the respective noise signals. Specifically, an attention block is introduced as guidance for the information selection. From the different modalities, one modality that contributes most to the results is selected as the master modality, which supervises the information selection of the other assistant modalities. The effectiveness of the proposed method is confirmed through breast mass segmentation in MR images of two modalities and better segmentation results are achieved compared to the state-of-the-art methods. |
| Tasks | Semantic Segmentation |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.01997v1 |
| https://arxiv.org/pdf/1908.01997v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-cross-modal-deep-representations-for-2 |
| Repo | |
| Framework | |
Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
| Title | Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators |
| Authors | Weiwen Jiang, Qiuwen Lou, Zheyu Yan, Lei Yang, Jingtong Hu, Xiaobo Sharon Hu, Yiyu Shi |
| Abstract | Co-exploration of neural architectures and hardware design is promising to simultaneously optimize network accuracy and hardware efficiency. However, state-of-the-art neural architecture search algorithms for the co-exploration are dedicated for the conventional von-neumann computing architecture, whose performance is heavily limited by the well-known memory wall. In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency. Such a novel combination makes opportunities to boost performance, but also brings a bunch of challenges. The design space spans across multiple layers from device type, circuit topology to neural architecture. In addition, the performance may degrade in the presence of device variation. To address these challenges, we propose a cross-layer exploration framework, namely NACIM, which jointly explores device, circuit and architecture design space and takes device variation into consideration to find the most robust neural architectures. Experimental results demonstrate that NACIM can find the robust neural network with 0.45% accuracy loss in the presence of device variation, compared with a 76.44% loss from the state-of-the-art NAS without consideration of variation; in addition, NACIM achieves an energy efficiency up to 16.3 TOPs/W, 3.17X higher than the state-of-the-art NAS. |
| Tasks | Neural Architecture Search |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.00139v2 |
| https://arxiv.org/pdf/1911.00139v2.pdf | |
| PWC | https://paperswithcode.com/paper/device-circuit-architecture-co-exploration |
| Repo | |
| Framework | |
An Effective Algorithm for Learning Single Occurrence Regular Expressions with Interleaving
| Title | An Effective Algorithm for Learning Single Occurrence Regular Expressions with Interleaving |
| Authors | Yeting Li, Haiming Chen, Xiaolan Zhang, Lingqi Zhang |
| Abstract | The advantages offered by the presence of a schema are numerous. However, many XML documents in practice are not accompanied by a (valid) schema, making schema inference an attractive research problem. The fundamental task in XML schema learning is inferring restricted subclasses of regular expressions. Most previous work either lacks support for interleaving or only has limited support for interleaving. In this paper, we first propose a new subclass Single Occurrence Regular Expressions with Interleaving (SOIRE), which has unrestricted support for interleaving. Then, based on single occurrence automaton and maximum independent set, we propose an algorithm iSOIRE to infer SOIREs. Finally, we further conduct a series of experiments on real datasets to evaluate the effectiveness of our work, comparing with both ongoing learning algorithms in academia and industrial tools in real-world. The results reveal the practicability of SOIRE and the effectiveness of iSOIRE, showing the high preciseness and conciseness of our work. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02074v1 |
| https://arxiv.org/pdf/1906.02074v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-effective-algorithm-for-learning-single |
| Repo | |
| Framework | |
Out-of-domain Detection for Natural Language Understanding in Dialog Systems
| Title | Out-of-domain Detection for Natural Language Understanding in Dialog Systems |
| Authors | Yinhe Zheng, Guanyi Chen, Minlie Huang |
| Abstract | Natural Language Understanding (NLU) is a vital component of dialogue systems, and its ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the acceptance of the OOD input that is unsupported by the current system may lead to catastrophic failure. However, most existing OOD detection methods rely heavily on manually labeled OOD samples and cannot take full advantage of unlabeled data. This limits the feasibility of these models in practical applications. In this paper, we propose a novel model to generate high-quality pseudo OOD samples that are akin to IN-Domain (IND) input utterances, and thereby improves the performance of OOD detection. To this end, an autoencoder is trained to map an input utterance into a latent code. and the codes of IND and OOD samples are trained to be indistinguishable by utilizing a generative adversarial network. To provide more supervision signals, an auxiliary classifier is introduced to regularize the generated OOD samples to have indistinguishable intent labels. Experiments show that these pseudo OOD samples generated by our model can be used to effectively improve OOD detection in NLU. Besides, we also demonstrate that the effectiveness of these pseudo OOD data can be further improved by efficiently utilizing unlabeled data. |
| Tasks | Text Generation |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03862v3 |
| https://arxiv.org/pdf/1909.03862v3.pdf | |
| PWC | https://paperswithcode.com/paper/out-of-domain-detection-for-natural-language |
| Repo | |
| Framework | |
Representation Internal-Manipulation (RIM): A Neuro-Inspired Computational Theory of Consciousness
| Title | Representation Internal-Manipulation (RIM): A Neuro-Inspired Computational Theory of Consciousness |
| Authors | Gianluca Baldassarre, Giovanni Granato |
| Abstract | Many theories, based on neuroscientific and psychological empirical evidence and on computational concepts, have been elaborated to explain the emergence of consciousness in the central nervous system. These theories propose key fundamental mechanisms to explain consciousness, but they only partially connect such mechanisms to the possible functional and adaptive role of consciousness. Recently, some cognitive and neuroscientific models try to solve this gap by linking consciousness to various aspects of goal-directed behaviour, the pivotal cognitive process that allows mammals to flexibly act in challenging environments. Here we propose the Representation Internal-Manipulation (RIM) theory of consciousness, a theory that links the main elements of consciousness theories to components and functions of goal-directed behaviour, ascribing a central role for consciousness to the goal-directed manipulation of internal representations. This manipulation relies on four specific computational operations to perform the flexible internal adaptation of all key elements of goal-directed computation, from the representations of objects to those of goals, actions, and plans. Finally, we propose the concept of `manipulation agency’ relating the sense of agency to the internal manipulation of representations. This allows us to propose that the subjective experience of consciousness is associated to the human capacity to generate and control a simulated internal reality that is vividly perceived and felt through the same perceptual and emotional mechanisms used to tackle the external world. | |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13490v1 |
| https://arxiv.org/pdf/1912.13490v1.pdf | |
| PWC | https://paperswithcode.com/paper/representation-internal-manipulation-rim-a |
| Repo | |
| Framework | |
Using Prolog for Transforming XML-Documents
| Title | Using Prolog for Transforming XML-Documents |
| Authors | René Haberland |
| Abstract | Proponents of the programming language Prolog share the opinion Prolog is more appropriate for transforming XML-documents as other well-established techniques and languages like XSLT. In order to clarify this position this work proposes a tuProlog-styled interpreter for parsing XML-documents into Prolog-internal lists and vice versa for serialising lists into XML-documents. Based on this implementation a comparison between XSLT and Prolog follows. First, criteria are researched, such as considered language features of XSLT, usability and expressibility. These criteria are validated. Second, it is assessed when Prolog distinguishes between input and output parameters towards reversible transformation. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.10817v1 |
| https://arxiv.org/pdf/1912.10817v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-prolog-for-transforming-xml-documents |
| Repo | |
| Framework | |
Adaptive Stress Testing for Autonomous Vehicles
| Title | Adaptive Stress Testing for Autonomous Vehicles |
| Authors | Mark Koren, Saud Alsaif, Ritchie Lee, Mykel J. Kochenderfer |
| Abstract | This paper presents a method for testing the decision making systems of autonomous vehicles. Our approach involves perturbing stochastic elements in the vehicle’s environment until the vehicle is involved in a collision. Instead of applying direct Monte Carlo sampling to find collision scenarios, we formulate the problem as a Markov decision process and use reinforcement learning algorithms to find the most likely failure scenarios. This paper presents Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (DRL) solutions that can scale to large environments. We show that DRL can find more likely failure scenarios than MCTS with fewer calls to the simulator. A simulation scenario involving a vehicle approaching a crosswalk is used to validate the framework. Our proposed approach is very general and can be easily applied to other scenarios given the appropriate models of the vehicle and the environment. |
| Tasks | Autonomous Vehicles, Decision Making |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01909v1 |
| http://arxiv.org/pdf/1902.01909v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-stress-testing-for-autonomous |
| Repo | |
| Framework | |
Inference of modes for linear stochastic processes
| Title | Inference of modes for linear stochastic processes |
| Authors | Robert S. MacKay |
| Abstract | For dynamical systems that can be modelled as asymptotically stable linear systems forced by Gaussian noise, this paper develops methods to infer or estimate their modes from observations in real time. The modes can be real or complex. For a real mode, we wish to infer its damping rate and mode shape. For a complex mode, we wish to infer its frequency, damping rate and (complex) mode shape. Their amplitudes and correlations are encoded in a mode covariance matrix. The work is motivated and illustrated by the problem of detection of oscillations in power flow in AC electrical networks. Suggestions of other applications are given. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10247v2 |
| https://arxiv.org/pdf/1909.10247v2.pdf | |
| PWC | https://paperswithcode.com/paper/inference-of-modes-for-linear-stochastic |
| Repo | |
| Framework | |
A simple baseline for domain adaptation using rotation prediction
| Title | A simple baseline for domain adaptation using rotation prediction |
| Authors | Ajinkya Tejankar, Hamed Pirsiavash |
| Abstract | Recently, domain adaptation has become a hot research area with lots of applications. The goal is to adapt a model trained in one domain to another domain with scarce annotated data. We propose a simple yet effective method based on self-supervised learning that outperforms or is on par with most state-of-the-art algorithms, e.g. adversarial domain adaptation. Our method involves two phases: predicting random rotations (self-supervised) on the target domain along with correct labels for the source domain (supervised), and then using self-distillation on the target domain. Our simple method achieves state-of-the-art results on semi-supervised domain adaptation on DomainNet dataset. Further, we observe that the unlabeled target datasets of popular domain adaptation benchmarks do not contain any categories apart from testing categories. We believe this introduces a bias that does not exist in many real applications. We show that removing this bias from the unlabeled data results in a large drop in performance of state-of-the-art methods, while our simple method is relatively robust. |
| Tasks | Domain Adaptation |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11903v1 |
| https://arxiv.org/pdf/1912.11903v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-baseline-for-domain-adaptation-using |
| Repo | |
| Framework | |
An Online Learning Approach for Dengue Fever Classification
| Title | An Online Learning Approach for Dengue Fever Classification |
| Authors | Siddharth Srivastava, Sumit Soman, Astha Rai |
| Abstract | This paper introduces a novel approach for dengue fever classification based on online learning paradigms. The proposed approach is suitable for practical implementation as it enables learning using only a few training samples. With time, the proposed approach is capable of learning incrementally from the data collected without need for retraining the model or redeployment of the prediction engine. Additionally, we also provide a comprehensive evaluation of machine learning methods for prediction of dengue fever. The input to the proposed pipeline comprises of recorded patient symptoms and diagnostic investigations. Offline classifier models have been employed to obtain baseline scores to establish that the feature set is optimal for classification of dengue. The primary benefit of the online detection model presented in the paper is that it has been established to effectively identify patients with high likelihood of dengue disease, and experiments on scalability in terms of number of training and test samples validate the use of the proposed model. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08092v1 |
| http://arxiv.org/pdf/1904.08092v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-learning-approach-for-dengue-fever |
| Repo | |
| Framework | |
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis
| Title | Deep learning with noisy labels: exploring techniques and remedies in medical image analysis |
| Authors | Davood Karimi, Haoran Dou, Simon K. Warfield, Ali Gholipour |
| Abstract | Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high inter- and intra-observer variability, and erroneous predictions may influence decisions that directly impact human health. In this paper, we first review the state-of-the-art in handling label noise in deep learning. Then, we review studies that have dealt with label noise in deep learning for medical image analysis. Our review shows that recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image analysis community. To help achieve a better understanding of the extent of the problem and its potential remedies, we conducted experiments with three medical imaging datasets with different types of label noise, where we investigated several existing strategies and developed new methods to combat the negative effect of label noise. Based on the results of these experiments and our review of the literature, we have made recommendations on methods that can be used to alleviate the effects of different types of label noise on deep models trained for medical image analysis. We hope that this article helps the medical image analysis researchers and developers in choosing and devising new techniques that effectively handle label noise in deep learning. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02911v4 |
| https://arxiv.org/pdf/1912.02911v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-with-noisy-labels-exploring |
| Repo | |
| Framework | |
Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
| Title | Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion |
| Authors | Ryutaro Tanno, Ardavan Saeedi, Swami Sankaranarayanan, Daniel C. Alexander, Nathan Silberman |
| Abstract | The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the “truth” under the influence of their varying skill-levels and biases. Blindly treating these noisy labels as the ground truth limits the accuracy of learning algorithms in the presence of strong disagreement. This problem is critical for applications in domains such as medical imaging where both the annotation cost and inter-observer variability are high. In this work, we present a method for simultaneously learning the individual annotator model and the underlying true label distribution, using only noisy observations. Each annotator is modeled by a confusion matrix that is jointly estimated along with the classifier predictions. We propose to add a regularization term to the loss function that encourages convergence to the true annotator confusion matrix. We provide a theoretical argument as to how the regularization is essential to our approach both for the case of single annotator and multiple annotators. Despite the simplicity of the idea, experiments on image classification tasks with both simulated and real labels show that our method either outperforms or performs on par with the state-of-the-art methods and is capable of estimating the skills of annotators even with a single label available per image. |
| Tasks | Image Classification |
| Published | 2019-02-10 |
| URL | https://arxiv.org/abs/1902.03680v3 |
| https://arxiv.org/pdf/1902.03680v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-noisy-labels-by-regularized |
| Repo | |
| Framework | |
