Paper Group ANR 1011
A Virtual Testbed for Critical Incident Investigation with Autonomous Remote Aerial Vehicle Surveying, Artificial Intelligence, and Decision Support. Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition. Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification. Visual Psychophysics for M …
A Virtual Testbed for Critical Incident Investigation with Autonomous Remote Aerial Vehicle Surveying, Artificial Intelligence, and Decision Support
| Title | A Virtual Testbed for Critical Incident Investigation with Autonomous Remote Aerial Vehicle Surveying, Artificial Intelligence, and Decision Support |
| Authors | David L. Smyth, Sai Abinesh, Nazli B. Karimi, Brett Drury, Ihsan Ullah, Frank G. Glavin, Michael G. Madden |
| Abstract | Autonomous robotics and artificial intelligence techniques can be used to support human personnel in the event of critical incidents. These incidents can pose great danger to human life. Some examples of such assistance include: multi-robot surveying of the scene; collection of sensor data and scene imagery, real-time risk assessment and analysis; object identification and anomaly detection; and retrieval of relevant supporting documentation such as standard operating procedures (SOPs). These incidents, although often rare, can involve chemical, biological, radiological/nuclear or explosive (CBRNE) substances and can be of high consequence. Real-world training and deployment of these systems can be costly and sometimes not feasible. For this reason, we have developed a realistic 3D model of a CBRNE scenario to act as a testbed for an initial set of assisting AI tools that we have developed. |
| Tasks | Anomaly Detection |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.06244v2 |
| http://arxiv.org/pdf/1809.06244v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-virtual-testbed-for-critical-incident |
| Repo | |
| Framework | |
Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition
| Title | Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition |
| Authors | Krishan Rajaratnam, Jugal Kalita |
| Abstract | Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploitable flaws. Initially applied to computer vision systems, the generation of adversarial examples is a process in which seemingly imperceptible perturbations are made to an image, with the purpose of inducing a deep learning based classifier to misclassify the image. Due to recent trends in speech processing, this has become a noticeable issue in speech recognition models. In late 2017, an attack was shown to be quite effective against the Speech Commands classification model. Limited-vocabulary speech classifiers, such as the Speech Commands model, are used quite frequently in a variety of applications, particularly in managing automated attendants in telephony contexts. As such, adversarial examples produced by this attack could have real-world consequences. While previous work in defending against these adversarial examples has investigated using audio preprocessing to reduce or distort adversarial noise, this work explores the idea of flooding particular frequency bands of an audio signal with random noise in order to detect adversarial examples. This technique of flooding, which does not require retraining or modifying the model, is inspired by work done in computer vision and builds on the idea that speech classifiers are relatively robust to natural noise. A combined defense incorporating 5 different frequency bands for flooding the signal with noise outperformed other existing defenses in the audio space, detecting adversarial examples with 91.8% precision and 93.5% recall. |
| Tasks | Speech Recognition |
| Published | 2018-12-25 |
| URL | http://arxiv.org/abs/1812.10061v1 |
| http://arxiv.org/pdf/1812.10061v1.pdf | |
| PWC | https://paperswithcode.com/paper/noise-flooding-for-detecting-audio |
| Repo | |
| Framework | |
Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification
| Title | Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification |
| Authors | Fenxiao Chen, Bin Wang, C. -C. Jay Kuo |
| Abstract | A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs. The DTG method can generate a richer and more accurate representation for nodes (or vertices) in graphs. It adds flexibility in exploring the vertex neighborhood information to better reflect the second order proximity and homophily equivalence in a graph. Then, a Deep-Tree Recursive Neural Network (DTRNN) method is presented and used to classify vertices that contains text data in graphs. To demonstrate the effectiveness of the DTRNN method, we apply it to three real-world graph datasets and show that the DTRNN method outperforms several state-of-the-art benchmarking methods. |
| Tasks | Text Classification |
| Published | 2018-09-04 |
| URL | http://arxiv.org/abs/1809.01219v1 |
| http://arxiv.org/pdf/1809.01219v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-based-deep-tree-recursive-neural |
| Repo | |
| Framework | |
Visual Psychophysics for Making Face Recognition Algorithms More Explainable
| Title | Visual Psychophysics for Making Face Recognition Algorithms More Explainable |
| Authors | Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer |
| Abstract | Scientific fields that are interested in faces have developed their own sets of concepts and procedures for understanding how a target model system (be it a person or algorithm) perceives a face under varying conditions. In computer vision, this has largely been in the form of dataset evaluation for recognition tasks where summary statistics are used to measure progress. While aggregate performance has continued to improve, understanding individual causes of failure has been difficult, as it is not always clear why a particular face fails to be recognized, or why an impostor is recognized by an algorithm. Importantly, other fields studying vision have addressed this via the use of visual psychophysics: the controlled manipulation of stimuli and careful study of the responses they evoke in a model system. In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable. A comprehensive set of procedures is developed for assessing face recognition algorithm behavior, which is then deployed over state-of-the-art convolutional neural networks and more basic, yet still widely used, shallow and handcrafted feature-based approaches. |
| Tasks | Face Recognition |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.07140v2 |
| http://arxiv.org/pdf/1803.07140v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-psychophysics-for-making-face |
| Repo | |
| Framework | |
A General Framework for Fair Regression
| Title | A General Framework for Fair Regression |
| Authors | Jack Fitzsimons, AbdulRahman Al Ali, Michael Osborne, Stephen Roberts |
| Abstract | Fairness, through its many forms and definitions, has become an important issue facing the machine learning community. In this work, we consider how to incorporate group fairness constraints in kernel regression methods, applicable to Gaussian processes, support vector machines, neural network regression and decision tree regression. Further, we focus on examining the effect of incorporating these constraints in decision tree regression, with direct applications to random forests and boosted trees amongst other widespread popular inference techniques. We show that the order of complexity of memory and computation is preserved for such models and tightly bound the expected perturbations to the model in terms of the number of leaves of the trees. Importantly, the approach works on trained models and hence can be easily applied to models in current use and group labels are only required on training data. |
| Tasks | Gaussian Processes |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.05041v2 |
| http://arxiv.org/pdf/1810.05041v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-framework-for-fair-regression |
| Repo | |
| Framework | |
Neural Networks with Activation Networks
| Title | Neural Networks with Activation Networks |
| Authors | Jinhyeok Jang, Jaehong Kim, Jaeyeon Lee, Seungjoon Yang |
| Abstract | This work presents an adaptive activation method for neural networks that exploits the interdependency of features. Each pixel, node, and layer is assigned with a polynomial activation function, whose coefficients are provided by an auxiliary activation network. The activation of a feature depends on the features of neighboring pixels in a convolutional layer and other nodes in a dense layer. The dependency is learned from data by the activation networks. In our experiments, networks with activation networks provide significant performance improvement compared to the baseline networks on which they are built. The proposed method can be used to improve the network performance as an alternative to increasing the number of nodes and layers. |
| Tasks | |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.08618v1 |
| http://arxiv.org/pdf/1811.08618v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-with-activation-networks |
| Repo | |
| Framework | |
Advancing PICO Element Detection in Biomedical Text via Deep Neural Networks
| Title | Advancing PICO Element Detection in Biomedical Text via Deep Neural Networks |
| Authors | Di Jin, Peter Szolovits |
| Abstract | In evidence-based medicine (EBM), defining a clinical question in terms of the specific patient problem aids the physicians to efficiently identify appropriate resources and search for the best available evidence for medical treatment. In order to formulate a well-defined, focused clinical question, a framework called PICO is widely used, which identifies the sentences in a given medical text that belong to the four components typically reported in clinical trials: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O). In this work, we propose a novel deep learning model for recognizing PICO elements in biomedical abstracts. Based on the previous state-of-the-art bidirectional long-short term memory (biLSTM) plus conditional random field (CRF) architecture, we add another layer of biLSTM upon the sentence representation vectors so that the contextual information from surrounding sentences can be gathered to help infer the interpretation of the current one. In addition, we propose two methods to further generalize and improve the model: adversarial training and unsupervised pre-training over large corpora. We tested our proposed approach over two benchmark datasets. One is the PubMed-PICO dataset, where our best results outperform the previous best by 5.5%, 7.9%, and 5.8% for P, I, and O elements in terms of F1 score, respectively. And for the other dataset named NICTA-PIBOSO, the improvements for P/I/O elements are 2.4%, 13.6%, and 1.0% in F1 score, respectively. Overall, our proposed deep learning model can obtain unprecedented PICO element detection accuracy while avoiding the need for any manual feature selection. |
| Tasks | Feature Selection |
| Published | 2018-10-30 |
| URL | https://arxiv.org/abs/1810.12780v4 |
| https://arxiv.org/pdf/1810.12780v4.pdf | |
| PWC | https://paperswithcode.com/paper/advancing-pico-element-detection-in-medical |
| Repo | |
| Framework | |
Fair lending needs explainable models for responsible recommendation
| Title | Fair lending needs explainable models for responsible recommendation |
| Authors | Jiahao Chen |
| Abstract | The financial services industry has unique explainability and fairness challenges arising from compliance and ethical considerations in credit decisioning. These challenges complicate the use of model machine learning and artificial intelligence methods in business decision processes. |
| Tasks | |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04684v1 |
| http://arxiv.org/pdf/1809.04684v1.pdf | |
| PWC | https://paperswithcode.com/paper/fair-lending-needs-explainable-models-for |
| Repo | |
| Framework | |
Hiding in the Crowd: A Massively Distributed Algorithm for Private Averaging with Malicious Adversaries
| Title | Hiding in the Crowd: A Massively Distributed Algorithm for Private Averaging with Malicious Adversaries |
| Authors | Pierre Dellenbach, Aurélien Bellet, Jan Ramon |
| Abstract | The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as raises serious concerns for the privacy of individuals. In this paper, we propose a massively distributed protocol for a large set of users to privately compute averages over their joint data, which can then be used to learn predictive models. Our protocol can find a solution of arbitrary accuracy, does not rely on a third party and preserves the privacy of users throughout the execution in both the honest-but-curious and malicious adversary models. Specifically, we prove that the information observed by the adversary (the set of maliciours users) does not significantly reduce the uncertainty in its prediction of private values compared to its prior belief. The level of privacy protection depends on a quantity related to the Laplacian matrix of the network graph and generally improves with the size of the graph. Furthermore, we design a verification procedure which offers protection against malicious users joining the service with the goal of manipulating the outcome of the algorithm. |
| Tasks | |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.09984v1 |
| http://arxiv.org/pdf/1803.09984v1.pdf | |
| PWC | https://paperswithcode.com/paper/hiding-in-the-crowd-a-massively-distributed |
| Repo | |
| Framework | |
Neural Trajectory Analysis of Recurrent Neural Network In Handwriting Synthesis
| Title | Neural Trajectory Analysis of Recurrent Neural Network In Handwriting Synthesis |
| Authors | Kristof B. Charbonneau, Osamu Shouno |
| Abstract | Recurrent neural networks (RNNs) are capable of learning to generate highly realistic, online handwritings in a wide variety of styles from a given text sequence. Furthermore, the networks can generate handwritings in the style of a particular writer when the network states are primed with a real sequence of pen movements from the writer. However, how populations of neurons in the RNN collectively achieve such performance still remains poorly understood. To tackle this problem, we investigated learned representations in RNNs by extracting low-dimensional, neural trajectories that summarize the activity of a population of neurons in the network during individual syntheses of handwritings. The neural trajectories show that different writing styles are encoded in different subspaces inside an internal space of the network. Within each subspace, different characters of the same style are represented as different state dynamics. These results demonstrate the effectiveness of analyzing the neural trajectory for intuitive understanding of how the RNNs work. |
| Tasks | |
| Published | 2018-04-13 |
| URL | http://arxiv.org/abs/1804.04890v1 |
| http://arxiv.org/pdf/1804.04890v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-trajectory-analysis-of-recurrent |
| Repo | |
| Framework | |
Finding and Following of Honeycombing Regions in Computed Tomography Lung Images by Deep Learning
| Title | Finding and Following of Honeycombing Regions in Computed Tomography Lung Images by Deep Learning |
| Authors | Emre Eğriboz, Furkan Kaynar, Songül Varlı Albayrak, Benan Müsellim, Tuba Selçuk |
| Abstract | In recent years, besides the medical treatment methods in medical field, Computer Aided Diagnosis (CAD) systems which can facilitate the decision making phase of the physician and can detect the disease at an early stage have started to be used frequently. The diagnosis of Idiopathic Pulmonary Fibrosis (IPF) disease by using CAD systems is very important in that it can be followed by doctors and radiologists. It has become possible to diagnose and follow up the disease with the help of CAD systems by the development of high resolution computed imaging scanners and increasing size of computation power. The purpose of this project is to design a tool that will help specialists diagnose and follow up the IPF disease by identifying areas of honeycombing and ground glass patterns in High Resolution Computed Tomography (HRCT) lung images. Creating a program module that segments the lung pair and creating a self-learner deep learning model from given Computed Tomography (CT) images for the specific diseased regions thanks to doctors are the main purposes of this work. Through the created model, program module will be able to find special regions in given new CT images. In this study, the performance of lung segmentation was tested by the S{\o}rensen-Dice coefficient method and the mean performance was measured as 90.7%, testing of the created model was performed with data not used in the training stage of the CNN network, and the average performance was measured as 87.8% for healthy regions, 73.3% for ground-glass areas and 69.1% for honeycombing zones. |
| Tasks | Computed Tomography (CT), Decision Making |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.02651v3 |
| http://arxiv.org/pdf/1811.02651v3.pdf | |
| PWC | https://paperswithcode.com/paper/finding-and-following-of-honeycombing-regions |
| Repo | |
| Framework | |
AFT*: Integrating Active Learning and Transfer Learning to Reduce Annotation Efforts
| Title | AFT*: Integrating Active Learning and Transfer Learning to Reduce Annotation Efforts |
| Authors | Zongwei Zhou, Jae Y. Shin, Suryakanth R. Gurudu, Michael B. Gotway, Jianming Liang |
| Abstract | The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributed to the availability of large annotated datasets, such as ImageNet and Places. However, in biomedical imaging, it is very challenging to create such large annotated datasets, as annotating biomedical images is not only tedious, laborious, and time consuming, but also demanding of costly, specialty-oriented skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method to naturally integrate active learning and transfer learning (fine-tuning) into a single framework, called AFT*, which starts directly with a pre-trained CNN to seek “worthy” samples for annotation and gradually enhance the (fine-tuned) CNN via continuous fine-tuning. We have evaluated our method in three distinct biomedical imaging applications, demonstrating that it can cut the annotation cost by at least half, in comparison with the state-of-the-art method. This performance is attributed to the several advantages derived from the advanced active, continuous learning capability of our method. Although AFT* was initially conceived in the context of computer-aided diagnosis in biomedical imaging, it is generic and applicable to many tasks in computer vision and image analysis; we illustrate the key ideas behind AFT* with the Places database for scene interpretation in natural images. |
| Tasks | Active Learning, Transfer Learning |
| Published | 2018-02-03 |
| URL | http://arxiv.org/abs/1802.00912v2 |
| http://arxiv.org/pdf/1802.00912v2.pdf | |
| PWC | https://paperswithcode.com/paper/aft-integrating-active-learning-and-transfer |
| Repo | |
| Framework | |
FotonNet: A HW-Efficient Object Detection System Using 3D-Depth Segmentation and 2D-DNN Classifier
| Title | FotonNet: A HW-Efficient Object Detection System Using 3D-Depth Segmentation and 2D-DNN Classifier |
| Authors | Gurjeet Singh, Sun Miao, Shi Shi, Patrick Chiang |
| Abstract | Object detection and classification is one of the most important computer vision problems. Ever since the introduction of deep learning \cite{krizhevsky2012imagenet}, we have witnessed a dramatic increase in the accuracy of this object detection problem. However, most of these improvements have occurred using conventional 2D image processing. Recently, low-cost 3D-image sensors, such as the Microsoft Kinect (Time-of-Flight) or the Apple FaceID (Structured-Light), can provide 3D-depth or point cloud data that can be added to a convolutional neural network, acting as an extra set of dimensions. In our proposed approach, we introduce a new 2D + 3D system that takes the 3D-data to determine the object region followed by any conventional 2D-DNN, such as AlexNet. In this method, our approach can easily dissociate the information collection from the Point Cloud and 2D-Image data and combine both operations later. Hence, our system can use any existing trained 2D network on a large image dataset, and does not require a large 3D-depth dataset for new training. Experimental object detection results across 30 images show an accuracy of 0.67, versus 0.54 and 0.51 for RCNN and YOLO, respectively. |
| Tasks | Object Detection |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07493v1 |
| http://arxiv.org/pdf/1811.07493v1.pdf | |
| PWC | https://paperswithcode.com/paper/fotonnet-a-hw-efficient-object-detection |
| Repo | |
| Framework | |
An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models
| Title | An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models |
| Authors | Ulrich Paquet, Marco Fraccaro |
| Abstract | This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from $N$-dimensional posterior distributions $p(xy)$, where $x \in R^N$ is drawn from a Gaussian Process (GP) prior, and observations $y_n$ are independent given $x_n$. Sufficient technical and algorithmic details are provided for the implementation of RMHMC for distributions arising from GP priors. |
| Tasks | |
| Published | 2018-10-28 |
| URL | http://arxiv.org/abs/1810.11893v1 |
| http://arxiv.org/pdf/1810.11893v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-implementation-of-riemannian |
| Repo | |
| Framework | |
Fuzzy Controller of Reward of Reinforcement Learning For Handwritten Digit Recognition
| Title | Fuzzy Controller of Reward of Reinforcement Learning For Handwritten Digit Recognition |
| Authors | Saber Malekzadeh |
| Abstract | Recognition of human environment with computer systems always was a big deal in artificial intelligence. In this area handwriting recognition and conceptualization of it to computer is an important area in it. In the past years with growth of machine learning in artificial intelligence, efforts to using this technique increased. In this paper is tried to using fuzzy controller, to optimizing amount of reward of reinforcement learning for recognition of handwritten digits. For this aim first a sample of every digit with 10 standard computer fonts, given to actor and then actor is trained. In the next level is tried to test the actor with dataset and then results show improvement of recognition when using fuzzy controller of reinforcement learning. |
| Tasks | Handwritten Digit Recognition |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.07028v1 |
| http://arxiv.org/pdf/1812.07028v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-controller-of-reward-of-reinforcement |
| Repo | |
| Framework | |
