July 28, 2019

3052 words 15 mins read

Paper Group ANR 455

Markov chain Hebbian learning algorithm with ternary synaptic units. Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts. Towards Automatic Learning of Heuristics for Mechanical Transformations of Procedural Code. Scalable Object Detection for Stylized Objects. Smart Augmentation - Learnin …

Markov chain Hebbian learning algorithm with ternary synaptic units


Title	Markov chain Hebbian learning algorithm with ternary synaptic units
Authors	Guhyun Kim, Vladimir Kornijcuk, Dohun Kim, Inho Kim, Jaewook Kim, Hyo Cheon Woo, Ji Hun Kim, Cheol Seong Hwang, Doo Seok Jeong
Abstract	In spite of remarkable progress in machine learning techniques, the state-of-the-art machine learning algorithms often keep machines from real-time learning (online learning) due in part to computational complexity in parameter optimization. As an alternative, a learning algorithm to train a memory in real time is proposed, which is named as the Markov chain Hebbian learning algorithm. The algorithm pursues efficient memory use during training in that (i) the weight matrix has ternary elements (-1, 0, 1) and (ii) each update follows a Markov chain–the upcoming update does not need past weight memory. The algorithm was verified by two proof-of-concept tasks (handwritten digit recognition and multiplication table memorization) in which numbers were taken as symbols. Particularly, the latter bases multiplication arithmetic on memory, which may be analogous to humans’ mental arithmetic. The memory-based multiplication arithmetic feasibly offers the basis of factorization, supporting novel insight into the arithmetic.
Tasks	Handwritten Digit Recognition
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08679v1
PDF	http://arxiv.org/pdf/1711.08679v1.pdf
PWC	https://paperswithcode.com/paper/markov-chain-hebbian-learning-algorithm-with
Repo
Framework

Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts


Title	Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts
Authors	Leandro B. dos Santos, Edilson A. Corrêa Jr, Osvaldo N. Oliveira Jr, Diego R. Amancio, Letícia L. Mansur, Sandra M. Aluísio
Abstract	Mild Cognitive Impairment (MCI) is a mental disorder difficult to diagnose. Linguistic features, mainly from parsers, have been used to detect MCI, but this is not suitable for large-scale assessments. MCI disfluencies produce non-grammatical speech that requires manual or high precision automatic correction of transcripts. In this paper, we modeled transcripts into complex networks and enriched them with word embedding (CNE) to better represent short texts produced in neuropsychological assessments. The network measurements were applied with well-known classifiers to automatically identify MCI in transcripts, in a binary classification task. A comparison was made with the performance of traditional approaches using Bag of Words (BoW) and linguistic features for three datasets: DementiaBank in English, and Cinderella and Arizona-Battery in Portuguese. Overall, CNE provided higher accuracy than using only complex networks, while Support Vector Machine was superior to other classifiers. CNE provided the highest accuracies for DementiaBank and Cinderella, but BoW was more efficient for the Arizona-Battery dataset probably owing to its short narratives. The approach using linguistic features yielded higher accuracy if the transcriptions of the Cinderella dataset were manually revised. Taken together, the results indicate that complex networks enriched with embedding is promising for detecting MCI in large-scale assessments
Tasks	Word Embeddings
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08088v1
PDF	http://arxiv.org/pdf/1704.08088v1.pdf
PWC	https://paperswithcode.com/paper/enriching-complex-networks-with-word
Repo
Framework

Towards Automatic Learning of Heuristics for Mechanical Transformations of Procedural Code


Title	Towards Automatic Learning of Heuristics for Mechanical Transformations of Procedural Code
Authors	Guillermo Vigueras, Manuel Carro, Salvador Tamarit, Julio Mariño
Abstract	The current trends in next-generation exascale systems go towards integrating a wide range of specialized (co-)processors into traditional supercomputers. Due to the efficiency of heterogeneous systems in terms of Watts and FLOPS per surface unit, opening the access of heterogeneous platforms to a wider range of users is an important problem to be tackled. However, heterogeneous platforms limit the portability of the applications and increase development complexity due to the programming skills required. Program transformation can help make programming heterogeneous systems easier by defining a step-wise transformation process that translates a given initial code into a semantically equivalent final code, but adapted to a specific platform. Program transformation systems require the definition of efficient transformation strategies to tackle the combinatorial problem that emerges due to the large set of transformations applicable at each step of the process. In this paper we propose a machine learning-based approach to learn heuristics to define program transformation strategies. Our approach proposes a novel combination of reinforcement learning and classification methods to efficiently tackle the problems inherent to this type of systems. Preliminary results demonstrate the suitability of this approach.
Tasks
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07123v1
PDF	http://arxiv.org/pdf/1701.07123v1.pdf
PWC	https://paperswithcode.com/paper/towards-automatic-learning-of-heuristics-for
Repo
Framework

Scalable Object Detection for Stylized Objects


Title	Scalable Object Detection for Stylized Objects
Authors	Aayush Garg, Thilo Will, William Darling, Willi Richert, Clemens Marschner
Abstract	Following recent breakthroughs in convolutional neural networks and monolithic model architectures, state-of-the-art object detection models can reliably and accurately scale into the realm of up to thousands of classes. Things quickly break down, however, when scaling into the tens of thousands, or, eventually, to millions or billions of unique objects. Further, bounding box-trained end-to-end models require extensive training data. Even though - with some tricks using hierarchies - one can sometimes scale up to thousands of classes, the labor requirements for clean image annotations quickly get out of control. In this paper, we present a two-layer object detection method for brand logos and other stylized objects for which prototypical images exist. It can scale to large numbers of unique classes. Our first layer is a CNN from the Single Shot Multibox Detector family of models that learns to propose regions where some stylized object is likely to appear. The contents of a proposed bounding box is then run against an image index that is targeted for the retrieval task at hand. The proposed architecture scales to a large number of object classes, allows to continously add new classes without retraining, and exhibits state-of-the-art quality on a stylized object detection task such as logo recognition.
Tasks	Logo Recognition, Object Detection
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09822v2
PDF	http://arxiv.org/pdf/1711.09822v2.pdf
PWC	https://paperswithcode.com/paper/scalable-object-detection-for-stylized
Repo
Framework

Smart Augmentation - Learning an Optimal Data Augmentation Strategy


Title	Smart Augmentation - Learning an Optimal Data Augmentation Strategy
Authors	Joseph Lemley, Shabab Bazrafkan, Peter Corcoran
Abstract	A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks(DNN). There are many techniques to address this, including data augmentation, dropout, and transfer learning. In this paper, we introduce an additional method which we call Smart Augmentation and we show how to use it to increase the accuracy and reduce overfitting on a target network. Smart Augmentation works by creating a network that learns how to generate augmented data during the training process of a target network in a way that reduces that networks loss. This allows us to learn augmentations that minimize the error of that network. Smart Augmentation has shown the potential to increase accuracy by demonstrably significant measures on all datasets tested. In addition, it has shown potential to achieve similar or improved performance levels with significantly smaller network sizes in a number of tested cases.
Tasks	Data Augmentation, Transfer Learning
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08383v1
PDF	http://arxiv.org/pdf/1703.08383v1.pdf
PWC	https://paperswithcode.com/paper/smart-augmentation-learning-an-optimal-data
Repo
Framework

Heat Kernel Smoothing in Irregular Image Domains


Title	Heat Kernel Smoothing in Irregular Image Domains
Authors	Moo K. Chung, Yanli Wang, Gurong Wu
Abstract	We present the discrete version of heat kernel smoothing on graph data structure. The method is used to smooth data in an irregularly shaped domains in 3D images. New statistical properties are derived. As an application, we show how to filter out data in the lung blood vessel trees obtained from computed tomography. The method can be further used in representing the complex vessel trees parametrically and extracting the skeleton representation of the trees.
Tasks
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07849v1
PDF	http://arxiv.org/pdf/1710.07849v1.pdf
PWC	https://paperswithcode.com/paper/heat-kernel-smoothing-in-irregular-image
Repo
Framework

Automatic Prediction of Discourse Connectives


Title	Automatic Prediction of Discourse Connectives
Authors	Eric Malmi, Daniele Pighin, Sebastian Krause, Mikhail Kozhevnikov
Abstract	Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.
Tasks
Published	2017-02-03
URL	http://arxiv.org/abs/1702.00992v2
PDF	http://arxiv.org/pdf/1702.00992v2.pdf
PWC	https://paperswithcode.com/paper/automatic-prediction-of-discourse-connectives
Repo
Framework

Cogniculture: Towards a Better Human-Machine Co-evolution


Title	Cogniculture: Towards a Better Human-Machine Co-evolution
Authors	Rakesh R Pimplikar, Kushal Mukherjee, Gyana Parija, Harit Vishwakarma, Ramasuri Narayanam, Sarthak Ahuja, Rohith D Vallam, Ritwik Chaudhuri, Joydeep Mondal
Abstract	Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life easier for human beings day by day, there is constant fear that AI based systems will pose a threat to humanity. People in AI community have diverse set of opinions regarding the pros and cons of AI mimicking human behavior. Instead of worrying about AI advancements, we propose a novel idea of cognitive agents, including both human and machines, living together in a complex adaptive ecosystem, collaborating on human computation for producing essential social goods while promoting sustenance, survival and evolution of the agents’ life cycle. We highlight several research challenges and technology barriers in achieving this goal. We propose a governance mechanism around this ecosystem to ensure ethical behaviors of all cognitive agents. Along with a novel set of use-cases of Cogniculture, we discuss the road map ahead for this journey.
Tasks
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03724v1
PDF	http://arxiv.org/pdf/1712.03724v1.pdf
PWC	https://paperswithcode.com/paper/cogniculture-towards-a-better-human-machine
Repo
Framework

DART: Noise Injection for Robust Imitation Learning


Title	DART: Noise Injection for Robust Imitation Learning
Authors	Michael Laskey, Jonathan Lee, Roy Fox, Anca Dragan, Ken Goldberg
Abstract	One approach to Imitation Learning is Behavior Cloning, in which a robot observes a supervisor and infers a control policy. A known problem with this “off-policy” approach is that the robot’s errors compound when drifting away from the supervisor’s demonstrations. On-policy, techniques alleviate this by iteratively collecting corrective actions for the current robot policy. However, these techniques can be tedious for human supervisors, add significant computation burden, and may visit dangerous states during training. We propose an off-policy approach that injects noise into the supervisor’s policy while demonstrating. This forces the supervisor to demonstrate how to recover from errors. We propose a new algorithm, DART (Disturbances for Augmenting Robot Trajectories), that collects demonstrations with injected noise, and optimizes the noise level to approximate the error of the robot’s trained policy during data collection. We compare DART with DAgger and Behavior Cloning in two domains: in simulation with an algorithmic supervisor on the MuJoCo tasks (Walker, Humanoid, Hopper, Half-Cheetah) and in physical experiments with human supervisors training a Toyota HSR robot to perform grasping in clutter. For high dimensional tasks like Humanoid, DART can be up to $3x$ faster in computation time and only decreases the supervisor’s cumulative reward by $5%$ during training, whereas DAgger executes policies that have $80%$ less cumulative reward than the supervisor. On the grasping in clutter task, DART obtains on average a $62%$ performance increase over Behavior Cloning.
Tasks	Imitation Learning
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09327v2
PDF	http://arxiv.org/pdf/1703.09327v2.pdf
PWC	https://paperswithcode.com/paper/dart-noise-injection-for-robust-imitation
Repo
Framework

Empirical Evaluation of Kernel PCA Approximation Methods in Classification Tasks


Title	Empirical Evaluation of Kernel PCA Approximation Methods in Classification Tasks
Authors	Deena P. Francis, Kumudha Raimond
Abstract	Kernel Principal Component Analysis (KPCA) is a popular dimensionality reduction technique with a wide range of applications. However, it suffers from the problem of poor scalability. Various approximation methods have been proposed in the past to overcome this problem. The Nystr"om method, Randomized Nonlinear Component Analysis (RNCA) and Streaming Kernel Principal Component Analysis (SKPCA) were proposed to deal with the scalability issue of KPCA. Despite having theoretical guarantees, their performance in real world learning tasks have not been explored previously. In this work the evaluation of SKPCA, RNCA and Nystr"om method for the task of classification is done for several real world datasets. The results obtained indicate that SKPCA based features gave much better classification accuracy when compared to the other methods for a very large dataset.
Tasks	Dimensionality Reduction
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04196v1
PDF	http://arxiv.org/pdf/1712.04196v1.pdf
PWC	https://paperswithcode.com/paper/empirical-evaluation-of-kernel-pca
Repo
Framework

Source Camera Identification Based On Content-Adaptive Fusion Network


Title	Source Camera Identification Based On Content-Adaptive Fusion Network
Authors	Pengpeng Yang, Wei Zhao, Rongrong Ni, Yao Zhao
Abstract	Source camera identification is still a hard task in forensics community, especially for the case of the small query image size. In this paper, we propose a solution to identify the source camera of the small-size images: content-adaptive fusion network. In order to learn better feature representation from the input data, content-adaptive convolutional neural networks(CA-CNN) are constructed. We add a convolutional layer in preprocessing stage. Moreover, with the purpose of capturing more comprehensive information, we parallel three CA-CNNs: CA3-CNN, CA5-CNN, CA7-CNN to get the content-adaptive fusion network. The difference of three CA-CNNs lies in the convolutional kernel size of pre-processing layer. The experimental results show that the proposed method is practicable and satisfactory.
Tasks
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04856v1
PDF	http://arxiv.org/pdf/1703.04856v1.pdf
PWC	https://paperswithcode.com/paper/source-camera-identification-based-on-content
Repo
Framework

Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration


Title	Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration
Authors	Mehreen Alam, Sibt ul Hussain
Abstract	Neural Machine Translation models have replaced the conventional phrase based statistical translation methods since the former takes a generic, scalable, data-driven approach rather than relying on manual, hand-crafted features. The neural machine translation system is based on one neural network that is composed of two parts, one that is responsible for input language sentence and other part that handles the desired output language sentence. This model based on encoder-decoder architecture also takes as input the distributed representations of the source language which enriches the learnt dependencies and gives a warm start to the network. In this work, we transform Roman-Urdu to Urdu transliteration into sequence to sequence learning problem. To this end, we make the following contributions. We create the first ever parallel corpora of Roman-Urdu to Urdu, create the first ever distributed representation of Roman-Urdu and present the first neural machine translation model that transliterates text from Roman-Urdu to Urdu language. Our model has achieved the state-of-the-art results using BLEU as the evaluation metric. Precisely, our model is able to correctly predict sentences up to length 10 while achieving BLEU score of 48.6 on the test set. We are hopeful that our model and our results shall serve as the baseline for further work in the domain of neural machine translation for Roman-Urdu to Urdu using distributed representation.
Tasks	Machine Translation, Transliteration
Published	2017-12-08
URL	http://arxiv.org/abs/1712.02959v1
PDF	http://arxiv.org/pdf/1712.02959v1.pdf
PWC	https://paperswithcode.com/paper/sequence-to-sequence-networks-for-roman-urdu
Repo
Framework

Feature Selective Networks for Object Detection


Title	Feature Selective Networks for Object Detection
Authors	Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li
Abstract	Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted by RoI pooling with little emphasis on these translation-variant feature components. We present feature selective networks to reform the feature representations of RoIs by exploiting their disparities among sub-regions and aspect ratios. Our network produces the sub-region attention bank and aspect ratio attention bank for the whole image. The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification. Equipped with a light-weight detection subnetwork, our network gets a consistent boost in detection performance based on general ConvNet backbones (ResNet-101, GoogLeNet and VGG-16). Without bells and whistles, our detectors equipped with ResNet-101 achieve more than 3% mAP improvement compared to counterparts on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets.
Tasks	Object Detection
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08879v1
PDF	http://arxiv.org/pdf/1711.08879v1.pdf
PWC	https://paperswithcode.com/paper/feature-selective-networks-for-object
Repo
Framework

Delving into adversarial attacks on deep policies


Title	Delving into adversarial attacks on deep policies
Authors	Jernej Kos, Dawn Song
Abstract	Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polices. We compare the effectiveness of the attacks using adversarial examples vs. random noise. We present a novel method for reducing the number of times adversarial examples need to be injected for a successful attack, based on the value function. We further explore how re-training on random noise and FGSM perturbations affects the resilience against adversarial examples.
Tasks
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06452v1
PDF	http://arxiv.org/pdf/1705.06452v1.pdf
PWC	https://paperswithcode.com/paper/delving-into-adversarial-attacks-on-deep
Repo
Framework

Improving Adherence to Heart Failure Management Guidelines via Abductive Reasoning


Title	Improving Adherence to Heart Failure Management Guidelines via Abductive Reasoning
Authors	Zhuo Chen, Elmer Salazar, Kyle Marple, Gopal Gupta, Lakshman Tamil, Sandeep Das, Alpesh Amin
Abstract	Management of chronic diseases such as heart failure (HF) is a major public health problem. A standard approach to managing chronic diseases by medical community is to have a committee of experts develop guidelines that all physicians should follow. Due to their complexity, these guidelines are difficult to implement and are adopted slowly by the medical community at large. We have developed a physician advisory system that codes the entire set of clinical practice guidelines for managing HF using answer set programming(ASP). In this paper we show how abductive reasoning can be deployed to find missing symptoms and conditions that the patient must exhibit in order for a treatment prescribed by a physician to work effectively. Thus, if a physician does not make an appropriate recommendation or makes a non-adherent recommendation, our system will advise the physician about symptoms and conditions that must be in effect for that recommendation to apply. It is under consideration for acceptance in TPLP.
Tasks
Published	2017-07-16
URL	http://arxiv.org/abs/1707.04957v1
PDF	http://arxiv.org/pdf/1707.04957v1.pdf
PWC	https://paperswithcode.com/paper/improving-adherence-to-heart-failure
Repo
Framework