July 29, 2019

3074 words 15 mins read

Paper Group ANR 26

Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention. A Deformable Interface for Human Touch Recognition using Stretchable Carbon Nanotube Dielectric Elastomer Sensors and Deep Neural Networks. Deep Convolutional Neural Networks for Pairwise Causality. An Approach to One-Bit Compressed Sensing Based on …

Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention


Title	Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention
Authors	Feiyun Zhu, Peng Liao
Abstract	Online reinforcement learning (RL) is increasingly popular for the personalized mobile health (mHealth) intervention. It is able to personalize the type and dose of interventions according to user’s ongoing statuses and changing needs. However, at the beginning of online learning, there are usually too few samples to support the RL updating, which leads to poor performances. A delay in good performance of the online learning algorithms can be especially detrimental in the mHealth, where users tend to quickly disengage with the mHealth app. To address this problem, we propose a new online RL methodology that focuses on an effective warm start. The main idea is to make full use of the data accumulated and the decision rule achieved in a former study. As a result, we can greatly enrich the data size at the beginning of online learning in our method. Such case accelerates the online learning process for new users to achieve good performances not only at the beginning of online learning but also through the whole online learning process. Besides, we use the decision rules achieved in a previous study to initialize the parameter in our online RL model for new users. It provides a good initialization for the proposed online RL algorithm. Experiment results show that promising improvements have been achieved by our method compared with the state-of-the-art method.
Tasks
Published	2017-04-17
URL	http://arxiv.org/abs/1704.04866v3
PDF	http://arxiv.org/pdf/1704.04866v3.pdf
PWC	https://paperswithcode.com/paper/effective-warm-start-for-the-online-actor
Repo
Framework

A Deformable Interface for Human Touch Recognition using Stretchable Carbon Nanotube Dielectric Elastomer Sensors and Deep Neural Networks


Title	A Deformable Interface for Human Touch Recognition using Stretchable Carbon Nanotube Dielectric Elastomer Sensors and Deep Neural Networks
Authors	Chris Larson, Josef Spjut, Ross Knepper, Robert Shepherd
Abstract	User interfaces provide an interactive window between physical and virtual environments. A new concept in the field of human-computer interaction is a soft user interface; a compliant surface that facilitates touch interaction through deformation. Despite the potential of these interfaces, they currently lack a signal processing framework that can efficiently extract information from their deformation. Here we present OrbTouch, a device that uses statistical learning algorithms, based on convolutional neural networks, to map deformations from human touch to categorical labels (i.e., gestures) and touch location using stretchable capacitor signals as inputs. We demonstrate this approach by using the device to control the popular game Tetris. OrbTouch provides a modular, robust framework to interpret deformation in soft media, laying a foundation for new modes of human computer interaction through shape changing solids.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02542v3
PDF	http://arxiv.org/pdf/1706.02542v3.pdf
PWC	https://paperswithcode.com/paper/a-deformable-interface-for-human-touch
Repo
Framework

Deep Convolutional Neural Networks for Pairwise Causality


Title	Deep Convolutional Neural Networks for Pairwise Causality
Authors	Karamjit Singh, Garima Gupta, Lovekesh Vig, Gautam Shroff, Puneet Agarwal
Abstract	Discovering causal models from observational and interventional data is an important first step preceding what-if analysis or counterfactual reasoning. As has been shown before, the direction of pairwise causal relations can, under certain conditions, be inferred from observational data via standard gradient-boosted classifiers (GBC) using carefully engineered statistical features. In this paper we apply deep convolutional neural networks (CNNs) to this problem by plotting attribute pairs as 2-D scatter plots that are fed to the CNN as images. We evaluate our approach on the ‘Cause- Effect Pairs’ NIPS 2013 Data Challenge. We observe that a weighted ensemble of CNN with the earlier GBC approach yields significant improvement. Further, we observe that when less training data is available, our approach performs better than the GBC based approach suggesting that CNN models pre-trained to determine the direction of pairwise causal direction could have wider applicability in causal discovery and enabling what-if or counterfactual analysis.
Tasks	Causal Discovery
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00597v1
PDF	http://arxiv.org/pdf/1701.00597v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-3
Repo
Framework

An Approach to One-Bit Compressed Sensing Based on Probably Approximately Correct Learning Theory


Title	An Approach to One-Bit Compressed Sensing Based on Probably Approximately Correct Learning Theory
Authors	Mehmet Eren Ahsen, Mathukumalli Vidyasagar
Abstract	In this paper, the problem of one-bit compressed sensing (OBCS) is formulated as a problem in probably approximately correct (PAC) learning. It is shown that the Vapnik-Chervonenkis (VC-) dimension of the set of half-spaces in $\mathbb{R}^n$ generated by $k$-sparse vectors is bounded below by $k \lg (n/k)$ and above by $2k \lg (n/k)$, plus some round-off terms. By coupling this estimate with well-established results in PAC learning theory, we show that a consistent algorithm can recover a $k$-sparse vector with $O(k \lg (n/k))$ measurements, given only the signs of the measurement vector. This result holds for \textit{all} probability measures on $\mathbb{R}^n$. It is further shown that random sign-flipping errors result only in an increase in the constant in the $O(k \lg (n/k))$ estimate. Because constructing a consistent algorithm is not straight-forward, we present a heuristic based on the $\ell_1$-norm support vector machine, and illustrate that its computational performance is superior to a currently popular method.
Tasks
Published	2017-10-22
URL	http://arxiv.org/abs/1710.07973v1
PDF	http://arxiv.org/pdf/1710.07973v1.pdf
PWC	https://paperswithcode.com/paper/an-approach-to-one-bit-compressed-sensing
Repo
Framework

Detection, Segmentation and Recognition of Face and its Features Using Neural Network


Title	Detection, Segmentation and Recognition of Face and its Features Using Neural Network
Authors	Smriti Tikoo, Nitin Malik
Abstract	Face detection and recognition has been prevalent with research scholars and diverse approaches have been incorporated till date to serve purpose. The rampant advent of biometric analysis systems, which may be full body scanners, or iris detection and recognition systems and the finger print recognition systems, and surveillance systems deployed for safety and security purposes have contributed to inclination towards same. Advances has been made with frontal view, lateral view of the face or using facial expressions such as anger, happiness and gloominess, still images and video image to be used for detection and recognition. This led to newer methods for face detection and recognition to be introduced in achieving accurate results and economically feasible and extremely secure. Techniques such as Principal Component analysis (PCA), Independent component analysis (ICA), Linear Discriminant Analysis (LDA), have been the predominant ones to be used. But with improvements needed in the previous approaches Neural Networks based recognition was like boon to the industry. It not only enhanced the recognition but also the efficiency of the process. Choosing Backpropagation as the learning method was clearly out of its efficiency to recognize nonlinear faces with an acceptance ratio of more than 90% and execution time of only few seconds.
Tasks	Face Detection
Published	2017-01-28
URL	http://arxiv.org/abs/1701.08259v1
PDF	http://arxiv.org/pdf/1701.08259v1.pdf
PWC	https://paperswithcode.com/paper/detection-segmentation-and-recognition-of
Repo
Framework

Fast and unsupervised methods for multilingual cognate clustering


Title	Fast and unsupervised methods for multilingual cognate clustering
Authors	Taraka Rama, Johannes Wahle, Pavel Sofroniev, Gerhard Jäger
Abstract	In this paper we explore the use of unsupervised methods for detecting cognates in multilingual word lists. We use online EM to train sound segment similarity weights for computing similarity between two words. We tested our online systems on geographically spread sixteen different language groups of the world and show that the Online PMI system (Pointwise Mutual Information) outperforms a HMM based system and two linguistically motivated systems: LexStat and ALINE. Our results suggest that a PMI system trained in an online fashion can be used by historical linguists for fast and accurate identification of cognates in not so well-studied language families.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04938v1
PDF	http://arxiv.org/pdf/1702.04938v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-unsupervised-methods-for
Repo
Framework

The Tensor Memory Hypothesis


Title	The Tensor Memory Hypothesis
Authors	Volker Tresp, Yunpu Ma
Abstract	We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories are generated via perception. We relate our mathematical approach to the hippocampal memory indexing theory. We describe the first detailed mathematical models for the complete processing pipeline from sensory input and its semantic decoding, i.e., perception, to the formation of episodic and semantic memories and their declarative semantic decodings. Our main hypothesis is that perception includes an active semantic decoding process, which relies on latent representations of entities and predicates, and that episodic and semantic memories depend on the same decoding process. We contribute to the debate between the leading memory consolidation theories, i.e., the standard consolidation theory (SCT) and the multiple trace theory (MTT). The latter is closely related to the complementary learning systems (CLS) framework. In particular, we show explicitly how episodic memory can teach the neocortex to form a semantic memory, which is a core issue in MTT and CLS.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02918v2
PDF	http://arxiv.org/pdf/1708.02918v2.pdf
PWC	https://paperswithcode.com/paper/the-tensor-memory-hypothesis
Repo
Framework

A Rule-Based Computational Model of Cognitive Arithmetic


Title	A Rule-Based Computational Model of Cognitive Arithmetic
Authors	Ashis Pati, Kantwon Rogers, Hanqing Zhu
Abstract	Cognitive arithmetic studies the mental processes used in solving math problems. This area of research explores the retrieval mechanisms and strategies used by people during a common cognitive task. Past research has shown that human performance in arithmetic operations is correlated to the numerical size of the problem. Past research on cognitive arithmetic has pinpointed this trend to either retrieval strength, error checking, or strategy-based approaches when solving equations. This paper describes a rule-based computational model that performs the four major arithmetic operations (addition, subtraction, multiplication and division) on two operands. We then evaluated our model to probe its validity in representing the prevailing concepts observed in psychology experiments from the related works. The experiments specifically explore the problem size effect, an activation-based model for fact retrieval, backup strategies when retrieval fails, and finally optimization strategies when faced with large operands. From our experimental results, we concluded that our model’s response times were comparable to results observed when people performed similar tasks during psychology experiments. The fit of our model in reproducing these results and incorporating accuracy into our model are discussed.
Tasks
Published	2017-05-03
URL	http://arxiv.org/abs/1705.01208v1
PDF	http://arxiv.org/pdf/1705.01208v1.pdf
PWC	https://paperswithcode.com/paper/a-rule-based-computational-model-of-cognitive
Repo
Framework

L2GSCI: Local to Global Seam Cutting and Integrating for Accurate Face Contour Extraction


Title	L2GSCI: Local to Global Seam Cutting and Integrating for Accurate Face Contour Extraction
Authors	Yongwei Nie, Xu Cao, Chengjiang Long, Ping Li, Guiqing Li
Abstract	Current face alignment algorithms can robustly find a set of landmarks along face contour. However, the landmarks are sparse and lack curve details, especially in chin and cheek areas where a lot of concave-convex bending information exists. In this paper, we propose a local to global seam cutting and integrating algorithm (L2GSCI) to extract continuous and accurate face contour. Our method works in three steps with the help of a rough initial curve. First, we sample small and overlapped squares along the initial curve. Second, the seam cutting part of L2GSCI extracts a local seam in each square region. Finally, the seam integrating part of L2GSCI connects all the redundant seams together to form a continuous and complete face curve. Overall, the proposed method is much more straightforward than existing face alignment algorithms, but can achieve pixel-level continuous face curves rather than discrete and sparse landmarks. Moreover, experiments on two face benchmark datasets (i.e., LFPW and HELEN) show that our method can precisely reveal concave-convex bending details of face contours, which has significantly improved the performance when compared with the state-ofthe- art face alignment approaches.
Tasks	Face Alignment
Published	2017-03-05
URL	http://arxiv.org/abs/1703.01605v1
PDF	http://arxiv.org/pdf/1703.01605v1.pdf
PWC	https://paperswithcode.com/paper/l2gsci-local-to-global-seam-cutting-and
Repo
Framework

Learning to Rank based on Analogical Reasoning


Title	Learning to Rank based on Analogical Reasoning
Authors	Mohsen Ahmadi Fahandar, Eyke Hüllermeier
Abstract	Object ranking or “learning to rank” is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. In this paper, we propose a new approach to object ranking based on principles of analogical reasoning. More specifically, our inference pattern is formalized in terms of so-called analogical proportions and can be summarized as follows: Given objects $A,B,C,D$, if object $A$ is known to be preferred to $B$, and $C$ relates to $D$ as $A$ relates to $B$, then $C$ is (supposedly) preferred to $D$. Our method applies this pattern as a main building block and combines it with ideas and techniques from instance-based learning and rank aggregation. Based on first experimental results for data sets from various domains (sports, education, tourism, etc.), we conclude that our approach is highly competitive. It appears to be specifically interesting in situations in which the objects are coming from different subdomains, and which hence require a kind of knowledge transfer.
Tasks	Learning-To-Rank, Transfer Learning
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10207v1
PDF	http://arxiv.org/pdf/1711.10207v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-rank-based-on-analogical
Repo
Framework

Independently Controllable Factors


Title	Independently Controllable Factors
Authors	Valentin Thomas, Jules Pondard, Emmanuel Bengio, Marc Sarfati, Philippe Beaudoin, Marie-Jean Meurs, Joelle Pineau, Doina Precup, Yoshua Bengio
Abstract	It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.
Tasks
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01289v2
PDF	http://arxiv.org/pdf/1708.01289v2.pdf
PWC	https://paperswithcode.com/paper/independently-controllable-factors
Repo
Framework

Model-Based Multiple Instance Learning


Title	Model-Based Multiple Instance Learning
Authors	Ba-Ngu Vo, Dinh Phung, Quang N. Tran, Ba-Tuong Vo
Abstract	While Multiple Instance (MI) data are point patterns – sets or multi-sets of unordered points – appropriate statistical point pattern models have not been used in MI learning. This article proposes a framework for model-based MI learning using point process theory. Likelihood functions for point pattern data derived from point process theory enable principled yet conceptually transparent extensions of learning tasks, such as classification, novelty detection and clustering, to point pattern data. Furthermore, tractable point pattern models as well as solutions for learning and decision making from point pattern data are developed.
Tasks	Decision Making, Multiple Instance Learning
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02155v2
PDF	http://arxiv.org/pdf/1703.02155v2.pdf
PWC	https://paperswithcode.com/paper/model-based-multiple-instance-learning
Repo
Framework

II-FCN for skin lesion analysis towards melanoma detection


Title	II-FCN for skin lesion analysis towards melanoma detection
Authors	Hongdiao Wen
Abstract	Dermoscopy image detection stays a tough task due to the weak distinguishable property of the object.Although the deep convolution neural network signifigantly boosted the performance on prevelance computer vision tasks in recent years,there remains a room to explore more robust and precise models to the problem of low contrast image segmentation.Towards the challenge of Lesion Segmentation in ISBI 2017,we built a symmetrical identity inception fully convolution network which is based on only 10 reversible inception blocks,every block composed of four convolution branches with combination of different layer depth and kernel size to extract sundry semantic features.Then we proposed an approximate loss function for jaccard index metrics to train our model.To overcome the drawbacks of traditional convolution,we adopted the dilation convolution and conditional random field method to rectify our segmentation.We also introduced multiple ways to prevent the problem of overfitting.The experimental results shows that our model achived jaccard index of 0.82 and kept learning from epoch to epoch.
Tasks	Lesion Segmentation
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08699v2
PDF	http://arxiv.org/pdf/1702.08699v2.pdf
PWC	https://paperswithcode.com/paper/ii-fcn-for-skin-lesion-analysis-towards
Repo
Framework

Delineation of line patterns in images using B-COSFIRE filters


Title	Delineation of line patterns in images using B-COSFIRE filters
Authors	Nicola Strisciuglio, Nicolai Petkov
Abstract	Delineation of line patterns in images is a basic step required in various applications such as blood vessel detection in medical images, segmentation of rivers or roads in aerial images, detection of cracks in walls or pavements, etc. In this paper we present trainable B-COSFIRE filters, which are a model of some neurons in area V1 of the primary visual cortex, and apply it to the delineation of line patterns in different kinds of images. B-COSFIRE filters are trainable as their selectivity is determined in an automatic configuration process given a prototype pattern of interest. They are configurable to detect any preferred line structure (e.g. segments, corners, cross-overs, etc.), so usable for automatic data representation learning. We carried out experiments on two data sets, namely a line-network data set from INRIA and a data set of retinal fundus images named IOSTAR. The results that we achieved confirm the robustness of the proposed approach and its effectiveness in the delineation of line structures in different kinds of images.
Tasks	Representation Learning
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07438v1
PDF	http://arxiv.org/pdf/1707.07438v1.pdf
PWC	https://paperswithcode.com/paper/delineation-of-line-patterns-in-images-using
Repo
Framework

Human Skin Detection Using RGB, HSV and YCbCr Color Models


Title	Human Skin Detection Using RGB, HSV and YCbCr Color Models
Authors	S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, J. Jatakia
Abstract	Human Skin detection deals with the recognition of skin-colored pixels and regions in a given image. Skin color is often used in human skin detection because it is invariant to orientation and size and is fast to process. A new human skin detection algorithm is proposed in this paper. The three main parameters for recognizing a skin pixel are RGB (Red, Green, Blue), HSV (Hue, Saturation, Value) and YCbCr (Luminance, Chrominance) color models. The objective of proposed algorithm is to improve the recognition of skin pixels in given images. The algorithm not only considers individual ranges of the three color parameters but also takes into ac- count combinational ranges which provide greater accuracy in recognizing the skin area in a given image.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02694v1
PDF	http://arxiv.org/pdf/1708.02694v1.pdf
PWC	https://paperswithcode.com/paper/human-skin-detection-using-rgb-hsv-and-ycbcr
Repo
Framework