May 7, 2019

2908 words 14 mins read

Paper Group ANR 29

Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework. Best-Buddies Tracking. Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation. Short-term time series prediction using Hilbert space embeddings of autoregressive processes. Distributed Representations for Biological Sequence …

Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework


Title	Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework
Authors	Linqi Song
Abstract	We study the stream-based online active learning in a contextual multi-armed bandit framework. In this framework, the reward depends on both the arm and the context. In a stream-based active learning setting, obtaining the ground truth of the reward is costly, and the conventional contextual multi-armed bandit algorithm fails to achieve a sublinear regret due to this cost. Hence, the algorithm needs to determine whether or not to request the ground truth of the reward at current time slot. In our framework, we consider a stream-based active learning setting in which a query request for the ground truth is sent to the annotator, together with some prior information of the ground truth. Depending on the accuracy of the prior information, the query cost varies. Our algorithm mainly carries out two operations: the refinement of the context and arm spaces and the selection of actions. In our algorithm, the partitions of the context space and the arm space are maintained for a certain time slots, and then become finer as more information about the rewards accumulates. We use a strategic way to select the arms and to request the ground truth of the reward, aiming to maximize the total reward. We analytically show that the regret is sublinear and in the same order with that of the conventional contextual multi-armed bandit algorithms, where no query cost
Tasks	Active Learning
Published	2016-07-11
URL	http://arxiv.org/abs/1607.03182v1
PDF	http://arxiv.org/pdf/1607.03182v1.pdf
PWC	https://paperswithcode.com/paper/stream-based-online-active-learning-in-a
Repo
Framework

Best-Buddies Tracking


Title	Best-Buddies Tracking
Authors	Shaul Oron, Denis Suhanov, Shai Avidan
Abstract	Best-Buddies Tracking (BBT) applies the Best-Buddies Similarity measure (BBS) to the problem of model-free online tracking. BBS was introduced as a similarity measure between two point sets and was shown to be very effective for template matching. Originally, BBS was designed to work with point sets of equal size, and we propose a modification that lets it handle point sets of different size. The modified BBS is better suited to handle scale changes in the template size, as well as support a variable number of template images. We embed the modified BBS in a particle filter framework and obtain good results on a number of standard benchmarks.
Tasks
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00148v1
PDF	http://arxiv.org/pdf/1611.00148v1.pdf
PWC	https://paperswithcode.com/paper/best-buddies-tracking
Repo
Framework

Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation


Title	Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
Authors	Piotr Antonik, François Duport, Michiel Hermans, Anteo Smerieri, Marc Haelterman, Serge Massar
Abstract	Reservoir Computing is a bio-inspired computing paradigm for processing time dependent signals. The performance of its analogue implementation are comparable to other state of the art algorithms for tasks such as speech recognition or chaotic time series prediction, but these are often constrained by the offline training methods commonly employed. Here we investigated the online learning approach by training an opto-electronic reservoir computer using a simple gradient descent algorithm, programmed on an FPGA chip. Our system was applied to wireless communications, a quickly growing domain with an increasing demand for fast analogue devices to equalise the nonlinear distorted channels. We report error rates up to two orders of magnitude lower than previous implementations on this task. We show that our system is particularly well-suited for realistic channel equalisation by testing it on a drifting and a switching channels and obtaining good performances
Tasks	Speech Recognition, Time Series, Time Series Prediction
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06268v1
PDF	http://arxiv.org/pdf/1610.06268v1.pdf
PWC	https://paperswithcode.com/paper/online-training-of-an-opto-electronic
Repo
Framework

Short-term time series prediction using Hilbert space embeddings of autoregressive processes


Title	Short-term time series prediction using Hilbert space embeddings of autoregressive processes
Authors	Edgar A. Valencia, Mauricio A. Álvarez
Abstract	Linear autoregressive models serve as basic representations of discrete time stochastic processes. Different attempts have been made to provide non-linear versions of the basic autoregressive process, including different versions based on kernel methods. Motivated by the powerful framework of Hilbert space embeddings of distributions, in this paper we apply this methodology for the kernel embedding of an autoregressive process of order $p$. By doing so, we provide a non-linear version of an autoregressive process, that shows increased performance over the linear model in highly complex time series. We use the method proposed for one-step ahead forecasting of different time-series, and compare its performance against other non-linear methods.
Tasks	Time Series, Time Series Prediction
Published	2016-03-16
URL	http://arxiv.org/abs/1603.05060v1
PDF	http://arxiv.org/pdf/1603.05060v1.pdf
PWC	https://paperswithcode.com/paper/short-term-time-series-prediction-using
Repo
Framework

Distributed Representations for Biological Sequence Analysis


Title	Distributed Representations for Biological Sequence Analysis
Authors	Dhananjay Kimothi, Akshay Soni, Pravesh Biyani, James M. Hogan
Abstract	Biological sequence comparison is a key step in inferring the relatedness of various organisms and the functional similarity of their components. Thanks to the Next Generation Sequencing efforts, an abundance of sequence data is now available to be processed for a range of bioinformatics applications. Embedding a biological sequence over a nucleotide or amino acid alphabet in a lower dimensional vector space makes the data more amenable for use by current machine learning tools, provided the quality of embedding is high and it captures the most meaningful information of the original sequences. Motivated by recent advances in the text document embedding literature, we present a new method, called seq2vec, to represent a complete biological sequence in an Euclidean space. The new representation has the potential to capture the contextual information of the original sequence necessary for sequence comparison tasks. We test our embeddings with protein sequence classification and retrieval tasks and demonstrate encouraging outcomes.
Tasks	Document Embedding
Published	2016-08-21
URL	http://arxiv.org/abs/1608.05949v2
PDF	http://arxiv.org/pdf/1608.05949v2.pdf
PWC	https://paperswithcode.com/paper/distributed-representations-for-biological
Repo
Framework

An Analysis System for DNA Gel Electrophoresis Images Based on Automatic Thresholding an Enhancement


Title	An Analysis System for DNA Gel Electrophoresis Images Based on Automatic Thresholding an Enhancement
Authors	Naima Kaabouch, Richard R. Schultz, Barry Milavetz, Lata Balakrishnan
Abstract	Gel electrophoresis, a widely used technique to separate DNA according to their size and weight, generates images that can be analyzed automatically. Manual or semiautomatic image processing presents a bottleneck for further development and leads to reproducibility issues. In this paper, we present a fully automated system with high accuracy for analyzing DNA and proteins. The proposed algorithm consists of four main steps: automatic thresholding, shifting, filtering, and data processing. Automatic thresholding, used to equalize the gray values of the gel electrophoresis image background, is one of the novel operations in this algorithm. Enhancement is also used to improve poor quality images that have faint DNA bands. Experimental results show that the proposed technique eliminates defects due to noise for average quality gel electrophoresis images, while it also improves the quality of poor images.
Tasks
Published	2016-07-03
URL	http://arxiv.org/abs/1607.00589v1
PDF	http://arxiv.org/pdf/1607.00589v1.pdf
PWC	https://paperswithcode.com/paper/an-analysis-system-for-dna-gel
Repo
Framework

Explicablility as Minimizing Distance from Expected Behavior


Title	Explicablility as Minimizing Distance from Expected Behavior
Authors	Anagha Kulkarni, Yantian Zha, Tathagata Chakraborti, Satya Gautam Vadlamudi, Yu Zhang, Subbarao Kambhampati
Abstract	In order to have effective human-AI collaboration, it is necessary to address how the AI agent’s behavior is being perceived by the humans-in-the-loop. When the agent’s task plans are generated without such considerations, they may often demonstrate inexplicable behavior from the human’s point of view. This problem may arise due to the human’s partial or inaccurate understanding of the agent’s planning model. This may have serious implications from increased cognitive load to more serious concerns of safety around a physical agent. In this paper, we address this issue by modeling plan explicability as a function of the distance between a plan that agent makes and the plan that human expects it to make. We learn a regression model for mapping the plan distances to explicability scores of plans and develop an anytime search algorithm that can use this model as a heuristic to come up with progressively explicable plans. We evaluate the effectiveness of our approach in a simulated autonomous car domain and a physical robot domain.
Tasks
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05497v4
PDF	http://arxiv.org/pdf/1611.05497v4.pdf
PWC	https://paperswithcode.com/paper/explicablility-as-minimizing-distance-from
Repo
Framework

Universality of Bayesian mixture predictors


Title	Universality of Bayesian mixture predictors
Authors	Daniil Ryabko
Abstract	The problem is that of sequential probability forecasting for finite-valued time series. The data is generated by an unknown probability distribution over the space of all one-way infinite sequences. It is known that this measure belongs to a given set C, but the latter is completely arbitrary (uncountably infinite, without any structure given). The performance is measured with asymptotic average log loss. In this work it is shown that the minimax asymptotic performance is always attainable, and it is attained by a convex combination of a countably many measures from the set C (a Bayesian mixture). This was previously only known for the case when the best achievable asymptotic error is 0. This also contrasts previous results that show that in the non-realizable case all Bayesian mixtures may be suboptimal, while there is a predictor that achieves the optimal performance.
Tasks	Time Series
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08249v2
PDF	http://arxiv.org/pdf/1610.08249v2.pdf
PWC	https://paperswithcode.com/paper/universality-of-bayesian-mixture-predictors
Repo
Framework

Multi-view Recurrent Neural Acoustic Word Embeddings


Title	Multi-view Recurrent Neural Acoustic Word Embeddings
Authors	Wanjia He, Weiran Wang, Karen Livescu
Abstract	Recent work has begun exploring neural acoustic word embeddings—fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks, where reasoning about whole words may make it possible to avoid ambiguous sub-word representations. The main idea is to map acoustic sequences to fixed-dimensional vectors such that examples of the same word are mapped to similar vectors, while different-word examples are mapped to very different vectors. In this work we take a multi-view approach to learning acoustic word embeddings, in which we jointly learn to embed acoustic sequences and their corresponding character sequences. We use deep bidirectional LSTM embedding models and multi-view contrastive losses. We study the effect of different loss variants, including fixed-margin and cost-sensitive losses. Our acoustic word embeddings improve over previous approaches for the task of word discrimination. We also present results on other tasks that are enabled by the multi-view approach, including cross-view word discrimination and word similarity.
Tasks	Word Embeddings
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04496v2
PDF	http://arxiv.org/pdf/1611.04496v2.pdf
PWC	https://paperswithcode.com/paper/multi-view-recurrent-neural-acoustic-word
Repo
Framework

Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds


Title	Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
Authors	Mark Bun, Thomas Steinke
Abstract	“Concentrated differential privacy” was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Renyi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and raise a few new questions. We also unify this approach with approximate differential privacy by giving an appropriate definition of “approximate concentrated differential privacy.”
Tasks
Published	2016-05-06
URL	http://arxiv.org/abs/1605.02065v1
PDF	http://arxiv.org/pdf/1605.02065v1.pdf
PWC	https://paperswithcode.com/paper/concentrated-differential-privacy
Repo
Framework

Spectral video construction from RGB video: Application to Image Guided Neurosurgery


Title	Spectral video construction from RGB video: Application to Image Guided Neurosurgery
Authors	Md. Abul Hasnat, Jussi Parkkinen, Markku Hauta-Kasari
Abstract	Spectral imaging has received enormous interest in the field of medical imaging modalities. It provides a powerful tool for the analysis of different organs and non-invasive tissues. Therefore, significant amount of research has been conducted to explore the possibility of using spectral imaging in biomedical applications. To observe spectral image information in real time during surgery and monitor the temporal changes in the organs and tissues is a demanding task. Available spectral imaging devices are not sufficient to accomplish this task with an acceptable spatial and spectral resolution. A solution to this problem is to estimate the spectral video from RGB video and perform visualization with the most prominent spectral bands. In this research, we propose a framework to generate neurosurgery spectral video from RGB video. A spectral estimation technique is applied on each RGB video frames. The RGB video is captured using a digital camera connected with an operational microscope dedicated to neurosurgery. A database of neurosurgery spectral images is used to collect training data and evaluate the estimation accuracy. A searching technique is used to identify the best training set. Five different spectrum estimation techniques are experimented to indentify the best method. Although this framework is established for neurosurgery spectral video generation, however, the methodology outlined here would also be applicable to other similar research.
Tasks	Video Generation
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04809v1
PDF	http://arxiv.org/pdf/1612.04809v1.pdf
PWC	https://paperswithcode.com/paper/spectral-video-construction-from-rgb-video
Repo
Framework

Non-Backtracking Spectrum of Degree-Corrected Stochastic Block Models


Title	Non-Backtracking Spectrum of Degree-Corrected Stochastic Block Models
Authors	Lennart Gulikers, Marc Lelarge, Laurent Massoulié
Abstract	Motivated by community detection, we characterise the spectrum of the non-backtracking matrix $B$ in the Degree-Corrected Stochastic Block Model. Specifically, we consider a random graph on $n$ vertices partitioned into two equal-sized clusters. The vertices have i.i.d. weights ${ \phi_u }_{u=1}^n$ with second moment $\Phi^{(2)}$. The intra-cluster connection probability for vertices $u$ and $v$ is $\frac{\phi_u \phi_v}{n}a$ and the inter-cluster connection probability is $\frac{\phi_u \phi_v}{n}b$. We show that with high probability, the following holds: The leading eigenvalue of the non-backtracking matrix $B$ is asymptotic to $\rho = \frac{a+b}{2} \Phi^{(2)}$. The second eigenvalue is asymptotic to $\mu_2 = \frac{a-b}{2} \Phi^{(2)}$ when $\mu_2^2 > \rho$, but asymptotically bounded by $\sqrt{\rho}$ when $\mu_2^2 \leq \rho$. All the remaining eigenvalues are asymptotically bounded by $\sqrt{\rho}$. As a result, a clustering positively-correlated with the true communities can be obtained based on the second eigenvector of $B$ in the regime where $\mu_2^2 > \rho.$ In a previous work we obtained that detection is impossible when $\mu_2^2 < \rho,$ meaning that there occurs a phase-transition in the sparse regime of the Degree-Corrected Stochastic Block Model. As a corollary, we obtain that Degree-Corrected Erd\H{o}s-R'enyi graphs asymptotically satisfy the graph Riemann hypothesis, a quasi-Ramanujan property. A by-product of our proof is a weak law of large numbers for local-functionals on Degree-Corrected Stochastic Block Models, which could be of independent interest.
Tasks	Community Detection
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02487v2
PDF	http://arxiv.org/pdf/1609.02487v2.pdf
PWC	https://paperswithcode.com/paper/non-backtracking-spectrum-of-degree-corrected
Repo
Framework

Beyond Holistic Object Recognition: Enriching Image Understanding with Part States


Title	Beyond Holistic Object Recognition: Enriching Image Understanding with Part States
Authors	Cewu Lu, Hao Su, Yongyi Lu, Li Yi, Chikeung Tang, Leonidas Guibas
Abstract	Important high-level vision tasks such as human-object interaction, image captioning and robotic manipulation require rich semantic descriptions of objects at part level. Based upon previous work on part localization, in this paper, we address the problem of inferring rich semantics imparted by an object part in still images. We propose to tokenize the semantic space as a discrete set of part states. Our modeling of part state is spatially localized, therefore, we formulate the part state inference problem as a pixel-wise annotation problem. An iterative part-state inference neural network is specifically designed for this task, which is efficient in time and accurate in performance. Extensive experiments demonstrate that the proposed method can effectively predict the semantic states of parts and simultaneously correct localization errors, thus benefiting a few visual understanding applications. The other contribution of this paper is our part state dataset which contains rich part-level semantic annotations.
Tasks	Human-Object Interaction Detection, Image Captioning, Object Recognition
Published	2016-12-15
URL	http://arxiv.org/abs/1612.07310v1
PDF	http://arxiv.org/pdf/1612.07310v1.pdf
PWC	https://paperswithcode.com/paper/beyond-holistic-object-recognition-enriching
Repo
Framework

Semi Automatic Color Segmentation of Document Pages


Title	Semi Automatic Color Segmentation of Document Pages
Authors	Stéphane Bres, Véronique Eglin, Vincent Poulain
Abstract	-This paper presents a semi automatic method used to segment color documents into different uniform color plans. The practical application is dedicated to administrative documents segmentation. In these documents, like in many other cases, color has a semantic meaning: it is then possible to identify some specific regions like manual annotations, rubber stamps or colored highlighting. A first step of user-controlled learning of the desired color plans is made on few sample documents. An automatic process can then be performed on the much bigger set as a batch. Our experiments show very interesting results in with a very competitive processing time.
Tasks
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08393v1
PDF	http://arxiv.org/pdf/1609.08393v1.pdf
PWC	https://paperswithcode.com/paper/semi-automatic-color-segmentation-of-document
Repo
Framework

Human Centred Object Co-Segmentation


Title	Human Centred Object Co-Segmentation
Authors	Chenxia Wu, Jiemi Zhang, Ashutosh Saxena, Silvio Savarese
Abstract	Co-segmentation is the automatic extraction of the common semantic regions given a set of images. Different from previous approaches mainly based on object visuals, in this paper, we propose a human centred object co-segmentation approach, which uses the human as another strong evidence. In order to discover the rich internal structure of the objects reflecting their human-object interactions and visual similarities, we propose an unsupervised fully connected CRF auto-encoder incorporating the rich object features and a novel human-object interaction representation. We propose an efficient learning and inference algorithm to allow the full connectivity of the CRF with the auto-encoder, that establishes pairwise relations on all pairs of the object proposals in the dataset. Moreover, the auto-encoder learns the parameters from the data itself rather than supervised learning or manually assigned parameters in the conventional CRF. In the extensive experiments on four datasets, we show that our approach is able to extract the common objects more accurately than the state-of-the-art co-segmentation algorithms.
Tasks	Human-Object Interaction Detection
Published	2016-06-12
URL	http://arxiv.org/abs/1606.03774v1
PDF	http://arxiv.org/pdf/1606.03774v1.pdf
PWC	https://paperswithcode.com/paper/human-centred-object-co-segmentation
Repo
Framework