July 28, 2019

3081 words 15 mins read

Paper Group ANR 365

Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning. Task-driven Visual Saliency and Attention-based Visual Question Answering. An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition. Efficient Diverse Ensemble for Discriminative Co-Tracking. M2D: Monolog to Di …

Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning


Title	Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning
Authors	Georgios Detorakis, Sadique Sheik, Charles Augustine, Somnath Paul, Bruno U. Pedroni, Nikil Dutt, Jeffrey Krichmar, Gert Cauwenberghs, Emre Neftci
Abstract	Embedded, continual learning for autonomous and adaptive behavior is a key application of neuromorphic hardware. However, neuromorphic implementations of embedded learning at large scales that are both flexible and efficient have been hindered by a lack of a suitable algorithmic framework. As a result, the most neuromorphic hardware is trained off-line on large clusters of dedicated processors or GPUs and transferred post hoc to the device. We address this by introducing the neural and synaptic array transceiver (NSAT), a neuromorphic computational framework facilitating flexible and efficient embedded learning by matching algorithmic requirements and neural and synaptic dynamics. NSAT supports event-driven supervised, unsupervised and reinforcement learning algorithms including deep learning. We demonstrate the NSAT in a wide range of tasks, including the simulation of Mihalas-Niebur neuron, dynamic neural fields, event-driven random back-propagation for event-based deep learning, event-based contrastive divergence for unsupervised learning, and voltage-based learning rules for sequence learning. We anticipate that this contribution will establish the foundation for a new generation of devices enabling adaptive mobile systems, wearable devices, and robots with data-driven autonomy.
Tasks	Continual Learning
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10205v3
PDF	http://arxiv.org/pdf/1709.10205v3.pdf
PWC	https://paperswithcode.com/paper/neural-and-synaptic-array-transceiver-a-brain
Repo
Framework

Task-driven Visual Saliency and Attention-based Visual Question Answering


Title	Task-driven Visual Saliency and Attention-based Visual Question Answering
Authors	Yuetan Lin, Zhangyang Pang, Donghui Wang, Yueting Zhuang
Abstract	Visual question answering (VQA) has witnessed great progress since May, 2015 as a classic problem unifying visual and textual data into a system. Many enlightening VQA works explore deep into the image and question encodings and fusing methods, of which attention is the most effective and infusive mechanism. Current attention based methods focus on adequate fusion of visual and textual features, but lack the attention to where people focus to ask questions about the image. Traditional attention based methods attach a single value to the feature at each spatial location, which losses many useful information. To remedy these problems, we propose a general method to perform saliency-like pre-selection on overlapped region features by the interrelation of bidirectional LSTM (BiLSTM), and use a novel element-wise multiplication based attention method to capture more competent correlation information between visual and textual features. We conduct experiments on the large-scale COCO-VQA dataset and analyze the effectiveness of our model demonstrated by strong empirical results.
Tasks	Question Answering, Visual Question Answering
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06700v1
PDF	http://arxiv.org/pdf/1702.06700v1.pdf
PWC	https://paperswithcode.com/paper/task-driven-visual-saliency-and-attention
Repo
Framework

An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition


Title	An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition
Authors	Neha Bhargava, Subhasis Chaudhuri
Abstract	We present an integrated framework for simultaneous tracking, group detection and multi-level activity recognition in crowd videos. Instead of solving these problems independently and sequentially, we solve them together in a unified framework to utilize the strong correlation that exists among individual motion, groups, and activities. We explore the hierarchical structure hidden in the video that connects individuals over time to produce tracks, connects individuals to form groups and also connects groups together to form a crowd. We show that estimation of this hidden structure corresponds to track association and group detection. We estimate this hidden structure under a linear programming formulation. The obtained graphical representation is further explored to recognize the node values that corresponds to multi-level activity recognition. This problem is solved under a structured SVM framework. The results on publicly available dataset show very competitive performance at all levels of granularity with the state-of-the-art batch processing methods despite the proposed technique being an online (causal) one.
Tasks	Activity Recognition
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11087v1
PDF	http://arxiv.org/pdf/1710.11087v1.pdf
PWC	https://paperswithcode.com/paper/an-integrated-approach-to-crowd-video
Repo
Framework

Efficient Diverse Ensemble for Discriminative Co-Tracking


Title	Efficient Diverse Ensemble for Discriminative Co-Tracking
Authors	Kourosh Meshgi, Shigeyuki Oba, Shin Ishii
Abstract	Ensemble discriminative tracking utilizes a committee of classifiers, to label data samples, which are in turn, used for retraining the tracker to localize the target using the collective knowledge of the committee. Committee members could vary in their features, memory update schemes, or training data, however, it is inevitable to have committee members that excessively agree because of large overlaps in their version space. To remove this redundancy and have an effective ensemble learning, it is critical for the committee to include consistent hypotheses that differ from one-another, covering the version space with minimum overlaps. In this study, we propose an online ensemble tracker that directly generates a diverse committee by generating an efficient set of artificial training. The artificial data is sampled from the empirical distribution of the samples taken from both target and background, whereas the process is governed by query-by-committee to shrink the overlap between classifiers. The experimental results demonstrate that the proposed scheme outperforms conventional ensemble trackers on public benchmarks.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06564v2
PDF	http://arxiv.org/pdf/1711.06564v2.pdf
PWC	https://paperswithcode.com/paper/efficient-diverse-ensemble-for-discriminative
Repo
Framework

M2D: Monolog to Dialog Generation for Conversational Story Telling


Title	M2D: Monolog to Dialog Generation for Conversational Story Telling
Authors	Kevin K. Bowden, Grace I. Lin, Lena I. Reed, Marilyn A. Walker
Abstract	Storytelling serves many different social functions, e.g. stories are used to persuade, share troubles, establish shared values, learn social behaviors, and entertain. Moreover, stories are often told conversationally through dialog, and previous work suggests that information provided dialogically is more engaging than when provided in monolog. In this paper, we present algorithms for converting a deep representation of a story into a dialogic storytelling, that can vary aspects of the telling, including the personality of the storytellers. We conduct several experiments to test whether dialogic storytellings are more engaging, and whether automatically generated variants in linguistic form that correspond to personality differences can be recognized in an extended storytelling dialog.
Tasks
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07476v1
PDF	http://arxiv.org/pdf/1708.07476v1.pdf
PWC	https://paperswithcode.com/paper/m2d-monolog-to-dialog-generation-for
Repo
Framework

Morphology dictates a robot’s ability to ground crowd-proposed language


Title	Morphology dictates a robot’s ability to ground crowd-proposed language
Authors	Zahra Mahoor, Jack Felag, Josh Bongard
Abstract	As more robots act in physical proximity to people, it is essential to ensure they make decisions and execute actions that align with human values. To do so, robots need to understand the true intentions behind human-issued commands. In this paper, we define a safe robot as one that receives a natural-language command from humans, considers an action in response to that command, and accurately predicts how humans will judge that action if is executed in reality. Our contribution is two-fold: First, we introduce a web platform for human users to propose commands to simulated robots. The robots receive commands and act based on those proposed commands, and then the users provide positive and/or negative reinforcement. Next, we train a critic for each robot to predict the crowd’s responses to one of the crowd-proposed commands. Second, we show that the morphology of a robot plays a role in the way it grounds language: The critics show that two of the robots used in the experiment achieve a lower prediction error than the others. Thus, those two robots are safer, according to our definition, since they ground the proposed command more accurately.
Tasks
Published	2017-12-16
URL	http://arxiv.org/abs/1712.05881v2
PDF	http://arxiv.org/pdf/1712.05881v2.pdf
PWC	https://paperswithcode.com/paper/morphology-dictates-a-robots-ability-to
Repo
Framework

Reliability Assessment of Distribution System Using Fuzzy Logic for Modelling of Transformer and Line Uncertainties


Title	Reliability Assessment of Distribution System Using Fuzzy Logic for Modelling of Transformer and Line Uncertainties
Authors	Ahmad Shokrollahi, Hossein Sangrody, Mahdi Motalleb, Mandana Rezaeiahari, Elham Foruzan, Fattah Hassanzadeh
Abstract	Reliability assessment of distribution system, based on historical data and probabilistic methods, leads to an unreliable estimation of reliability indices since the data for the distribution components are usually inaccurate or unavailable. Fuzzy logic is an efficient method to deal with the uncertainty in reliability inputs. In this paper, the ENS index along with other commonly used indices in reliability assessment are evaluated for the distribution system using fuzzy logic. Accordingly, the influential variables on the failure rate and outage duration time of the distribution components, which are natural or human-made, are explained using proposed fuzzy membership functions. The reliability indices are calculated and compared for different cases of the system operations by simulation on the IEEE RBTS Bus 2. The results of simulation show how utilities can significantly improve the reliability of their distribution system by considering the risk of the influential variables.
Tasks
Published	2017-07-11
URL	http://arxiv.org/abs/1707.04506v1
PDF	http://arxiv.org/pdf/1707.04506v1.pdf
PWC	https://paperswithcode.com/paper/reliability-assessment-of-distribution-system
Repo
Framework

A Framework for Super-Resolution of Scalable Video via Sparse Reconstruction of Residual Frames


Title	A Framework for Super-Resolution of Scalable Video via Sparse Reconstruction of Residual Frames
Authors	Mohammad Hossein Moghaddam, Mohammad Javad Azizipour, Saeed Vahidian, Besma Smida
Abstract	This paper introduces a framework for super-resolution of scalable video based on compressive sensing and sparse representation of residual frames in reconnaissance and surveillance applications. We exploit efficient compressive sampling and sparse reconstruction algorithms to super-resolve the video sequence with respect to different compression rates. We use the sparsity of residual information in residual frames as the key point in devising our framework. Moreover, a controlling factor as the compressibility threshold to control the complexity-performance trade-off is defined. Numerical experiments confirm the efficiency of the proposed framework in terms of the compression rate as well as the quality of reconstructed video sequence in terms of PSNR measure. The framework leads to a more efficient compression rate and higher video quality compared to other state-of-the-art algorithms considering performance-complexity trade-offs.
Tasks	Compressive Sensing, Super-Resolution
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09926v1
PDF	http://arxiv.org/pdf/1707.09926v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-super-resolution-of-scalable
Repo
Framework

Topics and Label Propagation: Best of Both Worlds for Weakly Supervised Text Classification


Title	Topics and Label Propagation: Best of Both Worlds for Weakly Supervised Text Classification
Authors	Sachin Pawar, Nitin Ramrakhiyani, Swapnil Hingmire, Girish K. Palshikar
Abstract	We propose a Label Propagation based algorithm for weakly supervised text classification. We construct a graph where each document is represented by a node and edge weights represent similarities among the documents. Additionally, we discover underlying topics using Latent Dirichlet Allocation (LDA) and enrich the document graph by including the topics in the form of additional nodes. The edge weights between a topic and a text document represent level of “affinity” between them. Our approach does not require document level labelling, instead it expects manual labels only for topic nodes. This significantly minimizes the level of supervision needed as only a few topics are observed to be enough for achieving sufficiently high accuracy. The Label Propagation Algorithm is employed on this enriched graph to propagate labels among the nodes. Our approach combines the advantages of Label Propagation (through document-document similarities) and Topic Modelling (for minimal but smart supervision). We demonstrate the effectiveness of our approach on various datasets and compare with state-of-the-art weakly supervised text classification approaches.
Tasks	Text Classification
Published	2017-12-04
URL	http://arxiv.org/abs/1712.02767v1
PDF	http://arxiv.org/pdf/1712.02767v1.pdf
PWC	https://paperswithcode.com/paper/topics-and-label-propagation-best-of-both
Repo
Framework

Product Function Need Recognition via Semi-supervised Attention Network


Title	Product Function Need Recognition via Semi-supervised Attention Network
Authors	Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
Abstract	Functionality is of utmost importance to customers when they purchase products. However, it is unclear to customers whether a product can really satisfy their needs on functions. Further, missing functions may be intentionally hidden by the manufacturers or the sellers. As a result, a customer needs to spend a fair amount of time before purchasing or just purchase the product on his/her own risk. In this paper, we first identify a novel QA corpus that is dense on product functionality information \footnote{The annotated corpus can be found at \url{https://www.cs.uic.edu/~hxu/}.}. We then design a neural network called Semi-supervised Attention Network (SAN) to discover product functions from questions. This model leverages unlabeled data as contextual information to perform semi-supervised sequence labeling. We conduct experiments to show that the extracted function have both high coverage and accuracy, compared with a wide spectrum of baselines.
Tasks
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02186v1
PDF	http://arxiv.org/pdf/1712.02186v1.pdf
PWC	https://paperswithcode.com/paper/product-function-need-recognition-via-semi
Repo
Framework

Block-wise Lensless Compressive Camera


Title	Block-wise Lensless Compressive Camera
Authors	Xin Yuan, Gang Huang, Hong Jiang, Paul Wilford
Abstract	The existing lensless compressive camera ($\text{L}^2\text{C}^2$)~\cite{Huang13ICIP} suffers from low capture rates, resulting in low resolution images when acquired over a short time. In this work, we propose a new regime to mitigate these drawbacks. We replace the global-based compressive sensing used in the existing $\text{L}^2\text{C}^2$ by the local block (patch) based compressive sensing. We use a single sensor for each block, rather than for the entire image, thus forming a multiple but spatially parallel sensor $\text{L}^2\text{C}^2$. This new camera retains the advantages of existing $\text{L}^2\text{C}^2$ while leading to the following additional benefits: 1) Since each block can be very small, {\em e.g.}$~8\times 8$ pixels, we only need to capture $\sim 10$ measurements to achieve reasonable reconstruction. Therefore the capture time can be reduced significantly. 2) The coding patterns used in each block can be the same, therefore the sensing matrix is only of the block size compared to the entire image size in existing $\text{L}^2\text{C}^2$. This saves the memory requirement of the sensing matrix as well as speeds up the reconstruction. 3) Patch based image reconstruction is fast and since real time stitching algorithms exist, we can perform real time reconstruction. 4) These small blocks can be integrated to any desirable number, leading to ultra high resolution images while retaining fast capture rate and fast reconstruction. We develop multiple geometries of this block-wise $\text{L}^2\text{C}^2$ in this paper. We have built prototypes of the proposed block-wise $\text{L}^2\text{C}^2$ and demonstrated excellent results of real data.
Tasks	Compressive Sensing, Image Reconstruction
Published	2017-01-19
URL	http://arxiv.org/abs/1701.05412v1
PDF	http://arxiv.org/pdf/1701.05412v1.pdf
PWC	https://paperswithcode.com/paper/block-wise-lensless-compressive-camera
Repo
Framework

Reservoir Computing using Stochastic p-Bits


Title	Reservoir Computing using Stochastic p-Bits
Authors	Samiran Ganguly, Kerem Y. Camsari, Avik W. Ghosh
Abstract	We present a general hardware framework for building networks that directly implement Reservoir Computing, a popular software method for implementing and training Recurrent Neural Networks and are particularly suited for temporal inferencing and pattern recognition. We provide a specific example of a candidate hardware unit based on a combination of soft-magnets, spin-orbit materials and CMOS transistors that can implement these networks. Efficient non von-Neumann hardware implementation of reservoir computers can open up a pathway for integration of temporal Neural Networks in a wide variety of emerging systems such as Internet of Things (IoTs), industrial controls, bio- and photo-sensors, and self-driving automotives.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10211v1
PDF	http://arxiv.org/pdf/1709.10211v1.pdf
PWC	https://paperswithcode.com/paper/reservoir-computing-using-stochastic-p-bits
Repo
Framework

$A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation


Title	$A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation
Authors	Rakshith Shetty, Bernt Schiele, Mario Fritz
Abstract	Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text’s author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adversarial Author Attribute Anonymity Neural Translation ($A^4NT$), to combat such text-based adversaries. We combine sequence-to-sequence language models used in machine translation and generative adversarial networks to obfuscate author attributes. Unlike machine translation techniques which need paired data, our method can be trained on unpaired corpora of text containing different authors. Importantly, we propose and evaluate techniques to impose constraints on our $A^4NT$ to preserve the semantics of the input text. $A^4NT$ learns to make minimal changes to the input text to successfully fool author attribute classifiers, while aiming to maintain the meaning of the input. We show through experiments on two different datasets and three settings that our proposed method is effective in fooling the author attribute classifiers and thereby improving the anonymity of authors.
Tasks	Machine Translation
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01921v3
PDF	http://arxiv.org/pdf/1711.01921v3.pdf
PWC	https://paperswithcode.com/paper/a4nt-author-attribute-anonymity-by
Repo
Framework

In silico generation of novel, drug-like chemical matter using the LSTM neural network


Title	In silico generation of novel, drug-like chemical matter using the LSTM neural network
Authors	Peter Ertl, Richard Lewis, Eric Martin, Valery Polyakov
Abstract	The exploration of novel chemical spaces is one of the most important tasks of cheminformatics when supporting the drug discovery process. Properly designed and trained deep neural networks can provide a viable alternative to brute-force de novo approaches or various other machine-learning techniques for generating novel drug-like molecules. In this article we present a method to generate molecules using a long short-term memory (LSTM) neural network and provide an analysis of the results, including a virtual screening test. Using the network one million drug-like molecules were generated in 2 hours. The molecules are novel, diverse (contain numerous novel chemotypes), have good physicochemical properties and have good synthetic accessibility, even though these qualities were not specific constraints. Although novel, their structural features and functional groups remain closely within the drug-like space defined by the bioactive molecules from ChEMBL. Virtual screening using the profile QSAR approach confirms that the potential of these novel molecules to show bioactivity is comparable to the ChEMBL set from which they were derived. The molecule generator written in Python used in this study is available on request.
Tasks	Drug Discovery
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07449v2
PDF	http://arxiv.org/pdf/1712.07449v2.pdf
PWC	https://paperswithcode.com/paper/in-silico-generation-of-novel-drug-like
Repo
Framework

The First Evaluation of Chinese Human-Computer Dialogue Technology


Title	The First Evaluation of Chinese Human-Computer Dialogue Technology
Authors	Wei-Nan Zhang, Zhigang Chen, Wanxiang Che, Guoping Hu, Ting Liu
Abstract	In this paper, we introduce the first evaluation of Chinese human-computer dialogue technology. We detail the evaluation scheme, tasks, metrics and how to collect and annotate the data for training, developing and test. The evaluation includes two tasks, namely user intent classification and online testing of task-oriented dialogue. To consider the different sources of the data for training and developing, the first task can also be divided into two sub tasks. Both the two tasks are coming from the real problems when using the applications developed by industry. The evaluation data is provided by the iFLYTEK Corporation. Meanwhile, in this paper, we publish the evaluation results to present the current performance of the participants in the two tasks of Chinese human-computer dialogue technology. Moreover, we analyze the existing problems of human-computer dialogue as well as the evaluation scheme itself.
Tasks	Intent Classification
Published	2017-09-29
URL	https://arxiv.org/abs/1709.10217v2
PDF	https://arxiv.org/pdf/1709.10217v2.pdf
PWC	https://paperswithcode.com/paper/the-first-evaluation-of-chinese-human
Repo
Framework