January 28, 2020

2736 words 13 mins read

Paper Group ANR 1050

3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories. Image retrieval approach based on local texture information derived from predefined patterns and spatial domain information. A Double Residual Compression Algorithm for Efficient Distributed Learning. Multi-User MABs with User Dependent …

3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories


Title	3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories
Authors	Mohammad Bavandpour, Shubham Sahay, Mohammad Reza Mahmoodi, Dmitri B. Strukov
Abstract	The first contribution of this paper is the development of extremely dense, energy-efficient mixed-signal vector-by-matrix-multiplication (VMM) circuits based on the existing 3D-NAND flash memory blocks, without any need for their modification. Such compatibility is achieved using time-domain-encoded VMM design. Our detailed simulations have shown that, for example, the 5-bit VMM of 200-element vectors, using the commercially available 64-layer gate-all-around macaroni-type 3D-NAND memory blocks designed in the 55-nm technology node, may provide an unprecedented area efficiency of 0.14 um2/byte and energy efficiency of ~10 fJ/Op, including the input/output and other peripheral circuitry overheads. Our second major contribution is the development of 3D-aCortex, a multi-purpose neuromorphic inference processor that utilizes the proposed 3D-VMM blocks as its core processing units. We have performed rigorous performance simulations of such a processor on both circuit and system levels, taking into account non-idealities such as drain-induced barrier lowering, capacitive coupling, charge injection, parasitics, process variations, and noise. Our modeling of the 3D-aCortex performing several state-of-the-art neuromorphic-network benchmarks has shown that it may provide the record-breaking storage efficiency of 4.34 MB/mm2, the peak energy efficiency of 70.43 TOps/J, and the computational throughput up to 10.66 TOps/s. The storage efficiency can be further improved seven-fold by aggressively sharing VMM peripheral circuits at the cost of slight decrease in energy efficiency and throughput.
Tasks
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02472v1
PDF	https://arxiv.org/pdf/1908.02472v1.pdf
PWC	https://paperswithcode.com/paper/3d-acortex-an-ultra-compact-energy-efficient
Repo
Framework

Image retrieval approach based on local texture information derived from predefined patterns and spatial domain information


Title	Image retrieval approach based on local texture information derived from predefined patterns and spatial domain information
Authors	Nazgol Hor, Shervan Fekri-Ershad
Abstract	With the development of Information technology and communication, a large part of the databases is dedicated to images and videos. Thus retrieving images related to a query image from a large database has become an important area of research in computer vision. Until now, there are various methods of image retrieval that try to define image contents by texture, color or shape properties. In this paper, a method is presented for image retrieval based on a combination of local texture information derived from two different texture descriptors. First, the color channels of the input image are separated. The texture information is extracted using two descriptors such as evaluated local binary patterns and predefined pattern units. After extracting the features, the similarity matching is done based on distance criteria. The performance of the proposed method is evaluated in terms of precision and recall on the Simplicity database. The comparative results showed that the proposed approach offers higher precision rate than many known methods.
Tasks	Image Retrieval
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12978v1
PDF	https://arxiv.org/pdf/1912.12978v1.pdf
PWC	https://paperswithcode.com/paper/image-retrieval-approach-based-on-local
Repo
Framework

A Double Residual Compression Algorithm for Efficient Distributed Learning


Title	A Double Residual Compression Algorithm for Efficient Distributed Learning
Authors	Xiaorui Liu, Yao Li, Jiliang Tang, Ming Yan
Abstract	Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms. However, the communication cost of gradient aggregation and model synchronization between the master and worker nodes becomes the major obstacle for efficient learning as the number of workers and the dimension of the model increase. In this paper, we propose DORE, a DOuble REsidual compression stochastic gradient descent algorithm, to reduce over $95%$ of the overall communication such that the obstacle can be immensely mitigated. Our theoretical analyses demonstrate that the proposed strategy has superior convergence properties for both strongly convex and nonconvex objective functions. The experimental results validate that DORE achieves the best communication efficiency while maintaining similar model accuracy and convergence speed in comparison with start-of-the-art baselines.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07561v1
PDF	https://arxiv.org/pdf/1910.07561v1.pdf
PWC	https://paperswithcode.com/paper/a-double-residual-compression-algorithm-for
Repo
Framework

Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access


Title	Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access
Authors	Akshayaa Magesh, Venugopal V. Veeravalli
Abstract	Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems. In this paper we consider the scenario where users cannot communicate with each other. In addition, the environment may appear differently to different users, ${i.e.}$, the mean rewards as observed by different users for the same channel may be different. With this setup, we present a policy that achieves a regret of $O (\log{T})$. This paper has been accepted at Asilomar Conference on Signals, Systems, and Computers 2019.
Tasks	Multi-Armed Bandits
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09091v3
PDF	https://arxiv.org/pdf/1910.09091v3.pdf
PWC	https://paperswithcode.com/paper/multi-user-mabs-with-user-dependent-rewards
Repo
Framework

Attending the Emotions to Detect Online Abusive Language


Title	Attending the Emotions to Detect Online Abusive Language
Authors	Niloofar Safi Samghabadi, Afsheen Hatami, Mahsa Shafaei, Sudipta Kar, Thamar Solorio
Abstract	In recent years, abusive behavior has become a serious issue in online social networks. In this paper, we present a new corpus from a semi-anonymous social media platform, which contains the instances of offensive and neutral classes. We introduce a single deep neural architecture that considers both local and sequential information from the text in order to detect abusive language. Along with this model, we introduce a new attention mechanism called emotion-aware attention. This mechanism utilizes the emotions behind the text to find the most important words within that text. We experiment with this model on our dataset and later present the analysis. Additionally, we evaluate our proposed method on different corpora and show new state-of-the-art results with respect to offensive language detection.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03100v1
PDF	https://arxiv.org/pdf/1909.03100v1.pdf
PWC	https://paperswithcode.com/paper/attending-the-emotions-to-detect-online
Repo
Framework

Learning a Unified Embedding for Visual Search at Pinterest


Title	Learning a Unified Embedding for Visual Search at Pinterest
Authors	Andrew Zhai, Hao-Yu Wu, Eric Tzeng, Dong Huk Park, Charles Rosenberg
Abstract	At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for shopping. In this work we describe a multi-task deep metric learning system to learn a single unified image embedding which can be used to power our multiple visual search products. The solution we present not only allows us to train for multiple application objectives in a single deep neural network architecture, but takes advantage of correlated information in the combination of all training data from each application to generate a unified embedding that outperforms all specialized embeddings previously deployed for each product. We discuss the challenges of handling images from different domains such as camera photos, high quality web images, and clean product catalog images. We also detail how to jointly train for multiple product objectives and how to leverage both engagement data and human labeled data. In addition, our trained embeddings can also be binarized for efficient storage and retrieval without compromising precision and recall. Through comprehensive evaluations on offline metrics, user studies, and online A/B experiments, we demonstrate that our proposed unified embedding improves both relevance and engagement of our visual search products for both browsing and searching purposes when compared to existing specialized embeddings. Finally, the deployment of the unified embedding at Pinterest has drastically reduced the operation and engineering cost of maintaining multiple embeddings while improving quality.
Tasks	Metric Learning, Recommendation Systems
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01707v1
PDF	https://arxiv.org/pdf/1908.01707v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-unified-embedding-for-visual
Repo
Framework

Learning by Active Nonlinear Diffusion


Title	Learning by Active Nonlinear Diffusion
Authors	Mauro Maggioni, James M. Murphy
Abstract	This article proposes an active learning method for high dimensional data, based on intrinsic data geometries learned through diffusion processes on graphs. Diffusion distances are used to parametrize low-dimensional structures on the dataset, which allow for high-accuracy labelings of the dataset with only a small number of carefully chosen labels. The geometric structure of the data suggests regions that have homogeneous labels, as well as regions with high label complexity that should be queried for labels. The proposed method enjoys theoretical performance guarantees on a general geometric data model, in which clusters corresponding to semantically meaningful classes are permitted to have nonlinear geometries, high ambient dimensionality, and suffer from significant noise and outlier corruption. The proposed algorithm is implemented in a manner that is quasilinear in the number of unlabeled data points, and exhibits competitive empirical performance on synthetic datasets and real hyperspectral remote sensing images.
Tasks	Active Learning
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12989v1
PDF	https://arxiv.org/pdf/1905.12989v1.pdf
PWC	https://paperswithcode.com/paper/learning-by-active-nonlinear-diffusion
Repo
Framework

“Hang in There”: Lexical and Visual Analysis to Identify Posts Warranting Empathetic Responses


Title	“Hang in There”: Lexical and Visual Analysis to Identify Posts Warranting Empathetic Responses
Authors	Mimansa Jaiswal, Sairam Tabibu, Erik Cambria
Abstract	In the past few years, social media has risen as a platform where people express and share personal incidences about abuse, violence and mental health issues. There is a need to pinpoint such posts and learn the kind of response expected. For this purpose, we understand the sentiment that a personal story elicits on different posts present on different social media sites, on the topics of abuse or mental health. In this paper, we propose a method supported by hand-crafted features to judge if the post requires an empathetic response. The model is trained upon posts from various web-pages and corresponding comments, on both the captions and the images. We were able to obtain 80% accuracy in tagging posts requiring empathetic responses.
Tasks
Published	2019-03-12
URL	http://arxiv.org/abs/1903.05210v1
PDF	http://arxiv.org/pdf/1903.05210v1.pdf
PWC	https://paperswithcode.com/paper/hang-in-there-lexical-and-visual-analysis-to
Repo
Framework

Broad Learning System Based on Maximum Correntropy Criterion


Title	Broad Learning System Based on Maximum Correntropy Criterion
Authors	Yunfei Zheng, Badong Chen, Senior Member, IEEE, Shiyuan Wang, Senior Member, IEEE, Weiqun Wang, Member, IEEE
Abstract	As an effective and efficient discriminative learning method, Broad Learning System (BLS) has received increasing attention due to its outstanding performance in various regression and classification problems. However, the standard BLS is derived under the minimum mean square error (MMSE) criterion, which is, of course, not always a good choice due to its sensitivity to outliers. To enhance the robustness of BLS, we propose in this work to adopt the maximum correntropy criterion (MCC) to train the output weights, obtaining a correntropy based broad learning system (C-BLS). Thanks to the inherent superiorities of MCC, the proposed C-BLS is expected to achieve excellent robustness to outliers while maintaining the original performance of the standard BLS in Gaussian or noise-free environment. In addition, three alternative incremental learning algorithms, derived from a weighted regularized least-squares solution rather than pseudoinverse formula, for C-BLS are developed.With the incremental learning algorithms, the system can be updated quickly without the entire retraining process from the beginning, when some new samples arrive or the network deems to be expanded. Experiments on various regression and classification datasets are reported to demonstrate the desirable performance of the new methods.
Tasks
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11368v1
PDF	https://arxiv.org/pdf/1912.11368v1.pdf
PWC	https://paperswithcode.com/paper/broad-learning-system-based-on-maximum
Repo
Framework

Tighter Theory for Local SGD on Identical and Heterogeneous Data


Title	Tighter Theory for Local SGD on Identical and Heterogeneous Data
Authors	Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik
Abstract	We provide a new analysis of local SGD, removing unnecessary assumptions and elaborating on the difference between two data regimes: identical and heterogeneous. In both cases, we improve the existing theory and provide values of the optimal stepsize and optimal number of local iterations. Our bounds are based on a new notion of variance that is specific to local SGD methods with different data. The tightness of our results is guaranteed by recovering known statements when we plug $H=1$, where $H$ is the number of local steps. The empirical evidence further validates the severe impact of data heterogeneity on the performance of local SGD.
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04746v3
PDF	https://arxiv.org/pdf/1909.04746v3.pdf
PWC	https://paperswithcode.com/paper/better-communication-complexity-for-local-sgd
Repo
Framework

Learning for Safety-Critical Control with Control Barrier Functions


Title	Learning for Safety-Critical Control with Control Barrier Functions
Authors	Andrew Taylor, Andrew Singletary, Yisong Yue, Aaron Ames
Abstract	Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10099v1
PDF	https://arxiv.org/pdf/1912.10099v1.pdf
PWC	https://paperswithcode.com/paper/learning-for-safety-critical-control-with
Repo
Framework

A Hybrid Framework for Topic Structure using Laughter Occurrences


Title	A Hybrid Framework for Topic Structure using Laughter Occurrences
Authors	Sucheta Ghosh
Abstract	Conversational discourse coherence depends on both linguistic and paralinguistic phenomena. In this work we combine both paralinguistic and linguistic knowledge into a hybrid framework through a multi-level hierarchy. Thus it outputs the discourse-level topic structures. The laughter occurrences are used as paralinguistic information from the multiparty meeting transcripts of ICSI database. A clustering-based algorithm is proposed that chose the best topic-segment cluster from two independent, optimized clusters, namely, hierarchical agglomerative clustering and $K$-medoids. Then it is iteratively hybridized with an existing lexical cohesion based Bayesian topic segmentation framework. The hybrid approach improves the performance of both of the stand-alone approaches. This leads to the brief study of interactions between topic structures with discourse relational structure. This training-free topic structuring approach can be applicable to online understanding of spoken dialogs.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/2001.00573v1
PDF	https://arxiv.org/pdf/2001.00573v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-framework-for-topic-structure-using
Repo
Framework

Correspondent Banking Networks: Theory and Experiment


Title	Correspondent Banking Networks: Theory and Experiment
Authors	Nima Safaei, Ivan A. Sergienko
Abstract	We employ the mathematical programming approach in conjunction with the graph theory to study the structure of correspondent banking networks. Optimizing the network requires decisions to be made to onboard, terminate or restrict the bank relationships to optimize the size and overall risk of the network. This study provides theoretical foundation to detect the components, the removal of which does not affect some key properties of the network such as connectivity and diameter. We find that the correspondent banking networks have a feature we call k-accessibility, which helps to drastically reduce the computational burden required for finding the above mentioned components. We prove a number of fundamental theorems related to k-accessible directed graphs, which should be also applicable beyond the particular problem of financial networks. The theoretical findings are verified through the data from a large international bank.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02262v2
PDF	https://arxiv.org/pdf/1912.02262v2.pdf
PWC	https://paperswithcode.com/paper/correspondent-banking-networks-theory-and
Repo
Framework

Integrating Automated Play in Level Co-Creation


Title	Integrating Automated Play in Level Co-Creation
Authors	Andrew Hoyt, Matthew Guzdial, Yalini Kumar, Gillian Smith, Mark O. Riedl
Abstract	In level co-creation an AI and human work together to create a video game level. One open challenge in level co-creation is how to empower human users to ensure particular qualities of the final level, such as challenge. There has been significant prior research into automated pathing and automated playtesting for video game levels, but not in how to incorporate these into tools. In this demonstration we present an improvement of the Morai Maker mixed-initiative level editor for Super Mario Bros. that includes automated pathing and challenge approximation features.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09219v1
PDF	https://arxiv.org/pdf/1911.09219v1.pdf
PWC	https://paperswithcode.com/paper/integrating-automated-play-in-level-co
Repo
Framework

CNN-based synthesis of realistic high-resolution LiDAR data


Title	CNN-based synthesis of realistic high-resolution LiDAR data
Authors	Larissa T. Triess, David Peter, Christoph B. Rist, Markus Enzweiler, J. Marius Zöllner
Abstract	This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our generated output with real-world sensor data by applying a perceptual loss. In large-scale experiments on real-world datasets, we evaluate both the geometric accuracy and semantic segmentation performance using our generated data vs. ground truth. In a mean opinion score testing we further assess the perceptual quality of our generated point clouds. Our results demonstrate a significant quantitative and qualitative improvement in both geometry and semantics over traditional non CNN-based up-sampling methods.
Tasks	Semantic Segmentation
Published	2019-06-28
URL	https://arxiv.org/abs/1907.00787v1
PDF	https://arxiv.org/pdf/1907.00787v1.pdf
PWC	https://paperswithcode.com/paper/cnn-based-synthesis-of-realistic-high
Repo
Framework