2023 57th Annual Conference on Information Sciences and Systems (CISS)最新文献

Coarse-Grained High-speed Reconfigurable Array-based Approximate Accelerator for Deep Learning Applications 面向深度学习应用的粗粒度高速可重构阵列近似加速器

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089735

Katherine Mercado, Sathwika Bavikadi, Sai Manoj Pudukotai Dinakarrao

{"title":"Coarse-Grained High-speed Reconfigurable Array-based Approximate Accelerator for Deep Learning Applications","authors":"Katherine Mercado, Sathwika Bavikadi, Sai Manoj Pudukotai Dinakarrao","doi":"10.1109/CISS56502.2023.10089735","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089735","url":null,"abstract":"Deep Neural Networks (DNNs) are widely deployed in various cognitive applications, including computer vision, speech recognition, and image processing. The surpassing accuracy and performance of deep neural networks come at the cost of high computational complexity. Therefore, software implementations of DNNs and Convolutional Neural Networks (CNNs) are often hindered by computational and communication bottlenecks. As a panacea, numerous hardware accelerators have been introduced in recent times to accelerate DNNs and CNNs. Despite effectiveness, the existing hardware accelerators are often confronted by the involved computational complexity and the need for special hardware units to implement each of the DNN/CNN operations. To address such challenges, a reconfigurable DNN/CNN accelerator is proposed in this work. The proposed architecture comprises nine processing elements (PEs) that can perform both convolution and arithmetic operations through run-time reconfiguration and with minimal overhead. To reduce the computational complexity, we employ Mitchell's algorithm, which is supported through low overhead coarse-grained reconfigurability in this work. To facilitate efficient data flow across the PEs, we pre-compute the dataflow paths and configure the dataflow during the run-time. The proposed design is realized on a field-programmable gate array (FPGA) platform for evaluation. The proposed evaluation indicates 1.26x lower resource utilization compared to the state-of-the-art DNN/CNN accelerators and also achieves 99.43% and 82% accuracy on MNIST and CIFAR-10 datasets, respectively.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121003863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-efficient Edge Approximation for Connected Vehicular Services 车联网服务的节能边缘逼近

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089724

Dewant Katare, A. Ding

引用次数: 0

Feasibility of Regression Modeling and Biomarker Analysis for Epileptic Seizure Prediction 回归模型和生物标志物分析在癫痫发作预测中的可行性

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089755

Dominique L. Tanner, M. Privitera, Marepalli Rao

引用次数: 0

AI/ML Systems Engineering Workbench Framework AI/ML系统工程工作台框架

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089781

K. Nyarko, Peter O. Taiwo, Chukwuemeka Duru, Emmanual Masa-Ibi

{"title":"AI/ML Systems Engineering Workbench Framework","authors":"K. Nyarko, Peter O. Taiwo, Chukwuemeka Duru, Emmanual Masa-Ibi","doi":"10.1109/CISS56502.2023.10089781","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089781","url":null,"abstract":"This paper presents the framework of a cloud-based Artificial Intelligence (AI) and Machine Learning (ML) workbench that provides services utilization and performance benchmarking. The framework promotes convenience by enabling a centralized platform for software developers and data scientists to perform federated search across various dataset repositories, choose problem domains, like Natural Language Processing, Speech and Computer Vision, and build/validate models. The benchmarking functionality of this framework helps users evaluate and compare performances of various solutions from multiple cloud service providers. The workbench framework consists of two primary layers. The Services layer which is rendered as an AI as a service (AIaaS) model, providing interfaces that connect users to vision, speech and natural language processing (NLP) services from various AI service providers. The Platform layer is an ML as a Service (MLaaS) model providing access to ML model training, tuning, inference and transfer learning tasks that are fulfillable on multiple cloud ML platforms with preset cloud-based compute instances. Benchmarking is provided on the workbench by comparing accuracy metrics on prediction and detection counts, F1 scores and ML training instances setup and completion time. By utilizing these performance benchmarking features, this framework can assist AI and ML practitioners in making informed judgments when selecting a cloud provider for specific activities. Additionally, it will increase the effectiveness and efficiency of data science training for both teachers and students.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124750984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

C-DIEGO: An Algorithm with Near-Optimal Sample Complexity for Distributed, Streaming PCA 分布式流PCA的近最优样本复杂度算法

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089668

Muhammad Zulqarnain, Arpita Gang, W. Bajwa

{"title":"C-DIEGO: An Algorithm with Near-Optimal Sample Complexity for Distributed, Streaming PCA","authors":"Muhammad Zulqarnain, Arpita Gang, W. Bajwa","doi":"10.1109/CISS56502.2023.10089668","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089668","url":null,"abstract":"The accuracy of many downstream machine learning algorithms is tied to the training data having uncorrelated features. With the modern-day data often being streaming in nature, geographically distributed, and having large dimensions, it is paramount to apply both uncorrelated feature learning and dimensionality reduction techniques in this scenario. Principal Component Analysis (PCA) is a state-of-the-art tool that simultaneously yields uncorrelated features and reduces data dimensions by projecting data onto the eigenvectors of the population covariance matrix. This paper introduces a novel algorithm called Consensus-DIstributEd Generalized Oja (C-DIEGO), which is based on Oja's method, to estimate the dominant eigenvector of a population covariance matrix in a distributed, streaming setting. The algorithm considers a distributed network of arbitrarily connected nodes without a central coordinator and assumes data samples continuously arrive at the individual nodes in a streaming manner. It is established in the paper that C-DIEGO can achieve an order-optimal convergence rate if nodes in the network are allowed to have enough consensus rounds per algorithmic iteration. Numerical results are also reported in the paper that showcase the efficacy of the proposed algorithm.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129678443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Search for Extraterrestrial Intelligence as One-Shot Hypothesis Testing 寻找外星智慧作为一次性假设检验

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089645

Ian George, Xinan Chen, L. Varshney

{"title":"Search for Extraterrestrial Intelligence as One-Shot Hypothesis Testing","authors":"Ian George, Xinan Chen, L. Varshney","doi":"10.1109/CISS56502.2023.10089645","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089645","url":null,"abstract":"Both the search for extraterrestrial intelligence (SETI) and messaging extraterrestrial intelligence (METI) struggle with a strong indeterminacy in what data to look for and when to do so. This has led to attempts at finding both fundamental mathematical limits for SETI as well as benchmarks regarding specific signals. Due to the natural correspondence, previous information-theoretic work has been formulated in terms of communication between extraterrestrial and human civilizations. In this work, we instead formalize SETI as a detection problem, specifically (quantum) one-shot asymmetric hypothesis testing. This framework holds for all detection scenarios-in particular, it is relevant for detection of any technosignature, including quantum mechanical signals. To the best of our knowledge, this is the first work to consider the applicability of SETI for quantum signals. Using this formalism, we are able to unify the analysis of fundamental limits and benchmarking specific signals. To show a distinction between METI and SETI, we show that significantly weaker signals may be useful in detection in comparison to communication. Furthermore, the framework is computationally efficient, so it can be implemented by practicing astrobiologists.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120891732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inducing Dynamic Group Sparsity on Vagus Nerve Recordings 迷走神经记录诱导动态组稀疏性

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089732

Khaled Aboumerhi, Ralph Etienne-Cummings

{"title":"Inducing Dynamic Group Sparsity on Vagus Nerve Recordings","authors":"Khaled Aboumerhi, Ralph Etienne-Cummings","doi":"10.1109/CISS56502.2023.10089732","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089732","url":null,"abstract":"As recording electrodes improve with higher spatial resolution, the large amount of incoming data is becoming difficult to handle on low-resource medical technologies, such as implantable devices. Processing each data sample is costly in terms of energy, memory allocation, bandwidth transmission and more. Accurate neural compression has thus become important in reducing the amount of data that needs to be processed, whether to an implantable device or a distant computer. Compression algorithms, such as EI balance networks, have been successfully implemented, but rely on the physical structure of neurons to have many connections, such as in the cortex. This structure does not exist in the peripheral nervous system and so cannot be accurately deployed. In this paper, we employ dynamic group sparsity (DGS) on two different nerve recording datasets to demonstrate intelligent compression schemes while retaining signal representation. DGS does not require structural connections, but instead assumes that neurons fire in groups. We assume that there is structure among neuron groups that fire sparsely, both spatially and temporally. We show that under certain conditions, DGS achieves 5x compression while retaining 99.2% signal integrity. We then compare these results to typical matching pursuit algorithms, such as OMP and CoSaMP, and conclude with future implementations of DGS in post-acquisition nerve recordings.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128096250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Particle Thompson Sampling with Static Particles 粒子汤普森采样与静态粒子

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089653

Zeyu Zhou, B. Hajek

引用次数: 1

Information-Directed Policy Search in Sparse-Reward Settings via the Occupancy Information Ratio 基于占用信息比的稀疏奖励环境下信息导向策略搜索

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089655

Wesley A. Suttle, Alec Koppel, Ji Liu

引用次数: 0

A Comprehensive Study of Gradient Inversion Attacks in Federated Learning and Baseline Defense Strategies 梯度反转攻击在联邦学习和基线防御策略中的综合研究

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089719

Pretom Roy Ovi, A. Gangopadhyay

{"title":"A Comprehensive Study of Gradient Inversion Attacks in Federated Learning and Baseline Defense Strategies","authors":"Pretom Roy Ovi, A. Gangopadhyay","doi":"10.1109/CISS56502.2023.10089719","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089719","url":null,"abstract":"With a greater emphasis on data confidentiality and legislation, collaborative machine learning algorithms are being developed to protect sensitive private data. Federated learning (FL) is the most popular of these methods, and FL enables collaborative model construction among a large number of users without the requirement for explicit data sharing. Because FL models are built in a distributed manner with gradient sharing protocol, they are vulnerable to “gradient inversion attacks,” where sensitive training data is extracted from raw gradients. Gradient inversion attacks to reconstruct data are regarded as one of the wickedest privacy risks in FL, as attackers covertly spy gradient updates and backtrack from the gradients to obtain information about the raw data without compromising model training quality. Even without prior knowledge about the private data, the attacker can breach the secrecy and confidentiality of the training data via the intermediate gradients. Existing FL training protocol have been proven to exhibit vulnerabilities that can be exploited by adversaries both within and outside the system to compromise data privacy. Thus, it is critical to make FL system designers aware of the implications of future FL algorithm design on privacy preservation. Motivated by this, our work focuses on exploring the data confidentiality and integrity in FL, where we emphasize the intuitions, approaches, and fundamental assumptions used by the existing strategies of gradient inversion attacks to retrieve the data. Then we examine the limitations of different approaches and evaluate their qualitative performance in retrieving raw data. Furthermore, we assessed the effectiveness of baseline defense mechanisms against these attacks for robust privacy preservation in FL.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133742875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1