2023 57th Annual Conference on Information Sciences and Systems (CISS)最新文献_第8页

Architecture Analysis for Symmetric Simplicial Deep Neural Networks on Chip 芯片上对称简单深度神经网络的结构分析

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089667

N. Rodríguez, M. Villemur, P. Julián

引用次数: 0

Towards an Improved Hyperdimensional Classifier for Event-Based Data 基于事件数据的改进超维分类器

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089705

Neal Anwar, Chethan Parameshwara, C. Fermüller, Y. Aloimonos

{"title":"Towards an Improved Hyperdimensional Classifier for Event-Based Data","authors":"Neal Anwar, Chethan Parameshwara, C. Fermüller, Y. Aloimonos","doi":"10.1109/CISS56502.2023.10089705","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089705","url":null,"abstract":"Hyperdimensional Computing (HDC) is an emerging neuroscience-inspired framework wherein data of various modalities can be represented uniformly $text{in}$ high-dimensional space as long, redundant holographic vectors. When equipped with the proper Vector Symbolic Architecture (VSA) and applied to neuromorphic hardware, HDC-based networks have been demonstrated to be capable of solving complex visual tasks with substantial energy efficiency gains and increased robustness to noise when compared to standard Artificial Neural Networks (ANNs). HDC has shown potential to be used with great efficacy for learning based on spatiotemporal data from neuromorphic sensors such as the Dynamic Vision Sensor (DVS), but prior work has been limited in this arena due to the complexity and unconventional nature of this type of data as well as difficulty choosing the appropriate VSA to hypervectorize spatiotemporal information. We present a bipolar HD encoding mechanism designed for encoding spatiotemporal data, which captures the contours of DVS-generated time surfaces created by moving objects by fitting to them local surfaces which are individually encoded into HD vectors and bundled into descriptive high-dimensional representations. We conclude with a sketch of the structure and training/inference pipelines associated with an HD classifier, predicated on our proposed HD encoding scheme, trained for the complex real-world task of pose estimation from event camera data.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"44 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":"127600079","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

Teaching Reinforcement Learning Agents via Reinforcement Learning 通过强化学习教学强化学习代理

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089695

Kun Yang, Chengshuai Shi, Cong Shen

{"title":"Teaching Reinforcement Learning Agents via Reinforcement Learning","authors":"Kun Yang, Chengshuai Shi, Cong Shen","doi":"10.1109/CISS56502.2023.10089695","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089695","url":null,"abstract":"In many real-world reinforcement learning (RL) tasks, the agent who takes the actions often only has partial observations of the environment. On the other hand, a principal may have a complete, system-level view but cannot directly take actions to interact with the environment. Motivated by this agent-principal capability mismatch, we study a novel “teaching” problem where the principal attempts to guide the agent's behavior via implicit adjustment on her observed rewards. Rather than solving specific instances of this problem, we develop a general RL framework for the principal to teach any RL agent without knowing the optimal action a priori. The key idea is to view the agent as part of the environment, and to directly set the reward adjustment as actions such that efficient learning and teaching can be simultaneously accomplished at the principal. This framework is fully adaptive to diverse principal and agent settings (such as heterogeneous agent strategies and adjustment costs), and can adopt a variety of RL algorithms to solve the teaching problem with provable performance guarantees. Extensive experimental results on different RL tasks demonstrate that the proposed framework guarantees a stable convergence and achieves the best tradeoff between rewards and costs among various baseline solutions.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"13 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":"116515709","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

Distributed Policy Gradient with Heterogeneous Computations for Federated Reinforcement Learning 基于异构计算的分布式策略梯度联邦强化学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089771

Ye Zhu, Xiaowen Gong

{"title":"Distributed Policy Gradient with Heterogeneous Computations for Federated Reinforcement Learning","authors":"Ye Zhu, Xiaowen Gong","doi":"10.1109/CISS56502.2023.10089771","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089771","url":null,"abstract":"The rapid advances in federated learning (FL) in the past few years have recently inspired federated reinforcement learning (FRL), where multiple reinforcement learning (RL) agents collaboratively learn a common decision-making policy without exchanging their raw interaction data with their environments. In this paper, we consider a general FRL framework where agents interact with different environments with identical state and action spaces but different rewards and dynamics. Motivated by the fact that agents often have heterogeneous computation capabilities, we propose a Federated Heterogeneous Policy Gradient (FedHPG) algorithm for FRL, where agents can use different numbers of data trajectories (i.e., batch sizes) and different numbers of local computation iterations for their respective PG algorithms. We characterize performance bounds for the learning accuracy of FedHPG, which shows that it achieves a learning accuracy ∊ with sample complexity of $O$ (1/∊2), which matches the performance of existing RL algorithms. The results also show the impacts of local iteration numbers and batch sizes for iteration on the learning accuracy. We also extend FedHPG to heterogeneous policy gradient variance reduction (FedHPGVR) algorithm based on the variance reduction method, and analyze the convergence of this algorithm. The theoretical results are verified empirically for benchmark RL tasks.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"4 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":"114658594","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

Multi-Output Career Prediction: Dataset, Method, and Benchmark Suite 多输出职业预测:数据集，方法和基准套件

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089642

Shruti Singh, Abhijeet Gupta, S. Baraheem, Tam V. Nguyen

引用次数: 0

Greedy Centroid Initialization for Federated K-means 联邦k均值的贪婪质心初始化

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089666

Kun Yang, M. Amiri, Sanjeev R. Kulkarni

{"title":"Greedy Centroid Initialization for Federated K-means","authors":"Kun Yang, M. Amiri, Sanjeev R. Kulkarni","doi":"10.1109/CISS56502.2023.10089666","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089666","url":null,"abstract":"K-means is a widely used data clustering algorithm which aims to partition a set of data points into $K$ clusters through finding the best $K$ centroids representing the data points. Initialization plays a vital role in the traditional centralized K-means clustering algorithm where the clustering is carried out at a central node accessing the entire data points. In this paper, we focus on K-means in a federated setting, where the clients store data locally, and the raw data never leaves the devices. Given the importance of initialization on the federated K-means algorithm, we aim to find better initial centroids by leveraging the local data on each client. To this end, we start the centroid initialization at the clients rather than at the server, which has no information about the clients' data initially. The clients first select their local initial clusters, and they share their clustering information (cluster centroids and sizes) with the server. The server then uses a greedy algorithm to choose the global initial centroids based on the information received from the clients. Numerical results on synthetic and public datasets show that our proposed method can achieve better and more stable performance than three federated K-means variants, and similar performance to the centralized K-means algorithm.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"51 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":"132153656","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

A Machine Learning Approach to Predict the Optical Properties of a Nanocube via Gaussian Process Regression 利用高斯过程回归预测纳米立方体光学性质的机器学习方法

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089714

Ekin Gunes Ozaktas, Alfredo Naef, G. Tagliabue

引用次数: 1

Retinomorphic Channel Design and Considerations 视胚通道设计与考虑

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089617

Jonah P. Sengupta, A. Andreou

{"title":"Retinomorphic Channel Design and Considerations","authors":"Jonah P. Sengupta, A. Andreou","doi":"10.1109/CISS56502.2023.10089617","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089617","url":null,"abstract":"By extrapolating functionality from the retina, retinomorphic engineering has yielded devices that have shown promise to alleviate the challenges presented in modern computer vision tasks. An incredible amount of work has been devoted in recent years to the development and deployment of these event-based vision sensors in applications requiring low-latency, energy-efficient, high dynamic range sensing solutions. However, not much work has been devoted to the area, energy, and speed analysis of the various encoding and decoding mechanisms necessary for sensory pipelines. This paper outlines an empirical framework that presents a clear tradeoff between the various methodologies to transduce physical information in to spikes (encoding) and reconstruct said stimuli from the incident events (decoding). Software-based models of these methodologies were constructed to evaluate the accuracy of stimuli reconstruction for a variety of input profiles. As a result, it is shown that an optimized retinomorphic architecture for a specific set of system-driven cost metrics requires a heterogenous fabric of encoders with a composition of 95% temporal contrast pixels and 5% intensity encoder assuming a temporal jitter of 1μs. Much like the composition of ganglion cells in magno- and parvo-cellular pathway, this multi-modal solution provides the most time, area, and power efficient method to convey visual data.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"5 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":"123815296","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

Langevin Monte Carlo with SPSA-approximated Gradients 具有spsa近似梯度的Langevin Monte Carlo

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089715

Shiqing Sun, J. Spall

引用次数: 0

Decoding EEG Signals with Visibility Graphs to Predict Varying Levels of Mental Workload 用可见性图解码脑电图信号以预测不同程度的脑力负荷

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089662

Arya Teymourlouei, R. Gentili, J. Reggia

{"title":"Decoding EEG Signals with Visibility Graphs to Predict Varying Levels of Mental Workload","authors":"Arya Teymourlouei, R. Gentili, J. Reggia","doi":"10.1109/CISS56502.2023.10089662","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089662","url":null,"abstract":"Recent work in predicting mental workload through EEG analysis has centered around features in the frequency domain. However, these features alone may not be enough to accurately predict mental workload. We propose a graph-based approach that filters EEG channels into five frequency bands. The time series data for each band is transformed into two types of visibility graphs. The natural visibility graph and horizontal visibility graph algorithms are used. Six graph-based features are then calculated which seek to distinguish between EEGs of low and high mental workload. Feature selection is evaluated with statistical tests. The features are fed as input data to two machine learning algorithms which are random forest and neural network. The accuracy of the random forest method is 90%, and the neural network has 86% accuracy. The graphical analysis showed that higher frequency ranges (alpha, beta, gamma) had a stronger ability to classify levels of mental workload. Unexpectedly, the natural visibility graph algorithm had better overall performance. Using the method presented here, accurate classification of MWL using EEG signals can enable the development of robust BCI.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"22 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":"133959293","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