https://community.mis.temple.edu/stalarico/files/2015/03/Final-resumeee.pdf
Samantha Talarico 1098 Spring Street | Old Forge | PA | 18518 | tel: 570.909.7512
https://faculty.cst.temple.edu/~szyld/reports/randCholQR_rev2_report.pdf
Our im-plementation confirms and illustrates the theory developed in this paper. Our secondary contribution is a computational study that tangibly demonstrates that the multisketched algorithm has superior performance over the existing single sketch algorithm and similar performance to the high-performance but less stable CholeskyQR2 algorithm.
https://tuljournals.temple.edu/index.php/strategic_visions/article/download/463/316
Morales carries this narrative of exploitation and betrayal to the current day. The devastating effects of Hurricane Maria in 2017 debunked most of the fantasy cloaking America’s relationship with Puerto Ricans. President Trump’s assertion that “you Puerto Ricans are throwing off our budget” delineated the island’s second-class status in the 21st century (207). As the territory tries ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/FedHAN.pdf
FedHAN: A Cache-Based Semi-Asynchronous Federated Learning Framework Defending Against Poisoning Attacks in Heterogeneous Clients Xiaoding Wang1 , Bin Ye1 , Li Xu1 , Lizhao Wu1 , Sun-Yuan Hsieh2 , Jie Wu3;4 and Limei Lin1 1College of Computer and Cyber Security, Fujian Provincial Key Laboratory of Network Security and Cryptology, Fujian Normal University, Fuzhou 350117, China 2Department of ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/INFOCOM2024_PSFL%20Parallel-Sequential%20Federated%20Learning%20with%20Convergence%20Guarantees.pdf
Abstract—Federated Learning (FL) is a novel distributed learning paradigm which can coordinate multiple clients to jointly train a machine learning model by using their local data samples. Existing FL works can be roughly divided into two categories according to the modes of model training: Parallel FL (PFL) and Sequential FL (SFL). PFL can speed up each round of model training time through ...
https://cis.temple.edu/~latecki/Papers/ICIP2019.pdf
ABSTRACT The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this prob-lem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic seg-mentation. More specifically, the encoder adopts a ResNet as backbone network, where two new ...
https://scholarshare.temple.edu/bitstreams/48e9e752-7b37-40de-96f0-ed735aa84796/download
Longin Jan Latecki, Advisory Chair, Computer and Information Sciences Slobodan Vucetic, Computer and Information Sciences Haibin Ling, Computer and Information Sciences Jianbo Shi, External Member, University of Pennsylvania
https://cis.temple.edu/~wu/teaching/Spring%202013/handoff.pdf
1.1 INTRODUCTION Mobility is the most important feature of a wireless cellular communication system. Usu-ally, continuous service is achieved by supporting handoff (or handover) from one cell to another. Handoff is the process of changing the channel (frequency, time slot, spreading code, or combination of them) associated with the current connection while a call is in progress. It is often ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/jiang_www_2020.pdf
ABSTRACT Serendipity recommendation has attracted more and more atten-tion in recent years; it is committed to providing recommendations which could not only cater to users’ demands but also broaden their horizons. However, existing approaches usually measure user-item relevance with a scalar instead of a vector, ignoring user preference direction, which increases the risk of unrelated ...
https://sites.temple.edu/sserrano/files/2020/08/18-Analysis-of-Muskingum-Equation-Based-Flood-Routing-Schemes.pdf
By John J. Gelegenis1 and Sergio E. Serrano2 ABSTRACT: The linear Muskingum method continues to be a simple and popular procedure for river flood routing. An alternative algorithm for the numerical estimation of the Muskingum routing parameters is presented. Fully implicit and semi-implicit finite-difference schemes are compared for accuracy with respect to the tradi-tional graphical procedure ...