Search Keywords

Results Restricted To:

https://www.temple.edu

Total Results: 2,800

Joint Optimization of DNN Partition and Scheduling for Mobile Cloud ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/ICPP_2021_Duan.pdf

ABSTRACT Reducing the inference time of Deep Neural Networks (DNNs) is critical when running time sensitive applications on mobile devices. Existing research has shown that partitioning a DNN and ofloading a part of its computation to cloud servers can reduce the inference time. The single DNN partition problem has been extensively in-vestigated recently. However, in real-world applications, a ...

The importance of representation: What Disney’s Black Little Mermaid ...

https://news.temple.edu/news/2023-05-17/importance-representation-what-disney-s-first-black-live-action-princess-means-film

After 34 years, Disney returns under the sea with its live-action adaptation of The Little Mermaid, premeiring in theaters on May 26. The new version stars Halle Bailey, most known for her role in the Grammy-nominated Chloe x Halle R&B duo, as Ariel in the actress’s first starring feature film role. This casting of a Black woman as the iconic mermaid has made waves.

A MEANINGFUL FLOOR FOR - Sites

https://sites.temple.edu/ticlj/files/2017/02/30.1.Crootof-TICLJ.pdf

it is grounded in the idea that all weaponry should be subject to ―meaningful human control.‖ This ―intuitively appealing‖ principle is immensely popular,

TileSR: Accelerate On-Device Super-Resolution with Parallel Offloading ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/m37113-chen%20final.pdf

Abstract—Recent years have witnessed the unprecedented performance of convolutional networks in image super-resolution (SR). SR involves upscaling a single low-resolution image to meet application-specific image quality demands, making it vital for mobile devices. However, the excessive computational and memory requirements of SR tasks pose a challenge in mapping SR networks on a single ...

Reinforcement Learning-based Dual-Identity Double Auction in ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/Reinforcement_Learning-based_Dual-Identity_Double_Auction_in_Personalized_Federated_Learning.pdf

Reinforcement Learning-based Dual-Identity Auction in Personalized Federated Juan Li, Member, IEEE, Zishang Chen, Tianzi Wu, Fellow, IEEE, Yanmin

“Neural-Symbolic Computing: An Effective Methodology for Principled ...

https://cis.temple.edu/tagit/presentations/Neural-Symbolic%20Computing%20An%20Effective%20Methodology%20for%20Principled%20Integration%20of%20Machine%20Learning%20and%20Reasoning.pdf

“Neural-symbolic computing aims at reconciling the dominating symbolic and connectionist paradigms of AI under a principled foundation. In neural-symbolic computing, knowledge is represented in symbolic form, whereas learning and reasoning are computed by a neural network.”

stoj-1.qxd - Temple University

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 ...

Automating Conflict Detection and Mitigation in Large-Scale IoT Syste

https://cis.temple.edu/~apal/ccgrid_iot.pdf

Abstract—In this paper we examine the problem of conflict detection and mitigation across multiple independently designed IoT subsystems deployed in a shared environment. The desired behavior of the system is codified in terms of predefined “safety properties”. We allow both the operational rules and safety properties to include time and temporal logic operations and detect their ...

A Modern Introduction to Probability and Statistics

https://cis.temple.edu/~latecki/Courses/Math3033-Fall09/DekkingBook07/A_modern_intro_probability_statistics_Dekking05.pdf

The two experiments are totally coupled: one has outcome ai if and the other has outcome ai. 2.6 Now there are 10 outcomes in B (for example (0,1,0,1,0)), each probability (1 p)3p2. Hence P(B) = 10(1 p)3p2. − − 2.7 This happens if and only if the experiment fails on Monday,. . . , and is a success on Sunday. This has probability p(1 p)6 to ...

Dense Subgraph Partition of Positive Hypergraphs

https://cis.temple.edu/~latecki/Papers/DSP_PAMI2014.pdf

Abstract—In this paper, we present a novel partition framework, called dense subgraph partition (DSP), to automatically, precisely and efficiently decompose a positive hypergraph into dense subgraphs. A positive hypergraph is a graph or hypergraph whose edges, except self-loops, have positive weights. We first define the concepts of core subgraph, conditional core subgraph, and disjoint ...