Search Keywords

Results Restricted To:

https://www.temple.edu

No results were found for your search.

Owl Byte – CIS Podcast

https://podcast.cis.temple.edu/

Interviews with information on industry job and academic research opportunities

DSpace - scholarshare.temple.edu

https://scholarshare.temple.edu/bitstream/handle/20.500.12613/6574/Kramarenko_temple_0225M_14499.pdf

DSpace - scholarshare.temple.edu ... DSpace

FedCPD: Personalized Federated Learning with Prototype-Enhanced ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/Paper%206190%20Camera%20Ready%20Version.pdf

a major challenge for federated learning in diverse settings. Personalized Federated Learning (PFL), [Tan et al., 2022a] addresses these issues by allowing client-specific models that leverage global insights to enhance local outcomes. The main challenge in PFL lies in balancing global knowledge sharing with preserving client-specific information, making the trade- off an important research ...

Adaptive Procedural Generation in Minecraft - Temple University

https://cis.temple.edu/~wangp/5603-AI/Project/2022S/pattersonblaker/Ward_Patterson_Final_Report.pdf

1 Abstract Minecraft has been the focus of much AI research in past years. Most recently, interest has risen in procedural generation of settlements in Minecraft, largely due to a annual competition established in 2018 called the Generative Design in Minecraft Competition. Inspired by this recent research, we aim to develop a set of algorithms that are capable of building a realistic ...

cis.temple.edu

https://cis.temple.edu/tagit/events/workshop2025/NARS_files/docs/GeneticNARSAGI25.pptx

the system’s memory; concepts, beliefs, goals, questions, etc. This level is acquired by the system’s experience, and can change during the system’s lifetime.

NARS Implementations - Temple University

https://cis.temple.edu/~pwang/demos.html

The file contains three tables showing the relations among uncertainty measurements, the truth-value functions of the one-premise rules, and the truth-value functions of the two-premise rules, respectively. In each table, the input values can be modified, and the outputs of the functions change accordingly. The system parameters used in the functions can also be adjusted.

Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic ...

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 ...

ArrayPipe: Introducing Job-Array Pipeline Parallelism for High ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/m48122-zhao%20final.pdf

ArrayPipe: Introducing Job-Array Pipeline Parallelism for High Throughput Model Exploration Hairui Zhao1, Hongliang Li1,2,∗, Qi Tian1, Jie Wu3, Meng Zhang1, Xiang Li1, Haixiao Xu4

Research Guides: Qualitative Data Analysis and QDA Tools: NVivo

https://guides.temple.edu/qda/nvivo

NVivo is a commercial qualitative research tool that allows advanced coding, analysis, and visualization for qualitative data. NVivo interface changed in 2020 and the term Code is now used instead of Node, among other changes. Latest version is NVivo 15. View version compatibility and MacOS and Windows differences.

Zhanteng Xie, Pujie Xin, and Philip Dames - Sites

https://sites.temple.edu/trail/files/2021/11/XieXinDamesIROS2021.pdf

Zhanteng Xie, Pujie Xin, and Philip Dames Abstract—This paper proposes a novel neural network-based control policy to enable a mobile robot to navigate safety through environments filled with both static obstacles, such as tables and chairs, and dense crowds of pedestrians. The network architecture uses early fusion to combine a short history of lidar data with kinematic data about nearby ...