sky-explore's Stars
Joey61Liuyi/Chiron
ICDCS2021
bitzj2015/DRL-Networking
Research on incentive mechanism design in mobile crowdsensing and mobile edge computing by deep reinforcement learning approaches.
asynchronous-machine-learning/Asynchronous-Differentially-Private-Learning-on-Distributed-Private-Data
We develop asynchronous differentially-private algorithms for collaboratively training machine-learning models on multiple private datasets. The asynchronous nature of the algorithms implies that a central learner interacts with the private data owners one-on-one whenever they are available for communication without needing to aggregate query responses to construct gradients of the entire fitness function.
pb1672/ML_Projects
Andrew Ng's Machine Learning Class Projects Description: Ex1 - Gradient Descent, Newton's Method, Linear Regression Ex2 - Sigmoid Kernels Ex3 - Logistic Regression Implementation Ex4 - Neural Networks implementation for Digit Recognition Ex5 - Regularized Linear Regression, Polynomial Regression Ex6 - SVM (Kernel implementation) for Spam Classification Ex8 - Recommender System (Collaborative Filtering) and Anomaly Detection
jordan8409212/RL-for-binary-computation-offloading-in-wireless-powered-MEC-networks
It's a implementation about the paper Liang Huang, Suzhi Bi, and Ying-jun Angela Zhang, "Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks", on https://ieeexplore.ieee.org/document/8771176
IBM/adaptive-federated-learning
Code for paper "Adaptive Federated Learning in Resource Constrained Edge Computing Systems"
PhuLai/eua-dataset
Edge server, user dataset for Edge Computing research
IBM/differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library
dw-wang/AA-ADMM
# AA-ADMM Python code for the numerical examples in the paper [On the Asymptotic Linear Convergence Speed of Anderson Acceleration Applied to ADMM](https://link.springer.com/article/10.1007/s10915-021-01548-2)
mschytt/NewtonADMM
chunlinsun/ADMM-for-Logistic-Regression
nirum/ADMM
Examples/code for the alternating direction method of multipliers (ADMM)
afbujan/admm_lasso
Lasso with ADMM in Python/MPI
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
jzxywpf/Intel_Lab_Data
A small project to explore the Intel Lab Data Series
haobolicpp/EdgeComputing
边缘计算测试与总结
mingt2019/Deep-Q-learning-for-mobile-edge-computing
Cyclotron2333/Task-Offloading-and-Resource-Allocation-for-Multi-Server-Mobile-Edge-Computing-Networks
lehongwen/awesome-edge-computing
边缘计算工程,从边缘计算概念、标准、软件系统、工程到商业应用。
jindongwang/MachineLearning
一些关于机器学习的学习资料与研究介绍
tensor-infinity/machine_learning_and_application_v1
本项目代码为雷明老师18年12月在清华出版社出版的《机器学习与应用》第一版中的配套代码,欢迎登录www.sigai.cn试听雷老师《机器学习》《深度学习》视频
MorvanZhou/Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
revenol/DROO
Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks
revenol/DDLO
Distributed Deep Learning-based Offloading for Mobile Edge Computing Networks
XiaTiancong/Deep-Reinforcement-Learning-for-IoT-Network-Dynamic-Clustering-in-Edge-Computing
datawhalechina/pumpkin-book
《机器学习》(西瓜书)公式详解
TolicWang/MachineLearningWithMe
wyc941012/Edge-Intelligence
随着移动云计算和边缘计算的快速发展,以及人工智能的广泛应用,产生了边缘智能(Edge Intelligence)的概念。深度神经网络(例如CNN)已被广泛应用于移动智能应用程序中,但是移动设备有限的存储和计算资源无法满足深度神经网络计算的需求。神经网络压缩与加速技术可以加速神经网络的计算,例如剪枝、量化、卷积核分解等。但是这些技术在实际应用非常复杂,并且可能导致模型精度的下降。在移动云计算或边缘计算中,任务卸载技术可以突破移动终端的资源限制,减轻移动设备的计算负载并提高任务处理效率。通过任务卸载技术优化深度神经网络成为边缘智能研究中的新方向。Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge这篇文章提出了协同推断的**,将深度神经网络进行分区,一部分层在移动端计算,而另一部分在云端计算。根据硬件平台、无线网络以及服务器负载等因素实现动态分区,降低时延以及能耗。本项目给出了边缘智能方面的相关论文,并且给出了一个Python语言实现的卷积神经网络协同推断实验平台。关键词:边缘智能(Edge Intelligence),计算卸载(Computing Offloading),CNN模型分区(CNN Partition),协同推断(Collaborative Inference),移动云计算(Mobile Cloud Computing)