Stars
TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network
A very simple generative adversarial network (GAN) in PyTorch
Federated Learning: Parameter Server doing aggregation of updates to a model coming from clients participating in a Federated Learning setup. See also the Android application companion at https://g…
Federated Learning: Client application doing classification of images and local training. Works better with the Parameter Server at https://github.com/mccorby/PhotoLabellerServer
simulation of the asynchronous federated learning system of paper "Asynchronous Federated Optimization"
Source code for the paper "Asynchronous Federated Optimization"
The project uses two public datasets WISDM Dataset and UCI-HAR Dataset as the source for recorded sensor data and a Convolutional Neural Network Model is designed and trained for tracking and predi…
Federated learning for human activity recognition (HAR) using convolutional neural network (CNN)
Code and raw result data for paper: AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation
Example of PyTorch DistributedDataParallel
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
tensorflow实战练习,包括强化学习、推荐系统、nlp等
Source Code
This is Code for "A Reinforcement Learning Approach for Minimizing Job Completion Time in Clustered Federated Learning";
This is a semi-asynchronous federated learning, completed for the paper"ASFL: Adaptive Semi-asynchronous Federated Learning for Balancing Model Accuracy and Total Latency in Mobile Edge Networks"
Convolutional and LSTM networks to classify human activity
37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 20 datasets.
Human Activity Recognition, exploring different sensor-types with RealWorld HAR dataset
Convolutional Neural Network examples from Denver Deep Learning presentation, September 26, 2016
Modeling Global Distribution for Federated Learning with Label Distribution Skew
Human Activity Recognition using Convolution Neural Network
Human Activity Recognition for different datasets using deep learning model
Read and replication project of a paper which proposes solution for Smartphone device heterogeniety problem in Human Activity Recognition using accelerometers.
Activity Recognition from Single Chest-Mounted Accelerometer Dataset using a Variety of Classifiers