liziyu403 Goto Github PK

architecture_simulator

assignment-reinforcement-learning

This repository contains some exercises from my RL course. In addition, I have been working on enhancing the project assignments from UC Berkeley's CS188. By experimenting with various evaluation functions, I improve the effectiveness of the assignments and strive for higher scores. I also implemented the Double Q-learning algorithm.

data-fusion

The repository was mainly implemented using Matlab and Python for code implementation. Classification prediction based on multiple data sources is performed according to the theory of evidence (D-S theory).

dataset-trans

dataset-trans2

distributed-computing

This GitHub repository is a project focused on distributed computing, highlighting concepts such as Coarse-grained locking, hand over hand locking, and lazy synchronization. These are essential techniques for managing concurrency and synchronization in distributed systems.

gradient-attacking

Reconstructing training data from gradients

main-color-analysis-app

This GitHub repository hosts an application for macOS that utilizes K-means clustering in the RGB color space to perform analysis and extract the top 5 dominant colors within an image. This application assists users in quickly identifying the predominant color composition of images.

posix-api-dev

This repository contains a C language implementation for a multitasking accumulator system. The system utilizes multithreading to acquire four asynchronous numerical inputs from an external SensorManager, . The code involves fundamental concepts of multithreaded programming such as thread synchronization, semaphores, mutexes, and more.

quantum-computing-simulation

Assignment of course "Quantum-Informtion". we delve into fundamental concepts related to quantum algorithms and explore their relationship with classical algorithms.

robot_simulation

A part of assignment of course "Robotique".

rxrt-node-red

L'utilisation de LoRaWAN, Node-RED, MQTT et du tableau de bord pour surveiller la qualité de l'air intérieur.

scotti-save-computation-at-training-time-with-an-adaptive-framework

we propose SCoTTi (Save Computation at Training Time), an adaptive framework that addresses the aforementioned challenge. It leverages an optimizable threshold parameter to effectively reduce the number of neuron updates during training which corresponds to a decrease in memory and computation footprint.