brianwu-s Goto Github PK

followers: 5.0 following: 4.0 repos: 17.0 gists: 0.0

Name: Brian Wu

Type: User

Bio: Hello guys, I'm Brian Wu. A graduate student of MSCS program at UCSD. My interest is Data Mining and Machine Learning.

Brian Wu's Projects

an-improved-oom-killer

This new OOM Killer is designed and implemented by myself to improve the OOM Killer’s kill process mechanism. That is to say, my work is to make the original Linux OOM Killer smarter)

android_process_tree-and-linux-practice

The whole project is developed under Linux OS(Ubuntu 20.04). A new Android system call is implemented with module to process tree information in a depthfirst-search (DFS) order.

bus-booking-platform

A customized Bus-Booking platform. It provides economical service with real-time flexible route planning and order dispatch, which contributes to a better user experience.

chaos_proxy

Chaos proxy is a web proxy server , which is used to simulate the real world network environment. Web FrameWork: Python Tornado

Computer network involves a lot of important knowledge and ideas. After reading James F. kurose's "computer networking -- a top-down approach" sixth edition and its corresponding Chinese version: 《计算机网络——自顶向下方法》 seventh edition, I have a basic understanding of this field. Here are the notes about the key concepts in Computer Network. Brief description about the framework and main contents of these notes lies in README.md.

core-os-riscv

🖥️ An xv6-like operating system on RISC-V with multi-core support. Documentation available online.

data_visualization_for_hangzhou-metro-traffic

Design a helpful GUI for data visualization of Hangzhou Metro Traffic. ( Language: QT)

database_technology

The use of database is very important for a developer or researcher. It is the basic tool of data mining, data science, big data algorithms and other big-data related fields. The use of database is very important for a developer or researcher. It is the basic tool of data mining, data science, big data algorithms and other big-data related fields. After reading Jeffrey D.Ullman's "A First Course in DataBase systems" third edition and its corresponding chinese version: 《数据库系统基础教程》third edition, I learned the concept of Relational Algebra, XML, XQuery, XPath and the basic use of MySQL . Here are the notes about the key concepts in DB. Brief description about the framework and main contents of these notes lies in Description.md. Brief description about the framework and main contents of these notes lies in Description.md.

dimentionality_reduction

Nowadays unstructured high-dimensional data like video, audio, text and images has become hot topics in mining research. However, high-dim data is often accompanied with the problem of substantial computation cost and low training efficiency. Otherwise high dimension brings about sparseness of data space representations, making it more likely to be overfitted. As a consequence, dimensionality reduction has to be applied to the preprocess of data. In this report, we try nine different dimensionality reduction methods, including selection by variance, Random Forest, PCA, kernel PCA, LDA, AE, VAE, t-SNE, Umap. Then we made overall comparisons between performance of various approaches and hyperparameters. The experiment on AwA2 dataset shows that LDA gets attains the most efficient performance with 0.93 accuracy and only 49 dimensions, while PCA with sigmoid kernel function reaches the best accuracy 0.935 but reduces dimension barely to 1024.

distance_metrics

Distance metrics are a key part of some machine learning algorithms, such as K-Nearest Neighbors KNN algorithm. Moreover, an effective distance metric can improve the performance of machine learning models, whether that's for classification tasks or clustering. In this project, we conducted experiments using the deep learning features of the (AwA2) dataset. First, we use the KNN algorithm combined with 4 simple metrics (Manhattan distance, Euclidean distance, Chebyshev distance and cosine distance) to conduct experiments and evaluate their performance. We also use preprocessing to improve efficiency(Use LDA to reduce dimension). Secondly, we tried 7 metric learning algorithms ( 4 supervised metric learning methods : LMNN, NCA, LDFA, MLKR; 3 weakly supervised metric learning methods : ITML, SDML, MMC to see different method's effect on KNN.

domain_adaptation

Domain Adaptation is one of the branches of migration learning. Its purpose is to map differently distributed source and target domain data into a feature space, minimizing the distance between the two in that space. In this report, we use Office-Home dataset as our dataset, and try traditional methods (TCA, JDA, CORAL, BDA, WBDA) and deep learning methods (DANN, DDC DeepCORAL) to do domain adaptation and evaluate the performances of them.

electron_microscopy_image_segmentation

Image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. In this project, we try to solve the problem in ISBI challenge.

housenet-main

Are you on the hunt for your dream residence? Look no further than HouseNet, the ultimate web application to help you find a place you can truly call home.

knowledge_framework

The repository is for my staged knowledge framework. Through markdown, I record important knowledge points and some of my own understanding of knowledge, so that I can review and deepen my understanding of the idea in the future. I will be happy if the knowledge can help you solve some problems. The contents mainly composed of the following parts: Machine Learning, Deep Learning, C++, Python (including tensorflow and pytorch).

machine_learning

Machine Learning is a wide range field, which mainly includes the following four parts: Supervised Learning, Unsupervised Learning, Weakly Supervised Learning and Reinforcement Learning. Also, deep learning is a sub-field of machine learning. Knowing what machine learning includes, understanding the mathematical principles and implementation details of these contents, and learning the specific ideas behind them are far more important than just calling python libraries to solve certain tasks. I have been playing machine learning for more than 2 years, including taking various machine learning-related courses and completing machine learning-related tasks. These courses include: Standford MachineLearning course , Coursera DeepLearning course taught by Andrew Ng; SJTU CS420 Machine Learning course and CS410 Artificial Intelligence course; CSDN machine learning course taught by Shunxiang Liu. The machine learning-related books I have read include: Professor Zhou Zhihua’s "machine learning book" (watermelon book), Ian Goodfellow's "Deep Learning" book (flower book) and Francois Chollet's "Deep Learning with Python". They are all very helpful to me. The machine learning related projects (codes and their corresponding description, reports) are also included in this repository. In short, this repository contains a lot of content, and I hope it can be helpful to you.

operating_system_notes

This repository is for the course notes and core idea of SJTU CS307: Operating Systems. I also borrowed some key ideas from ABRAHAM SILBERSCHATZ's "Operating System Concepts" , 10th Edition. You can view the knowledge summary in "os_summary.pdf" and the mindmap of entire course in "Mindmap.pdf". Hope this will be helpful for you.

reinforcement_learning_algorithms

This repository is the implementation (Tensorflow) of classical Reinforcement Learning algorithms, which includes: PPO, DPPO, DDPG, A3C, AC, DQNs (Double DQN, Dueling DQN, Prioritized DQN), Policy Gradient, Q-learning , SARSA (SARSA $\lambda$). The algorithm's perfomance is checked with OpenAI Gym, Mujoco environments.

brianwu-s Goto Github PK

Brian Wu's Projects

Recommend Projects

Recommend Topics

Recommend Org