Giter Club home page Giter Club logo

disco-pytorch's Introduction

πŸ‘‹πŸ‘‹ Hello there, I'm Jie Xu

1) Latent Representation

Nice to meet you!

I am a Chinese student pursuing a Ph.D. in Artificial Intelligence at Ajou University in Korea. Since September 2021, I have been working under the supervision of Prof. Wonjun Hwang. My research interests during my Ph.D. studies include neural network quantization and knowledge distillation, utilizing the Information Theoretic Learning approach for image analysis. Before this, I completed my B.E. degree in Telecommunications and an M.Sc. in Computer Engineering from Jeju National University in Korea in 2021. During my undergraduate studies, I received three Korean National Scholarships. And my Ph.D. research is supported by Brain Korea Ph.D. Scholarship.

My recent research interests include uncertainty awareness of the deep compression model for diffusion models.

  1. Model Compression/Acceleration: Information theoretic learning, Neural network Pruning, Low-rank Approximation, Knowledge Distillation, and Binary Neural Network.
  2. Image-related tasks: Image classification, diffusion model.

Also, I am fond of mountaineering πŸ—» and photography πŸ“Έ. I have visited several mountains in my hometown, including 'Huang Shan - ι»„ε±±', 'Zi Peng Shan - 紫蓬山', and 'Xiao Bie Shan - 小别山', all located in Anhui Province. Besides, I have been to 'ν•œλΌμ‚° - 汉拿山' three times on Jeju Island in South Korea.

wo(1)

Updates

  • Jan 2024: One paper on the quantization model is submitted to the journal.
  • May 2024: Starting to learn the diffusion model & quantization model.

2) Study by Coursera Course

  • Neural Networks and Deep Learning - - Andrew Ng, Kian Katanforoosh, Younes BensoudaMourri
  • Machine Learning - - Andrew Ng
  • Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization - - Andrew Ng
  • Fundamentals of Reinforcement Learning - - Martha White, Adam White
  • TinyML and Efficient Deep Learning - MIT 6s965-Fall 2022 open tutorial
  • TinyML and Efficient Deep Learning - MIT 6.5940-Fall 2023 open tutorial
  • For learning the Diffusion model: https://learn.deeplearning.ai/accomplishments/0f02e4ca-56e7-49b7-a352-56e2c73b9182?usp=sharing
  • Attention on 2024-WAIC technique speech.

3) Techniques

  • C++, Python, TensorFlow(a little), PyTorch, Matrix.
  • Web development, Android application, Web crawler, Recommendation System, QNN(quantization neural network), Computer Vision, Diffusion model.

5) Languages

  • English Medium Level
  • Korean High Level
  • Chinese Mother tongue
  • My Chinese name: 徐摀

6) Building Fully Connected Layers

  • School Email: [email protected]
  • WeChat: kyen77-88_
  • Office: Ajou University, Paldal Hall, 913-2 room.

disco-pytorch's People

Contributors

jiaxinzhuang avatar yuting-gao avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.