Jian Lin
  • ABOUT
  • BLOG (current)
  • PROJECTS
  • CV
  • Reinforcement Learning — From Reward-Penalty Rules to Q-Learning

    A structured walkthrough of core RL concepts, from the reward-penalty weight update rule to Temporal Difference learning, SARSA, and Q-learning.

    4 min read   ·   May 28, 2026

    2026   ·   deep-learning   reinforcement-learning   TD-learning   Q-learning   ·   machine-learning

  • Unsupervised Learning — Neural Networks vs. Classical Machine Learning

    A comparative review of unsupervised learning techniques across neural network and classical ML perspectives, from PCA and SOM to Autoencoders and Diffusion Models.

    5 min read   ·   May 25, 2026

    2026   ·   deep-learning   unsupervised-learning   PCA   SOM   VAE   ·   machine-learning

  • Supervised Recurrent Networks and the GRU to Vanishing Gradients

    A deep dive into how Recurrent Neural Networks handle sequential data

    4 min read   ·   May 20, 2026

    2026   ·   deep-learning   RNN   GRU   neural-networks   ·   machine-learning

  • EM Algorithm for Gaussian Mixture Models

    Implementing GMM from scratch reminded me of the mathematical elegance behind classical statistical models — and why EM algorithm is an optimization masterpiece.

    3 min read   ·   May 16, 2026

    2026   ·   machine-learning   statistics   EM   GMM   ·   machine-learning

© Copyright 2026 Jian Lin. Powered by Jekyll with al-folio theme. Hosted by GitHub Pages.