<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>TimeGAN on AI Tech Blog</title>
    <link>https://jesamkim.github.io/ai-tech-blog/tags/timegan/</link>
    <description>Recent content in TimeGAN on AI Tech Blog</description>
    <generator>Hugo -- 0.147.6</generator>
    <language>ko</language>
    <lastBuildDate>Mon, 04 May 2026 15:30:00 +0900</lastBuildDate>
    <atom:link href="https://jesamkim.github.io/ai-tech-blog/tags/timegan/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>금융 시계열을 AI로 재현? — World Model의 첫 걸음</title>
      <link>https://jesamkim.github.io/ai-tech-blog/posts/2026-05-04-world-model-financial-timeseries/</link>
      <pubDate>Mon, 04 May 2026 15:30:00 +0900</pubDate>
      <guid>https://jesamkim.github.io/ai-tech-blog/posts/2026-05-04-world-model-financial-timeseries/</guid>
      <description>Ha and Schmidhuber의 World Model V-M-C 구조를 금융 시계열 도메인에 붙여본 개인 실험 기록입니다. Diffusion(DDPM)과 TimeGAN을 베이스라인 3종과 나란히 비교해 어느 모델이 시장의 변동성 클러스터링과 fat tail을 얼마나 재현하는지 정량적으로 확인했습니다.</description>
    </item>
  </channel>
</rss>
