TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Exploration vs Exploitation: ฮต-greedy๋ถํฐ UCB, Thompson๊น์ง
Compare ฮต-greedy, UCB, Thompson Sampling, and RND for sparse rewards. See which exploration strategy actually works in hard environments.
-
VAE๋ก ์ ์ ๋ฐ์ดํฐ๋ง์ผ๋ก ํฐ๋น ๋ฒ ์ด๋ง ๊ณ ์ฅ ๊ฐ์งํ๊ธฐ: ๋ฌด๋ผ๋ฒจ ์ด์ ํ์ง ์ค์ ๊ฐ์ด๋
Detect turbine bearing failures using only normal data. VAE reconstruction error approach with Python code โ no labels required.
-
Python ์ด์์น ํ์ง: IQR, Z-Score, Isolation Forest ๋น๊ต
IQR vs Z-Score vs Isolation Forest vs DBSCAN for outlier detection. Real performance numbers and when to use each method in production.
-
Python ์์กด๋ถ์: lifelines๋ก ๊ณ ๊ฐ ์ดํ ์์ธกํ๊ธฐ
Predict customer churn with survival analysis using lifelines. Kaplan-Meier curves and Cox regression explained with working Python code.
-
๋ฐฑํธ๋ํน(Backtracking) ์ค์ ํ์ด ์ ๋ต – N-Queen๋ถํฐ ์์ด/์กฐํฉ ์์ฑ๊น์ง
Solve N-Queen, permutations, and Sudoku with backtracking. Python implementations with pruning strategies that actually speed things up.
-
Federated Learning์ผ๋ก ๋ค์ค ๊ณต์ฅ ์ค๋น ๊ณ ์ฅ ์์ธกํ๊ธฐ: ๋ฐ์ดํฐ ๊ณต์ ์์ด AI ๋ชจ๋ธ ํ์ ํ์ต ๊ตฌํ
Train fault prediction across factories without sharing data. Federated Learning with FedAvg โ solve Non-IID issues in PyTorch.
-
Python Poetry์์ uv๋ก ๋ง์ด๊ทธ๋ ์ด์ ์์ ๊ฐ์ด๋: ํจํค์ง ๊ด๋ฆฌ ์๋๋ฅผ 10๋ฐฐ ๋์ด๋ ์ค์ ์ ํ ๋ฐฉ๋ฒ
Migrate Poetry to uv and cut package install time by 10x. Step-by-step pyproject.toml conversion plus CI/CD updates included.
-
Model-Based RL: Dyna-Q๋ถํฐ MuZero๊น์ง Planning ์ ๋ต
Dyna-Q to MuZero: how model-based RL learns environment dynamics. MCTS planning and MBPO/Dreamer implementation strategies with code.