0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

生成AIプロンプトTIPS(ツリー構造で全体像の可視化)

Last updated at Posted at 2025-03-15

魔法の言葉「ツリー構造で全て列挙してください」

分野の全体像を知りたい時、出力形式をツリー構造に指定すると、わかりやすくコードベースで回答してくれます。

入力

機械学習の種類をツリー構造で全て列挙してください。

出力

機械学習の種類をツリー構造で整理すると、以下のようになります。

機械学習
├── 教師あり学習 (Supervised Learning)
│   ├── 回帰 (Regression)
│   │   ├── 線形回帰 (Linear Regression)
│   │   ├── 多項式回帰 (Polynomial Regression)
│   │   ├── リッジ回帰 (Ridge Regression)
│   │   ├── ラッソ回帰 (Lasso Regression)
│   │   ├── Elastic Net 回帰 (Elastic Net Regression)
│   │   ├── サポートベクター回帰 (Support Vector Regression, SVR)
│   │   ├── 決定木回帰 (Decision Tree Regression)
│   │   ├── ランダムフォレスト回帰 (Random Forest Regression)
│   │   ├── XGBoost回帰 (XGBoost Regression)
│   │   ├── ニューラルネット回帰 (Neural Network Regression)
│   │   └── Gaussian Process 回帰 (Gaussian Process Regression)
│   ├── 分類 (Classification)
│   │   ├── ロジスティック回帰 (Logistic Regression)
│   │   ├── k近傍法 (k-Nearest Neighbors, k-NN)
│   │   ├── サポートベクターマシン (Support Vector Machine, SVM)
│   │   ├── 決定木 (Decision Tree)
│   │   ├── ランダムフォレスト (Random Forest)
│   │   ├── XGBoost (Extreme Gradient Boosting)
│   │   ├── LightGBM (Light Gradient Boosting Machine)
│   │   ├── カーネルメソッド (Kernel Methods)
│   │   ├── ベイズ分類 (Naive Bayes Classifier)
│   │   ├── ニューラルネットワーク (Neural Networks)
│   │   └── 畳み込みニューラルネットワーク (Convolutional Neural Network, CNN)
│   └── 順序分類 (Ordinal Classification)
│       ├── Proportional Odds Model
│       ├── Ordered Logistic Regression
│       └── Support Vector Ordinal Regression
├── 教師なし学習 (Unsupervised Learning)
│   ├── クラスタリング (Clustering)
│   │   ├── k-means法 (k-Means Clustering)
│   │   ├── 階層クラスタリング (Hierarchical Clustering)
│   │   ├── DBSCAN (Density-Based Spatial Clustering)
│   │   ├── Gaussian Mixture Model (GMM)
│   │   └── Mean Shift Clustering
│   ├── 次元削減 (Dimensionality Reduction)
│   │   ├── 主成分分析 (Principal Component Analysis, PCA)
│   │   ├── t-SNE (t-Distributed Stochastic Neighbor Embedding)
│   │   ├── UMAP (Uniform Manifold Approximation and Projection)
│   │   ├── 独立成分分析 (Independent Component Analysis, ICA)
│   │   ├── 特異値分解 (Singular Value Decomposition, SVD)
│   │   ├── 自己符号化器 (Autoencoder)
│   │   └── 多次元尺度構成法 (Multidimensional Scaling, MDS)
│   ├── 関係ルール学習 (Association Rule Learning)
│   │   ├── Aprioriアルゴリズム
│   │   └── FP-Growthアルゴリズム
│   └── 異常検知 (Anomaly Detection)
│       ├── 一般化異常検知
│       │   ├── k-NNベース
│       │   ├── LOF (Local Outlier Factor)
│       │   ├── Isolation Forest
│       │   ├── One-Class SVM
│       │   ├── Autoencoder
│       │   └── Gaussian Distribution Based Methods
│       └── 時系列異常検知
│           ├── ARIMAベース
│           ├── LSTM Autoencoder
│           ├── Prophet
│           └── Seasonal Hybrid ESD (S-H-ESD)
├── 強化学習 (Reinforcement Learning)
│   ├── 価値ベース (Value-Based)
│   │   ├── Q学習 (Q-Learning)
│   │   ├── Deep Q Network (DQN)
│   │   ├── Double DQN
│   │   ├── Dueling DQN
│   │   └── Rainbow DQN
│   ├── 方策ベース (Policy-Based)
│   │   ├── REINFORCEアルゴリズム
│   │   ├── Deterministic Policy Gradient (DPG)
│   │   ├── Stochastic Policy Gradient (SPG)
│   │   └── Trust Region Policy Optimization (TRPO)
│   ├── アクター・クリティック法 (Actor-Critic Methods)
│   │   ├── Advantage Actor-Critic (A2C)
│   │   ├── Asynchronous Advantage Actor-Critic (A3C)
│   │   ├── Deep Deterministic Policy Gradient (DDPG)
│   │   ├── Proximal Policy Optimization (PPO)
│   │   └── Soft Actor-Critic (SAC)
│   └── モデルベース強化学習 (Model-Based Reinforcement Learning)
│       ├── AlphaGo
│       ├── AlphaZero
│       ├── Model Predictive Control (MPC)
│       └── World Models
└── 半教師あり学習 (Semi-Supervised Learning)
    ├── グラフベース手法 (Graph-Based Methods)
    ├── 自己学習 (Self-Training)
    ├── Co-Training
    ├── 生成モデル (Generative Models)
    │   ├── GANs (Generative Adversarial Networks)
    │   └── Variational Autoencoders (VAE)
    └── Consistency Regularization

このツリーは、機械学習の主要な種類と代表的な手法を階層的に整理したものです。さらに細分化したい場合は、各カテゴリに特化した手法を追加できます。

まとめ

こりゃあ便利ですね。
GPT以外のモデルはマークダウン記法で返してくるので注意が必要です

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?