Supervised Learning

Paradigma machine learning di mana model belajar dari dataset berlabel (input-output pairs). Klasifikasi, regresi, object detection.

Supervised learning butuh data berlabel. Algoritma: linear regression, decision trees, SVM, neural networks. Tantangan: butuh banyak data berlabel, overfitting.

Also known as: pembelajaran terawasi
Print

Supervised Learning

Definisi

Model belajar dari dataset berlabel {(x₁, y₁), (x₂, y₂), …} untuk memprediksi output y untuk input x baru.

Jenis

  • Klasifikasi — output kategori (spam/not spam, image class)
  • Regresi — output numerik (harga rumah, suhu)
  • Object detection — bounding box + class
  • Sequence labeling — POS tagging, NER

Algoritma

  • Linear/Logistic regression
  • Decision trees & Random Forest
  • SVM
  • k-NN
  • Neural networks

Connected to

Not yet written

The following pages are referenced but don't exist yet — they'd make good future additions.

  • /concepts/machine-learning

References

  1. Wikipedia

Type at least 2 characters to search.

Press to navigate, to open, esc to close.