Skip to main content

AI & machine learning

Overview​

Machine learning (ML) learns patterns from data to make predictions or generate content; AI is the broader goal of building systems that perform tasks requiring human-like judgment. In production, success depends on data quality, evaluation, governance, and MLOps as much as on model architecture.

Key concepts​

  • Supervised vs unsupervised — Labeled targets vs structure discovery.
  • Training, validation, test — Avoid leaking test knowledge into modeling choices.
  • Overfitting — Memorizing noise; mitigated with regularization and more data.
  • Embeddings & LLMs — Representations and generative models for text, code, images.
  • Responsible AI — Safety, bias, privacy, and human oversight.

ML experiment loop​

Sample: Python training sketch (scikit-learn style)​

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)
print(classification_report(y_test, model.predict(X_test)))

References​