IT Wiki

Chosen response

Rejected response

Reference model

Policy model

Human feedback

Instruction tuning

Chat template

Loss masking

Synthetic data

Overfitting

Learning-rate schedule

Batch size

Mini-batch

Dynamic batching

Feature engineering

Feature selection

Numeric feature

Categorical feature

Feature store

Feature importance

Pseudo-label

Residual

Multi-class classification

Cross-entropy

Precision

Confusion matrix

Gaussian Mixture Model

Distance metric

Silhouette score

Forecast horizon

Recommendation system

Content-based filtering

Matrix factorization

Candidate generation

User-item interaction

Reinforcement Learning

Value function

Q-learning

Supervised Learning

Generalization

Unsupervised Learning

Dimensionality reduction

PCA

Representation learning

Pseudo-labeling

Consistency regularization

Teacher-student model

Mean Teacher