Reference 4 stops to get here · leads to 1

Empirical Risk Minimization

The principle of choosing a model that minimizes error on training data, fundamental to supervised learning.

Your route here

4 stops · basics first
  1. Dataset ✓ understood

    A collection of data examples used for training, validating, or testing machine learning models.

  2. Training Data ✓ understood

    The examples a model learns its weights from, kept separate from the validation and test data used to check how well it generalizes.

  3. Training ✓ understood

    The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.

  4. Loss Function ✓ understood

    A function that scores how wrong a model's prediction is as a single number, which training then works to make as small as possible.

  5. Empirical Risk Minimization · you are here ✓ understood

The principle of choosing a model that minimizes error on training data, fundamental to supervised learning.

This concept is essential for understanding machine learning fundamentals and forms a key part of modern AI systems.

  • Loss Function
  • Training
  • Optimization

Where it sits

Before this

Loss Function Training Data
Empirical Risk Minimization

Leads to

PAC Learning

Explore nearby

Training Overfitting When a model fits its training data too closely, noise included, so it scores well on examples it has seen and poorly on new ones. Training Regularization Techniques to prevent overfitting by adding constraints or penalties to the model (L1, L2, dropout, early stopping). Foundations PAC Learning Probably Approximately Correct - a theoretical framework for analyzing learning algorithm guarantees. Foundations Maximum Likelihood Estimation Finding model parameters that maximize the probability of observing the training data. Training Gradient Descent An optimization method that repeatedly moves a model's parameters a small step in the direction that most reduces the loss.