Landmark 5 stops to get here · leads to 2

Hyperparameter

Configuration settings external to the model (learning rate, batch size) that must be set before training begins.

Your route here

5 stops · basics first
  1. Dataset ✓ understood

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

  2. 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.

  3. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  4. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  5. Parameter ✓ understood

    Learnable values (weights and biases) in a neural network that are adjusted during training to minimize loss.

  6. Hyperparameter · you are here ✓ understood

Picture it

Hyperparameters

  • Set by you before training
  • Learning rate, batch size
  • Epochs, layer count
  • Tuned by trying runs

Parameters

  • Learned during training
  • Weights and biases
  • Often millions or billions
  • Updated by gradient descent
Notice that hyperparameters shape how training runs, while parameters are what training actually produces.

Where it sits

Before this

Parameter Training
Hyperparameter

Leads to

Experiment Tracking Hyperparameter Tuning

Explore nearby

Training Learning Rate A hyperparameter controlling the step size in gradient descent - too high causes instability, too low slows convergence. Training Batch Size The number of training examples processed together in one forward/backward pass. Training Epoch One complete pass through the entire training dataset during the training process. Training Hyperparameter Tuning The process of finding optimal hyperparameter values through techniques like grid search, random search, or Bayesian optimization. Training Regularization Techniques to prevent overfitting by adding constraints or penalties to the model (L1, L2, dropout, early stopping).