Model Parameters

Model parameters are also called weights and biases.

These parameters are adjusted during the training process to optimize the model’s performance on the given task.

See also: Model Parameters Tuning Optimisation techniques

Examples

1. Linear Regression:

   • Coefficients (weights) for each feature in the input data.
   • Intercept term (bias).

2. Logistic Regression:

   • Similar to linear regression, it has coefficients for each feature and an intercept term, but it models the probability of a binary outcome.

3. Neural Networks:

   • Weights: The connections between neurons in different layers.
   • Biases: Additional parameters added to the weighted sum of inputs to a neuron.

4. Support Vector Machines (SVM):

   • Support vectors: Data points that define the decision boundary.
   • Coefficients for the hyperplane equation.

5. Decision Trees: Decision Tree

   • Splitting thresholds for each node.
   • Structure of the tree (which features are used at each split).

6. K-Means Clustering:

   • Centroids: The center points of each cluster.