Mini toolsDefinition
An iterative algorithm for finding maximum likelihood estimates in models with latent variables.
Detailed Explanation
EM alternates between estimating the distribution of unobserved variables (E-step) and updating model parameters (M-step). It guarantees convergence to a local optimum and is widely used for mixture models and incomplete data problems.
Use Cases
1. Mixture model fitting 2. Image segmentation 3. Speech recognition 4. Gene sequence analysis
