https://arshadhs.github.io/tags/expectation-maximization/Recent content in Expectation Maximization on Arshad SiddiquiHugoen-ushttps://arshadhs.github.io/docs/ai/statistics/060-gaussian-mixture-model-em/Mon, 01 Jan 0001 00:00:00 +0000https://arshadhs.github.io/docs/ai/statistics/060-gaussian-mixture-model-em/<h1 id="gaussian-mixture-model--expectation-maximization"> Gaussian Mixture Model &amp; Expectation Maximization <a class="anchor" href="#gaussian-mixture-model--expectation-maximization">#</a> </h1> <p>A Gaussian Mixture Model represents data as a weighted combination of multiple Gaussian distributions.</p> <p>It is commonly used for soft clustering and density estimation.</p> <blockquote class="book-hint info"> <p><strong>Key takeaway:</strong><br> K-means gives hard cluster membership.</p> <p>GMM gives probabilities of belonging to each cluster.</p> </blockquote> <ul> <li>Gaussian Mixture Model</li> <li>soft clustering</li> <li>mixing coefficients</li> <li>latent variables</li> <li>likelihood and log-likelihood</li> <li>Expectation-Maximization algorithm</li> <li>E-step and M-step</li> <li>responsibilities</li> <li>convergence</li> </ul> <hr> <h2 id="motivation-"> Motivation ☆ <a class="anchor" href="#motivation-">#</a> </h2> <p>Many real datasets are not described well by one Gaussian distribution.</p>