View RSS Feed


  1. Data Science and Machine Learning (Part 06): Gradient Descent

    by , 07-31-2022 at 02:53 AM
    The idea is to take repeated steps in the opposite direction of the gradient (or approximate gradient) of the function at the current point, because this is the direction of steepest descent. Conversely, stepping in the direction of the gradient will lead to a local maximum of that function; the procedure is then known as gradient ascent.