You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Python code for visualizing Gradient Descent optimization paths with animated contours. Demonstrates two strategies: fixed and optimal step sizes. Includes Fibonacci search for step size and data saved with Pickle.
Gradient Descent is the process of minimizing a function by following the gradients of the cost function. This involves knowing the form of the cost as well as the derivative so that from a given point you know the gradient and can move in that direction, e.g. downhill towards the minimum value.
An easy implementation of the GD implementation, comparison using different functions using fixed alpha or the alpha obtained through backtracking algo