Gradient Descent
Defined in 5 lectures. Each definition is in that lecture's terms.
Definitions are written by AI from each lecture’s transcript. The time opens the lecture where the lecturer explains it.
- An optimization algorithm that modifies parameters by small steps in the direction of the gradient to minimize the loss.2:02:08Spelled-Out Intro to Neural Networks & Backpropagation: Building microgradAndrej Karpathy · Independent / Eureka Labs
- An algorithm that takes steps in the negative gradient direction to descend a function as fast as possible to a local minimum.11:01Optimization: A Bootcamp for Machine Learning, Inverse Problems, and ControlSteve Brunton · University of Washington
- An optimization method that updates model parameters in the direction of the gradient to minimize a cost function over training data.
- An iterative optimization algorithm that moves parameters in the direction of the maximal gradient of the cost function to find a minimum.
- Optimization method that improves a model by repeatedly moving downhill on error.