Gradient Descent

Overall Progress 0%

Predict a continuous value with ลท = wx + b. Derive the MSE loss and compute one gradient descent step from scratch.

Go to Linear Regression โ†’

The optimization algorithm behind every trained ML model: iteratively follow the negative gradient to minimize a loss.

Go to Gradient Descent โ†’

Binary classifier from scratch: sigmoid + cross-entropy loss + gradient update. The building block of softmax policies.

Go to Logistic Regression โ†’