What exactly means 'delta' in gradient descent algorithm?
See on this picture which 'delta' I mean: https://skitch.com/sebastianzontek/gn2fm/machine-learning
I am not completly authorized to answer this question but maybe it will be helpful if i say that this term is derivative of the theta, which is used to control aspects of cost function minimization (direction and rate). Let theta be a coordinate on X-axis (name it A) . B will be corresponding coordinate on Y-axis. If You draw tangent line to function J at point (A, B) the deriviative will be the slope of this tangent line.
Answer this question
Write a full and a complete answer. Use your knowlede to help others!