# Why do we subtract the slope * a in Gradient Descent?

# Ok, I got it. But still, why is it MINUS?

# Because your goal is to MINIMIZE J(θ).

So, in the maximization problem, you need to **ADD **alpha * slope.

So, in the maximization problem, you need to **ADD **alpha * slope.

I’m an Engineering Manager at Scale AI and this is my notepad for Applied Math / CS / Deep Learning topics. Follow me on Twitter for more!

I’m an Engineering Manager at Scale AI and this is my notepad for Applied Math / CS / Deep Learning topics. Follow me on Twitter for more!