A fellow student asks you, \In elementary calculus we found minima of a function by differentiating it, setting the resulting expression to zero, and then solving the equation. Since our loss function is differentiable, why don't we do that rather than bothering with gradient descent?" Explain why this is not, in fact, possible.
Already registered? Login
Not Account? Sign up
Enter your email address to reset your password
Back to Login? Click here