Automatic Differentiation

grad(func[, grad_vars, dyn_vars, argnums, ...])	Automatic gradient computation for functions or class objects.
vector_grad(func[, dyn_vars, grad_vars, ...])	Take vector-valued gradients for function func.
jacobian(func[, grad_vars, dyn_vars, ...])	Extending automatic Jacobian (reverse-mode) of func to classes.
jacrev(func[, grad_vars, dyn_vars, argnums, ...])	Extending automatic Jacobian (reverse-mode) of func to classes.
jacfwd(func[, grad_vars, dyn_vars, argnums, ...])	Extending automatic Jacobian (forward-mode) of func to classes.
hessian(func[, dyn_vars, grad_vars, ...])	Hessian of func as a dense array.