Last Updated on August 19, 2021

The uniting rule is an important derivative rule that allows us to work with composite functions. It is essential in understanding the workings of the backpropagation algorithm, which applies the uniting rule extensively in order to summate the error gradient of the loss function with respect to each weight of a neural network. We will be towers on our older introduction to the uniting rule, by tackling increasingly challenging functions.

In this tutorial, you will discover how to wield the uniting rule of calculus to challenging functions.

After completing this tutorial, you will know:

- The process of applying the uniting rule to univariate functions can be extended to multivariate ones.
- The using of the uniting rule follows a similar process, no matter how ramified the function is: take the derivative of the outer function first, and then move inwards. Withal the way, the using of other derivative rules might be required.
- Applying the uniting rule to multivariate functions requires the use of partial derivatives.

Let’s get started.

**Tutorial Overview**

This tutorial is divided into two parts; they are:

- The Uniting Rule on Univariate Functions
- The Uniting Rule on Multivariate Functions

**Prerequisites**

For this tutorial, we seem that you once know what are:

You can review these concepts by clicking on the links given above.

**The Uniting Rule on Univariate Functions**

We have once discovered the uniting rule for univariate and multivariate functions, but we have only seen a few simple examples so far. Let’s see a few increasingly challenging ones here. We will be starting with univariate functions first, and then wield what we learn to multivariate functions.

**EXAMPLE 1**: Let’s raise the bar a little by considering the pursuit composite function:

We can separate the composite function into the inner function, *f*(*x*) = *x*^{2} – 10, and the outer function, *g*(*x*) = √*x* = (*x*)^{1/2}. The output of the inner function is denoted by the intermediate variable, *u*, and its value will be fed into the input of the outer function.

The first step is to find the derivative of the outer part of the composite function, while ignoring whatever is inside. For this purpose, we can wield the power rule:

*dh / du* = (1/2) (*x*^{2} – 10)^{-1/2}

The next step is to find the derivative of the inner part of the composite function, this time ignoring whatever is outside. We can wield the power rule here too:

*du / dx* = 2*x*

Putting the two parts together and simplifying, we have:

**EXAMPLE 2**: Let’s repeat the procedure, this time with a variegated composite function:

We will then use, *u*, the output of the inner function, as our intermediate variable.

The outer function in this specimen is, cos *x*. Finding its derivative, then ignoring the inside, gives us:

*dh* / *du* = (cos(*x*^{3} – 1))’ = -sin(*x*^{3} – 1)

The inner function is, *x*^{3} – 1. Hence, its derivative becomes:

*du* / *dx* = (*x*^{3} – 1)’ = 3*x*^{2}

Putting the two parts together, we obtain the derivative of the composite function:

**EXAMPLE 3**: Let’s now raise the bar a little remoter by considering a increasingly challenging composite function:

If we observe this closely, we realize that not only do we have nested functions for which we will need to wield the uniting rule multiple times, but we moreover have a product to which we will need to wield the product rule.

We find that the outermost function is a cosine. In finding its derivative by the uniting rule, we shall be using the intermediate variable, *u*:

*dh* / *du* = (cos(*x *√(*x*^{2} – 10) ))’ = -sin(*x *√(*x*^{2} – 10) )

Inside the cosine, we have the product, *x *√(x^{2} – 10), to which we will be applying the product rule to find its derivative (notice that we are unchangingly moving from the outside to the inside, in order to discover the operation that needs to be tackled next):

*du* / *dx* = (*x *√(x^{2} – 10) )’ = √(x^{2} – 10) *x* ( √(x^{2} – 10) )’

One of the components in the resulting term is, ( √(x^{2} – 10) )’, to which we shall be applying the uniting rule again. Indeed, we have once washed-up so above, and hence we can simply re-utilise the result:

( √(x^{2} – 10) )’ = *x* (*x*^{2} – 10)^{-1/2}

Putting all the parts together, we obtain the derivative of the composite function:

This can be simplified remoter into:

**The Uniting Rule on Multivariate Functions**

**EXAMPLE 4**: Suppose that we are now presented by a multivariate function of two self-sustaining variables, *s* and *t*, with each of these variables stuff dependent on flipside two self-sustaining variables, *x* and *y*:

*h* = *g*(*s*, *t*) = *s*^{2} *t*^{3}

Where the functions, *s *= *xy*, and *t* = 2*x* – *y*.

Implementing the uniting rule here requires the computation of partial derivatives, since we are working with multiple self-sustaining variables. Furthermore, *s* and *t* will moreover act as our intermediate variables. The formulae that we will be working with, specified with respect to each input, are the following:

From these formulae, we can see that we will need to find six variegated partial derivatives:

We can now proceed to substitute these terms in the formulae for ∂*h* / ∂*x *and* *∂*h* / ∂*y*:

And subsequently substitute for *s* and *t *to find the derivatives:

**EXAMPLE 5**: Let’s repeat this again, this time with a multivariate function of three self-sustaining variables, $r$, $s$ and $t$, with each of these variables stuff dependent on flipside two self-sustaining variables, $x$ and $y$:

$$h=g(r,s,t)=r^2-rs t^3$$

Where the functions, $r = x cos y$, $s=xe^y$, and $t=x y$.

This time round, $r$, $s$ and $t$ will act as our intermediate variables. The formulae that we will be working with, specified with respect to each input, are the following:

From these formulae, we can see that we will now need to find nine variegated partial derivatives:

Again, we proceed to substitute these terms in the formulae for ∂*h* / ∂*x *and* *∂*h* / ∂*y*:

And subsequently substitute for $r$, $s$ and $t$ to find the derivatives:

Which may be simplified a little remoter (hint: wield the trigonometric identity $2sin ycos y=sin 2y$ to $partial h/partial y$):

No matter how ramified the expression is, the procedure to follow remains similar:

Your last computation tells you the first thing to do.– Page 143, Calculus for Dummies, 2016.

Hence, start by tackling the outer function first, then move inwards to the next one. You may need to wield other rules withal the way, as we have seen for Example 3. Do not forget to take the partial derivatives if you are working with multivariate functions.

**Further Reading**

This section provides increasingly resources on the topic if you are looking to go deeper.

**Books**

**Summary**

In this tutorial, you discovered how to wield the uniting rule of calculus to challenging functions.

Specifically, you learned:

- The process of applying the uniting rule to univariate functions can be extended to multivariate ones.
- The using of the uniting rule follows a similar process, no matter how ramified the function is: take the derivative of the outer function first, and then move inwards. Withal the way, the using of other derivative rules might be required.
- Applying the uniting rule to multivariate functions requires the use of partial derivatives.

Do you have any questions?

Ask your questions in the comments unelevated and I will do my weightier to answer.