Derivation of Backpropagation algorithm
In machine learning, specifically deep learning, backpropagation (backprop,[1]BP) is an algorithm widely used in the training of feedforward neural networks for supervised learning; generalizations exist for other artificial neural networks (ANNs), and for functions generally.[2] Backpropagation efficiently computes the gradient of the loss function with respect to the weights of the network for a single input-output example. This makes it feasible to use gradient methods for training multi-layer networks, updating weights to minimize loss; commonly one uses gradient descent or variants such as stochastic gradient descent. The backpropagation algorithm works by computing the gradient of the loss function with respect to each weight by the chain rule, iterating backwards one layer at a time from the last layer to avoid redundant calculations of intermediate terms in the chain rule; this is an example of dynamic programming.[3]
The term backpropagation strictly refers only to the
algorithm for computing the gradient, but it is often used loosely
to refer to the entire learning algorithm, also including how the
gradient is used, such as by stochastic gradient
descent.[4] Backpropagation generalizes the gradient
computation in the Delta rule, which is the single-layer version of
backpropagation, and is in turn generalized by automatic
differentiation, where backpropagation is a special case of reverse
accumulation (or "reverse mode").[5] The term
backpropagation and its general use in neural networks was
announced in Rumelhart, Hinton & Williams (1986a), then
elaborated and popularized in Rumelhart, Hinton & Williams
(1986b), but the technique was independently rediscovered many
times, and had many predecessors dating to the 1960s; see §
History.[6] A modern overview is given in Goodfellow,
Bengio & Courville (2016).[7]In machine learning,
specifically deep learning, backpropagation
(backprop,[1]BP) is an
algorithm widely used in the training of feedforward neural
networks for supervised learning; generalizations exist for other
artificial neural networks (ANNs), and for functions
generally.[2] Backpropagation efficiently computes the
gradient of the loss function with respect to the weights of the
network for a single input-output example. This makes it feasible
to use gradient methods for training multi-layer networks, updating
weights to minimize loss; commonly one uses gradient descent or
variants such as stochastic gradient descent. The backpropagation
algorithm works by computing the gradient of the loss function with
respect to each weight by the chain rule, iterating backwards one
layer at a time from the last layer to avoid redundant calculations
of intermediate terms in the chain rule; this is an example of
dynamic programming.[3]
Overview
Backpropagation computes the gradient in weight space of a feedforward neural network, with respect to a loss function. Denote:
For classification, output will be a vector of class probabilities (e.g., (0.1,0.7,0.2), and target output is a specific class, encoded by the one-hot/dummy variable (e.g., (0,1,0)).
For classification, this is usually cross entropy (XC, log loss), while for regression it is usually squared error loss (SEL).
For classification the last layer is usually the logistic function for binary classification, and softmax (softargmax) for multi-class classification, while for the hidden layers this was traditionally a sigmoid function (logistic function or others) on each node (coordinate), but today is more varied, with rectifier (ramp, ReLU) being common.
In the derivation of backpropagation, other intermediate quantities are used; they are introduced as needed below. Bias terms are not treated specially, as they correspond to a weight with a fixed input of 1. For the purpose of backpropagation, the specific loss function and activation functions don't matter, so long as they and their derivatives can be evaluated efficiently.
The overall network is then a combination of function composition and matrix multiplication:
For a training set there will be a set of input-output pairs,. For each input-output pair in the training set, the loss of the model on that pair is the cost of the difference between the predicted output and the target output :
Note the distinction: during model evaluation, the weights are fixed, while the inputs vary (and the target output may be unknown), and the network ends with the output layer (it does not include the loss function). During model training, the input-output pair is fixed, while the weights vary, and the network ends with the loss function.
Backpropagation computes the gradient for a fixed input-output pair , where the weights can vary. Each individual component of the gradient, can be computed by the chain rule; however, doing this separately for each weight is inefficient. Backpropagation efficiently computes the gradient by avoiding duplicate calculations and not computing unnecessary intermediate values, by computing the gradient of each layer – specifically, the gradient of the weighted input of each layer, denoted by – from back to front.
Informally, the key point is that since the only way a weight in affects the loss is through its effect on the next layer, and it does so linearly, are the only data you need to compute the gradients of the weights at layer l, and then you can compute the previous layer and repeat recursively. This avoids inefficiency in two ways. Firstly, it avoids duplication because when computing the gradient at layer , you do not need to recompute all the derivatives on later layers each time. Secondly, it avoids unnecessary intermediate calculations because at each stage it directly computes the gradient of the weights with respect to the ultimate output (the loss), rather than unnecessarily computing the derivatives of the values of hidden layers with respect to changes in weights .
Backpropagation can be expressed for simple feedforward networks in terms of matrix multiplication, or more generally in terms of the adjoint graph.
Matrix multiplication[edit]
For the basic case of a feedforward network, where nodes in each layer are connected only to nodes in the immediate next layer (without skipping any layers), and there is a loss function that computes a scalar loss for the final output, backpropagation can be understood simply by matrix multiplication.[c] Essentially, backpropagation evaluates the expression for the derivative of the cost function as a product of derivatives between each layer from left to right – "backwards" – with the gradient of the weights between each layer being a simple modification of the partial products (the "backwards propagated error").
Given an input-output pair , the loss is:
In order to compute this, one starts with the input and works forward; denote the weighted input of each layer as and the output of layer as the activation . For backpropagation, the activation as well as the derivatives (evaluated at ) must be cached for use during the backwards pass.
The derivative of the loss in terms of the inputs is given by the chain rule; note that each term is a total derivative, evaluated at the value of the network (at each node) on the input :
These terms are: the derivative of the loss function;[d] the derivatives of the activation functions;[e] and the matrices of weights:[f]
The gradient is the transpose of the derivative of the output in terms of the input, so the matrices are transposed and the order of multiplication is reversed, but the entries are the same:
Backpropagation then consists essentially of evaluating this expression from right to left (equivalently, multiplying the previous expression for the derivative from left to right), computing the gradient at each layer on the way; there is an added step, because the gradient of the weights isn't just a subexpression: there's an extra multiplication.
Introducing the auxiliary quantity for the partial products (multiplying from right to left), interpreted as the "error at level " and defined as the gradient of the input values at level :
Note that is a vector, of length equal to the number of nodes in level ; each term is interpreted as the "cost attributable to (the value of) that node".
The gradient of the weights in layer is then:
The factor of is because the weights between level and affect level proportionally to the inputs (activations): the inputs are fixed, the weights vary.
The can easily be computed recursively as:
The gradients of the weights can thus be computed using a few matrix multiplications for each level; this is backpropagation.
Compared with naively computing forwards (using the for illustration):
there are two key differences with backpropagation:
Adjoint graph
Intuition For more general graphs, and other advanced variations,
backpropagation can be understood in terms of automatic
differentiation, where backpropagation is a special case of reverse
accumulation (or "reverse mode").[5]
Motivation
The goal of any supervised learning algorithm is to find a function that best maps a set of inputs to their correct output. The motivation for backpropagation is to train a multi-layered neural network such that it can learn the appropriate internal representations to allow it to learn any arbitrary mapping of input to output.[8]
Learning as an optimization problem
To understand the mathematical derivation of the backpropagation algorithm, it helps to first develop some intuition about the relationship between the actual output of a neuron and the correct output for a particular training example. Consider a simple neural network with two input units, one output unit and no hidden units, and in which each neuron uses a linear output (unlike most work on neural networks, in which mapping from inputs to outputs is non-linear)[g] that is the weighted sum of its input.
A simple neural network with two input units (each with a single input) and one output unit (with two inputs)
Initially, before training, the weights will be set randomly. Then the neuron learns from training examples, which in this case consist of a set of tuples where and are the inputs to the network and t is the correct output (the output the network should produce given those inputs, when it has been trained). The initial network, given and , will compute an output y that likely differs from t (given random weights). A loss function is used for measuring the discrepancy between the target output t and the computed output y. For regression analysis problems the squared error can be used as a loss function, for classification the categorical crossentropy can be used.
As an example consider a regression problem using the square error as a loss:
where E is the discrepancy or error.
Consider the network on a single training case:. Thus, the input and are 1 and 1 respectively and the correct output, t is 0. Now if the relation is plotted between the network's output y on the horizontal axis and the error E on the vertical axis, the result is a parabola. The minimum of the parabola corresponds to the output y which minimizes the error E. For a single training case, the minimum also touches the horizontal axis, which means the error will be zero and the network can produce an output y that exactly matches the target output t. Therefore, the problem of mapping inputs to outputs can be reduced to an optimization problem of finding a function that will produce the minimal error.
Error surface of a linear neuron for a single training case
However, the output of a neuron depends on the weighted sum of all its inputs:
where and are the weights on the connection from the input units to the output unit. Therefore, the error also depends on the incoming weights to the neuron, which is ultimately what needs to be changed in the network to enable learning. If each weight is plotted on a separate horizontal axis and the error on the vertical axis, the result is a parabolic bowl. For a neuron with k weights, the same plot would require an elliptic paraboloid of dimensions.
Error surface of a linear neuron with two input weights
One commonly used algorithm to find the set of weights that minimizes the error is gradient descent. Backpropagation is then used to calculate the steepest descent direction in an efficient way.
Derivation[edit]
The gradient descent method involves calculating the derivative of the loss function with respect to the weights of the network. This is normally done using backpropagation. Assuming one output neuron,[h] the squared error function is
where
is the loss for the output and target value ,
is the target output for a training sample, and
is the actual output of the output neuron.
For each neuron, its output is defined as
where the activation function {\displaystyle \varphi } is non-linear and differentiable (even if the ReLU is not in one point). A historically used activation function is the logistic function:
which has a convenient derivative of:
The input to a neuron is the weighted sum of outputs of previous neurons. If the neuron is in the first layer after the input layer, the of the input layer are simply the inputs to the network. The number of input units to the neuron is . The variable denotes the weight between neuron of the previous layer and neuron of the current layer.
Finding the derivative of the error[edit]
Diagram of an artificial neural network to illustrate the notation used here.
Calculating the partial derivative of the error with respect to a weight is done using the chain rule twice:
|
(Eq. 1) |
In the last factor of the right-hand side of the above, only one term in the sum, , depends on , so that
|
(Eq. 2) |
If the neuron is in the first layer after the input layer, is just .
The derivative of the output of neuron with respect to its input is simply the partial derivative of the activation function:
|
(Eq. 3) |
which for the logistic activation function case is:
This is the reason why backpropagation requires the activation function to be differentiable. (Nevertheless, the ReLU activation function, which is non-differentiable at 0, has become quite popular, e.g. in AlexNet)
The first factor is straightforward to evaluate if the neuron is in the output layer, because then and
|
(Eq. 4) |
If the logistic function is used as activation and square error as loss function we can rewrite it as
However, if {\displaystyle j} is in an arbitrary inner layer of the network, finding the derivative with respect to is less obvious.
Considering as a function with the inputs being all neurons receiving input from neuron ,
and taking the total derivative with respect to , a recursive expression for the derivative is obtained:
|
(Eq. 5) |
Therefore, the derivative with respect to can be calculated if all the derivatives with respect to the outputs of the next layer – the ones closer to the output neuron – are known.
Substituting Eq. 2, Eq. 3 Eq.4 and Eq. 5 in Eq. 1 we obtain:
with
if is the logistic function, and the error is the square error:
To update the weight using gradient descent, one must choose a learning rate, . The change in weight needs to reflect the impact on of an increase or decrease in . If , an increase in increases ; conversely, if, an increase in decreases. The new is added to the old weight, and the product of the learning rate and the gradient, multiplied by guarantees that changes in a way that always decreases . In other words, in the equation immediately below, always changes in such a way that is decreased:
Loss function[edit]
Further information: Loss function
The loss function is a function that maps values of one or more variables onto a real number intuitively representing some "cost" associated with those values. For backpropagation, the loss function calculates the difference between the network output and its expected output, after a training example has propagated through the network.
Assumptions[edit]
The mathematical expression of the loss function must fulfill two conditions in order for it to be possibly used in backpropagation.[9] The first is that it can be written as an average over error functions, for individual training examples, . The reason for this assumption is that the backpropagation algorithm calculates the gradient of the error function for a single training example, which needs to be generalized to the overall error function. The second assumption is that it can be written as a function of the outputs from the neural network.
Example loss function[edit]
Let be vectors in .
Select an error function measuring the difference between two outputs. The standard choice is the square of the Euclidean distance between the vectors and :
The error function over training examples can then be written as an average of losses over individual examples:
Is BP equal to MLP
Multi Layer Perceptron training algorithm for MLPs is BP which is an extended form of the method used to train the perceptron. This algorithm entails a backward flow of the error corrections through each neuron in the network. The process of adjusting the weights and biases of a perceptron or MLP is known as training. The perceptron algorithm (for training simple perceptrons) consists of comparing the output of the perceptron with an associated target value. The most common training algorithm for MLPs is BP which is an extended form of the method used to train the perceptron. This algorithm entails a backward flow of the error corrections through each neuron in the network. In the most basic form, an ANN requires an input and should be associated with a reference which it tracks during each training iteration. The output, at the end of each training epoch, is compared with the reference and a corresponding adaptation of the connectionist weights are carried out. This is repeated till the output of the ANN is nearly equal to that of the reference. One cycle through the complete training set forms one epoch. The above is repeated till MSE meets the performance criteria. While repeating the above the number of epoch elapsed is counted. A few methods used for MLP training includes Gradient Descent BP (GDBP), Gradient Descent with Momentum BP (GDMBP), Gradient Descent with Adaptive Learning Rate BP (GDALRBP), Gradient Descent with Adaptive Learning Rate and Momentum BP (GDALMBP) and Gradient Descent with LevenbergMarquardt BP (GDLMBP).
Is BP equal to supervised learning algorithm
BP is a supervised learning algorithm that learns a function f (·): Rm → Ro by training on a data set, where m is the number of dimensions for input and o is the number of dimensions for output.
Answer Each Question (3 points each) • Describe the derivation of BP algorithm. • Is BP...
Analytics question: Describe the relationship between a supervised learning classifier and a set of linear equations.
Analytics question: Describe the relationship between a supervised learning classifier and a set of linear equations.
For the following set of points, describe how the CLOSEST-PAIR algorithm finds a closest pair of points: (3) (3,2),(2,1),(2,3),(1,2),(3,1),(2,2),(1,3),(3,−1),(5,−2)
Describe at least 3 physiologic variables that can change BP. How do these factors influence BP (raise or lower) and why/how?
3. [15 marks] Describe an algorithm in pseudocode that locates an element in a list of increasing integers by successively splitting the list into four sublists of equal size (or as close to equal size as possible) and restricting the search to the appropriate piece. procedure tetrary search(x: integer, a1, a2, ..., an: increasing integers) (location is the subscript of the term equal to x, or 0 if not found) 3. [15 marks] Describe an algorithm in pseudocode that locates...
9. (5 points) Please describe an algorithm that takes as input a list of n integers and finds the number of negative integers in the list. 10. (5 points) Please devise an algorithm that finds all modes. (Recall that a list of integers is nondecreasing if each term of the list is at least as large as the preceding term.) 11. (5 points) Please find the least integer n such that f() is 0(3") for each of these functions f()...
2. Describe why finding a polynomial-time algorithm for a NP-complete problem would answer the question if P = NP. What would the answer be? (7-10 sentences minimum)
Dijkstra's Algorithm Using the following graph, please answer each question below. Dijkstra's Algorithm 5) Consider the following graph: 80 70 90 60 10 Use Dijkstra's algorithm to find the costs of the shortest paths from A to each of the other vertices. Show your work at every step. a. b. Are any of the costs you computed using Dijkstra's algorithm in part (a) incorrect? Why or whynot? Explain how you can use Dijkstra's algorithm the recover the actual paths...
Question 24 (4 points) Describe the "structural cap model" for microtubules and the basis for the "catastrophic disassembly of the microtubule bp.
Question 9 0 / 10 points Describe the basic operations that can be performed on a stack. Write an algorithm (using bullet points or a description, not Java or C) which shows how to remove an item from a stack that is implemented as an array. No text entered - This question has not been graded. The correct answer is not displayed for Written Response type questions. Question 10 0 / 10 points What are the main characteristics of a...