In this Machine Learning tutorial, we will cover the top Neural Network Algorithms. These algorithms are used to train the Artificial Neural Network. This blog provides you a deep learning of the Gradient Descent, Evolutionary Algorithms, and Genetic Algorithm in Neural Network.
2. 1. Objective
In this Machine Learning tutorial, we will cover the top Neural Network
Algorithms. These algorithms are used to train the Artificial Neural
Network. This blog provides you a deep learning of the Gradient
Descent, Evolutionary Algorithms, and Genetic Algorithm in Neural
Network.
2. Top Neural Network Algorithms
Learning of neural network takes place on the basis of a sample of the
population under study. During the course of learning, compare the value
delivered by output unit with actual value. After that adjust the weights of
all units so to improve the prediction.
There are many Neural Network Algorithms are available for
training Artificial Neural Network. Let us now see some important
Algorithms for training Neural Networks:
3. • Gradient Descent – Used to find the local minimum of a function.
• Evolutionary Algorithms – Based on the concept of natural selection
or survival of the fittest in Biology.
• Genetic Algorithm – Enable the most appropriate rules for the
solution of a problem and select it. So, that they send their ‘genetic
material’ to ‘child’ rules. We will learn about them in details below.
Get the introduction of learning rules in Neural Network for more
understanding of Neural Network Algorithms.
2.1. Gradient Descent
We use the gradient descent algorithm to find the local smallest of a
function. This algorithm converges to the local smallest. By approaching
proportional to the negative of the gradient of the function. To find local
maxima, take the steps proportional to the positive gradient of the
function. This is gradient ascendant process.
In linear models, error surface is well defined and well known
mathematical object in shape of a parabola. Then find the least point by
calculation. Unlike linear models, neural networks are complex nonlinear
models. Here, the error surface has an irregular layout, crisscrossed with
hills, valleys, plateau, and deep ravines. To find the least point on this
surface, for which no maps are available, the user must explore it.
In this algorithm, you move over the error surface by following the line
with the greatest slope. It also offers the possibility of reaching the lowest
possible point. You then have to work out at the optimal rate at which you
should travel down the slope.
The correct speed is proportional to the slope of the surface and the
learning rate. Learning rate controls the extent of modification of the
weights during the learning process.
Hence, the moment of a neural network can affect the performance
of multilayer perceptron.
2.2. Evolutionary Algorithms
This algorithm based on the concept of natural selection or survival of the
fittest in Biology. Concept of natural selection states that – for a given
4. population, environment conditions use a pressure that results in the
rise of the fittest in that population.
To measure fittest in a given population, you can apply a function as an
abstract measure.
In the context of evolutionary algorithms, refer recombination to as an
operator. Then apply it to two or more candidates known as parents, and
result in one of more new candidates known as children. Apply the
mutation on a single candidate and results in a new candidate. By applying
recombination and mutation, we can get a set of new candidates to place in
the next generation based on their fittest measure.
The two basic elements of evolutionary algorithms are:
• Variation operators (recombination and mutation)
• Selection process (selection of the fittest)
The common features of evolutionary algorithms are:
• Evolutionary algorithms are population based.
• Evolutionary algorithms use recombination mix candidates of a
population and create new candidates.
• On random selection evolutionary algorithm based.
Hence, on the basis of details and applied problems, we use various
formats of evolutionary algorithms.
Some common evolutionary algorithms are:
• Genetic Algorithm Genetic Algorithm – It provides the solution for
optimization problems. It provides the solution by the help of
natural evolution processes. Like mutation, recombination,
crossover, and inheritance.
• Genetic Programming – The genetic programming provides a
solution in the form of computer programs. By the ability to solve
computational problems accuracy of a program measures.
• Evolutionary Programming – In a simulated environment to develop
the AI we use it.
• Evolution Strategy It is an optimization algorithm. Grounded on the
concepts of the adaptation and the evolution in biological science.
5. • Neuroevolution – To train neural networks we uses
Neuroevolution. By specifying structure and connection weights
genomes uses to develop neural networks.
In all these algorithms, genetic algorithm is the most common evolutionary
algorithm.
2.3. Genetic Algorithm
Genetic algorithms, developed by John Holland’s group from the early
1970s. It enables the most appropriate rules for the solution of a problem
to be selected. So that they send their ‘genetic material’ (their variables
and categories) to ‘child’ rules.
Here refer a as a set of categories of variables. For example, customers
aged between 36 and 50, having financial assets of less than $20,000 and a
monthly income of more than $2000.
A rule is the equal of a branch of a decision tree; it is also analogous to a
gene. You can understand genes as units inside cells that control how
living organisms inherit features of their parents. Thus, Genetic algorithms
aim to reproduce the mechanisms of natural selection. By selecting the
rules best adapted to prediction and by crossing and mutating them until
get a predictive model.
Together with neural networks, they form the second type of algorithm.
Which mimics natural mechanisms to explain phenomena that are not
necassary natural.
The steps for executing genetic algorithms are:
• Step 1: Random generation of initial rules – Generate the rules first
with the constraint being that they must be all distinct. Each rule
contains a random number of variables chosen by user.
• Step 2: Selection of the best rules – Check the Rules in view of the
aim by fitness function to guide the evolution toward the best rules.
Best rules maximize the fitness function and retain with probability
that increases as the rule improves. Some rules will disappear while
others select several times.
6. • Step 3: Generation of new rules by mutation or crossing – First, go
to step 2 until the execution of the algorithm stops. Chosen rules
are randomly mutated or crossed. Mutation is replacement of a
variable or a category of original rule with another.
Crossing of 2 rules is exchange of some of their variables or categories to
produce 2 new rules. Crossing is more common than mutation.
Algorithm ends when 1 of the following 2 conditions meets:
• Specified number of iterations that reached.
• Starting from generation of rank n, rules of generations n, n-1 and
n-2 are (almost) identical.
3. Conclusion
In Conclusion, Artificial Neural Network is typically difficult to configure
and slow to train, but once prepared are very fast in the application. They
are generally designed as models to overcome the mathematical,
computational, and engineering problems. Since, there is a lot of research
in mathematics, neurobiology and computer science.
If you’d like to share your opinion and have any query about Artificial
Neural Network Algorithms, please do so in the comment section.