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:

- 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.

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.

*Source for picture: click here*

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 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.
- 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.

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.
- 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.

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.

© 2020 Data Science Central ® Powered by

Badges | Report an Issue | Privacy Policy | Terms of Service

**Upcoming DSC Webinar**

**Your Model Will Probably Fail (And How to Prevent it)**- July 9

Data science is more popular than ever, but many data scientists struggle with complicated workflows to run their models as well as how to best communicate the output to less technical stakeholders. Tableau can solve both of these challenges by designing R workflows and creating visualizations that break complicated models down into easily understandable stories.**Register today**.

**Most Popular Content on DSC**

To not miss this type of content in the future, subscribe to our newsletter.

- Book: Statistics -- New Foundations, Toolbox, and Machine Learning Recipes
- Book: Classification and Regression In a Weekend - With Python
- Book: Applied Stochastic Processes
- Long-range Correlations in Time Series: Modeling, Testing, Case Study
- How to Automatically Determine the Number of Clusters in your Data
- New Machine Learning Cheat Sheet | Old one
- Confidence Intervals Without Pain - With Resampling
- Advanced Machine Learning with Basic Excel
- New Perspectives on Statistical Distributions and Deep Learning
- Fascinating New Results in the Theory of Randomness
- Fast Combinatorial Feature Selection

**Other popular resources**

- Comprehensive Repository of Data Science and ML Resources
- Statistical Concepts Explained in Simple English
- Machine Learning Concepts Explained in One Picture
- 100 Data Science Interview Questions and Answers
- Cheat Sheets | Curated Articles | Search | Jobs | Courses
- Post a Blog | Forum Questions | Books | Salaries | News

**Archives:** 2008-2014 |
2015-2016 |
2017-2019 |
Book 1 |
Book 2 |
More

**Upcoming DSC Webinar**

**Your Model Will Probably Fail (And How to Prevent it)**- July 9

Data science is more popular than ever, but many data scientists struggle with complicated workflows to run their models as well as how to best communicate the output to less technical stakeholders. Tableau can solve both of these challenges by designing R workflows and creating visualizations that break complicated models down into easily understandable stories.**Register today**.

**Most popular articles**

- Free Book and Resources for DSC Members
- New Perspectives on Statistical Distributions and Deep Learning
- Time series, Growth Modeling and Data Science Wizardy
- Statistical Concepts Explained in Simple English
- Machine Learning Concepts Explained in One Picture
- Comprehensive Repository of Data Science and ML Resources
- Advanced Machine Learning with Basic Excel
- Difference between ML, Data Science, AI, Deep Learning, and Statistics
- Selected Business Analytics, Data Science and ML articles
- How to Automatically Determine the Number of Clusters in your Data
- Fascinating New Results in the Theory of Randomness
- Hire a Data Scientist | Search DSC | Find a Job
- Post a Blog | Forum Questions

## You need to be a member of Data Science Central to add comments!

Join Data Science Central