Trending Technology Machine Learning, Artificial Intelligent, Block Chain, IoT, DevOps, Data Science

Recent Post

Codecademy Code Foundations

Search This Blog

Artificial Neural Network Applications in the Real World

The Artificial Neural Network has seen an explosion of interest over the last few years and is being successfully applied across an extra ordinary range of problem domains in the area such as Handwriting Recognition, Image compression, Traveling Salesman problem, stock Exchange prediction etc. In this Machine Learning Blog, We will discuss all these Artificial Neural Network Applications in detail.

2. Artificial Neural Network Applications

As we have already seen the introduction to Artificial neural networks, let us now see the major Artificial Neural Network Applications.
  • Handwriting Recognition – The idea of Handwriting recognition has become very important. This is because handheld devices like the Palm Pilot are becoming very popular. Hence, we can use Neural networks to recognize handwritten characters.
  • Traveling Salesman Problem – Neural networks can also solve the traveling salesman problem. But this is to a certain degree of approximation only.
  • Image Compression – Vast amounts of information is received and processed at once by neural networks. This makes them useful in image compression. With the Internet explosion and more sites using more images on their sites, using neural networks for image compression is worth a look.
  • Stock Exchange Prediction – The day-to-day business of the stock market is very complicated. Many factors weigh in whether a given stock will go up or down on any given day. Thus, Neural networks can examine a lot of information in a fast manner and sort it all out. So we can use them to predict stock prices since

Below is the description of every ANN application to get the proper understanding

2.1. Handwriting Recognition

The idea of using feed forward networks to recognize handwritten characters is straightforward. The bitmap pattern of the handwritten character is input, with the correct letter or digit as the desired output. Such programs need the user to train the network by providing the program with their handwritten patterns.

The two common applications of handwriting recognition are:

  • Optical character recognition for data entry
  • Validation of signatures on bank cheque

Feed-forward networks have the following characteristics:

a. First, they arrange perceptrons in layers, with the first layer taking in inputs and the last layer producing outputs. The middle layers have no connection with the external world, and hence we call them hidden layers.

b. Each perceptron in one layer is connected to every perceptron on the next layer. Hence information is “fed forward” from one layer to the next in a continuous manner. This explains why we call these networks feed-forward networks.

c. There is no connection among perceptrons in the same layer.

2.2. Traveling Salesman Problem

The traveling salesmen problem refers to the finding the shortest possible path to travel all cities in a given area. We can use Neural Networks to solve this problem.

A neural network algorithm such as genetic algorithm starts with random orientation of the network, to solve the problem. This algorithm chooses a city in a random manner each time and finds the nearest city. Thus, this process continues several times. After every iteration, the shape of the network changes and network converges to a ring around all the cities.

The used algorithm minimizes the length of rings. In this way, we can estimate the traveling problem.

2.3. Image Compression

A Neural Network used for image compression contain the equal size of input and output layer. The intermediate layer is of smaller size. The ratio of the input layer to the intermediate layer is the compression ratio of the network.

We can get the comparison ratio for image compression using the following formula:

Comparison Ratio = Input Layer / Intermediate Layer

Idea behind data compression neural networks is to store, encrypt and re-create the actual image again. Thus in such network, we can use input for training purposes itself.

2.4. Stock Exchange Prediction

The prediction accuracy of neural networks has made them useful in making a stock market prediction. For large business companies, making predictions for stock exchange is common. This is by using parameters, such as current trends, political situation, public view, and economists’ advice.

We can also use neural networks in currency prediction, business failure prediction, debt risk assessment, and credit approval.

No comments:

Post a Comment

Popular Articles