The Use of Artificial Neural Networks

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 4

COMP 427: NEURAL NETWORKS

ASSIGNMENT 1

COM/008/17

JOAN NANZALA SIMIYU

THE USE OF ARTIFICIAL NEURAL NETWORKS

According to Dr. Robert hecht-Nielsen, a neural network is a computing system made up of

simple, highly interconnected processing elements, which process information by their dynamic

state responses to external inputs. Neural networks have a variety of applications as explained

below.

ECOMMERCE

(Mach,2021) in his article, identifies that neural networks are used in ecommerce for various

purposes but more so in personalizing the purchaser’s experience. Platforms like Amazon show

related and recommended products based on the user’s behavior and related items. By this the

system remembers the customer’s preferences and show those items that meeting their needs.

STOCK EXCHANGE PREDICTION

This is common for large business companies. (DataFair team,2018) Neural networks can be

used in currency prediction, business failure prediction, debt risk assessment and credit approval

FINANCE

There exist neural network applications for fraud detection, management and forecasting. An

example is the SAS Real Time Decision Manager which helps banks to find solution to their

issues like whether or not they should give someone credit, risks and probable profits. The

counter propagation model is used here.


SECURITY

To ensure protection against computer viruses and fraud, neural networks are used. For example,

the ICSP Neural protects from cyber-attacks by determining the bad USB device containing

viruses and exploiting no vulnerabilities. The algorithm used here is the algorithm and least

mean square algorithm.

HANDWRITING RECOGNITION

Feedforward networks are used to recognize handwritten characters. Bitmap pattern of the

handwritten character is input and the desired output is the correct letter or digit. Thse needs the

user to train the network by providing the program with their handwritten patterns. Applications

of handwriting recognition include, optical character recognition for data entry and validation of

signatures on a bank cheque. The model used is the Neocogntition.

TRAVELLING SALESMAN PROBLEM

This refers to finding the shortest possible route to travel all cities in a given area. An algorithm

like a genetic algorithm solves this problem by random orientation of the network. It chooses a

city randomly every time and finds the nearest city severally. The shape of the network changes

after every iteration, the network converges to a ring around all the cities . This algorithm

reduces the length of rings , hence the travelling problem can be estimated.

IMAGE COMPRESSION

The idea behind data compression neural networks is to store, encrypt, and recreate the actual

image again. The neural network used here has equal size of input and output layer, intermediate

layer is of smaller size. Compression ratio of the network is the ratio of input layer to the

intermediate layer. The artificial neural network model used is the Hopefield.
MEDICAL APPLICATIONS

Artificial neural networks are used in detecting cancer cells and analyzing the MRI images in

order to give detailed results about the patient’s condition. The multilayer perceptron algorithm

is used to achieve this medical diagnosis (Berta W, 2019)

ENGINEERING APPLICATIONS

(Ramos, 2018), says Engineering is where neural network applications are essential, especially in

the high assuarance systems that have come up in different fields.

The engineering fields that make use of neural networks include:

Automotive; This includes the improved guidance systems, warranty activity analyzers, and

virtual sensors

Aerospace; Neural networks are used to detect fault in aircraft components, aircraft control

systems, flight path simulations and high performance auto-piloting

Manufacturing; Artificial neural networks are used in chemical product analysis, dynamic

modelling of chemical process systems, product design and analysis, visual quality inspection.
REFERENCES

Shahid N, Rappon T, Berta W (2019) Applications of artificial neural networks in health care

organizational decision-making: A scoping review. PLoS ONE 14(2): e0212356.

https://doi.org/10.1371/journal.pone.0212356

Smartsheet Contributor Diana Ramos on Oct 17, 2018

DataFlair team 2018

You might also like