Business Intelligence

Date: 2020-06-03

PLAGIARISM SCAN REPORT

Exclude Url : None

Content Checked For Plagiarism

What is ANN, and what are the commonalities and differences between biological and artificial neural networks? What types of business

problems can be solved with ANN? Artificial neural networks are an attempt to kindle the system of neurons that make up the human brain

to enable computers to learn and make a human-like judgment (Da Silva et al, 2017). This is essentially a software application or AIs

(Artificial intelligence) tool that is stimulated by brain structure, artificial neural network. Artificial neural networks are generated by

programming typical programs to act and trigger human behavior. Biological neurons are sophisticated components with internal machinery,

chemical, and mechanical processes that are focused on performing various tasks. Artificial neural networks derive a lot of their inspiration

from the biological nervous system. Commonalities and differences between biological and artificial neural networks Size: Artificial neural

networks' is far less than biological neurons. The human brain comprises eighty-six thousand neurons and an excess of a hundred

thousand billion connections whereas, in an artificial network, neurons are approximately between ten to one thousand (Richard, 2018).

Speed: Some biological neurons fires on average, about 1200 times a minute. Signals move at varying speeds subject to the form of the

nerve impulse, varying between 0.61 m / s upwards to 119 m / s. However, different factors such as age, sex, height, temperature, and

medical conditions influence the signal travel speed. Information in artificial neurons is instead carried over by the continuous floating-point.

This means that artificial neurons function faster than biological neurons as the artificial neuron networks are free from fatigue and the

calculation of artificial neurons can be performed multiple times and at a speed level permitted by computer systems. Fault-tolerance:

Biological neuron network is fault-tolerance due to its topology. Minor failure will not lose the memory as the information is stored

redundantly. Biological neuron does not have one central controller or a single central portion, and the brain can also recover and heal to an

extent. Networks in artificial neurons are not built for fault tolerance and they do not regenerate implying that fault-tolerance is not applicable

in ANNs and information cannot be retrieved. Learning Process: The learning process of ANNs is the modification of weight to the fixed

connections between neurons via a back-propagation algorithm in which neurons are altered either by adding or removing. The BNN

learning process reinforces the existing connections and makes a new connection via continuing and repeated stimulation. BNN has a

complex visual system While ANN visual system is more straightforward (Richard, 2018). Different types of business problem can be solved

with ANN as listed below: • Detecting Spam: Artificial neural networks aid in filtering junk emails and detect spam which helps individuals

and companies to protect vital information/data and emails regularly Sales Forecasting: Artificial neural networks are fundamental to

Artificial Intelligence. ANNs plays an important function in furcating business and aids in identifying market trends based on the history and

system (Livieris, et al., 2019) • Product promotion: ANNs assists in product promotion by tracking the purchase history of specific clients.

Moreover, ML models cab can help detect the consumer’s preference. ANN derives the pattern among the group of products based on the

customer’s daily transaction. Such act of tracking history helps to boost the product and enables to identify the target customers that highly

benefits to e-commerce business (Livieris, et al., 2019). References Richard, N. (2018). The differences between Artificial and Biological

Neural Networks. Towards Data Science, Towards Data Science, 4. Da Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H. B., & dos

Reis Alves, S. F. (2017). Artificial neural networks. Cham: Springer International Publishing, 39. Livieris, I. E., Kiriakidou, N., Kanavos, A.,

Vonitsanos, G., & Tampakas, V. (2019, May). Employing Constrained Neural Networks for Forecasting New Product’s Sales Increase.

In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 161-172). Springer, Cham.

35% Plagiarised

65% Unique

658 Words

4574 Characters

26% Plagiarised

Different types of business problem can be solved with ANN as listed below: Image of page 1. • Sales Forecasting : Artificial neural

networks are the core of ...

https://www.coursehero.com/file/54657640/What-is-ANNdocx/

3% Plagiarised

Sep 4, 2018 - Information in artificial neurons is instead carried over by the continuous, floating point number values of synaptic

weights. How quickly feedforward or backpropagation algorithms are calculated carries no information, other than making the

execution and training of the model faster.

https://towardsdatascience.com/the-differences-between-artificial-and-biological-neural-networks-a8b46db828b7

3% Plagiarised

May 15, 2019 - In this work, we evaluate the performance of weight-constrained neural networks for forecasting new product's sales

increase. These new prediction models are characterized by the application of conditions on the weights of the network in the form of

box-constraints, during the training process.

https://link.springer.com/chapter/10.1007/978-3-030-19909-8_14

3% Plagiarised

... Sales Increase. 15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019,

Hersonissos, Greece. pp.161-172, ...

https://hal.inria.fr/IFIP-AICT-560/hal-02363848