@article{MAKHILLJEAS2019141318020,
    title = {Neural Networks in Business Applications},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {14},
    number = {13},
    pages = {4491-4500},
    year = {2019},
    issn = {1816-949x},
    doi = {jeasci.2019.4491.4500},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2019.4491.4500},
    author = {Mohammed Khawwam},
    keywords = {Artificial Neural Network (ANN),neuron,transfer functions,hidden lopper supervised training,momentum factor,training tolerance,backdrop,galion,cross-validation,jackknifing andbootstrapping},
    abstract = {Neural networks originally inspired from neuroscience provide powerful models for statistical data
analysis. Their most major feature is their ability to “learn” dependencies based on a finite number of
observations. In the context of neural networks the term “learning” means that the knowledge acquired from
the samples can be generalized to as yet, sense observation. In this sense, a neural network is often called a
learning machine. As such, neural networks might be considered as a symbol for an agent who learns
dependencies of his environment and thus, infers strategies of behavior based on al limited number of
observations. In this contribution, however, the researcher does not want to abstract from the biological origins
of neural network technique but present it as a purely mathematical model and also its statistical applications.}
    }