Artificial Neural Network: Usage
ARTIFICIAL NEURAL NETWORK: USE IN MANAGEMENT
Neuron Transfer Function:
The transfer function of a neuron is chosen to have a number of properties which either enhance or simplify the network containing the neuron. Crucially, for instance, any multilayer perceptron using a linear transfer function has an equivalent single-layer network; a non-linear function is therefore necessary to gain the advantages of a multi-layer network. Types of neuron transfer function
• Pure Linear Transfer Function
• Hard Limit Transfer Function
• Log Sigmoid Transfer Function
Neural Network Structures:
• Feed Forward Network - Information flow is unidirectional, information processing is parallel, memory less, cannot modify output based on error
• Recurrent ( or feedback) Network – Information travelling in both directions, learn from mistakes, dynamic in nature
• Feed Forward Back Propagation Network
How ANN Functions?
ANN functions through learning. Like human beings, ANN works by learning from its past experiences and mistakes. ANN is inspired by the learning processes that take place in biological systems.
utomating this are:
• Saving quality time
• Saving resources in terms of human resources and finance
• Eliminating human error
• Leveraging technology
• Having fairness in the process
The framework proposed extracts data from various data sets. For example, while recruiting employees in IT industries, the typical process is to take an aptitude test, followed by an interview process. It also takes into account the marks obtained in the engineering semesters. However, the weight age and pattern of marks varies from college to college within the country.
Supposing 100 applicants apply for 1 post gives us the ratio 1:100 and the number of candidates called for interview after the screening is 30, 20 or 10. Lesser the number of interviewees, more efficient is the process. Thus ANN should aim to reduce this ratio.
Data mining is the important
Neuron Transfer Function:
The transfer function of a neuron is chosen to have a number of properties which either enhance or simplify the network containing the neuron. Crucially, for instance, any multilayer perceptron using a linear transfer function has an equivalent single-layer network; a non-linear function is therefore necessary to gain the advantages of a multi-layer network. Types of neuron transfer function
• Pure Linear Transfer Function
• Hard Limit Transfer Function
• Log Sigmoid Transfer Function
Neural Network Structures:
• Feed Forward Network - Information flow is unidirectional, information processing is parallel, memory less, cannot modify output based on error
• Recurrent ( or feedback) Network – Information travelling in both directions, learn from mistakes, dynamic in nature
• Feed Forward Back Propagation Network
How ANN Functions?
ANN functions through learning. Like human beings, ANN works by learning from its past experiences and mistakes. ANN is inspired by the learning processes that take place in biological systems.
utomating this are:
• Saving quality time
• Saving resources in terms of human resources and finance
• Eliminating human error
• Leveraging technology
• Having fairness in the process
The framework proposed extracts data from various data sets. For example, while recruiting employees in IT industries, the typical process is to take an aptitude test, followed by an interview process. It also takes into account the marks obtained in the engineering semesters. However, the weight age and pattern of marks varies from college to college within the country.
Supposing 100 applicants apply for 1 post gives us the ratio 1:100 and the number of candidates called for interview after the screening is 30, 20 or 10. Lesser the number of interviewees, more efficient is the process. Thus ANN should aim to reduce this ratio.
Data mining is the important