Page 185 - DCAP208_Management Support Systems

Management Support Systems

Notes 11.1 Concept of Neural Network

Neural networks represent a brain metaphor for information processing. These models are
biologically inspired rather than an exact replica of how the brain actually functions. Neural
networks have been shown to be very promising systems in many forecasting applications and
business classification applications due to their ability to “learn” from the data, their
nonparametric nature (i.e., no rigid assumptions), and their ability to generalize. Neural
computing refers to a pattern recognition methodology for machine learning. The resulting
model from neural computing is often called an artificial neural network (ANN) or a neural
network.
11.1.1 Artificial Neural Network (ANN)

The human brain possesses bewildering capabilities for information processing and problem
solving that modern computers cannot compete with in many aspects. It has been postulated
that a model or a system that is enlightened and supported by the results from brain research,
with a structure similar to that of biological neural networks, could exhibit similar intelligent
functionality. Based on this bottom-up postulation, ANN (also known as connectionist models,
parallel distributed processing models, neuromorphic systems, or simply neural networks)
have been developed as biologically inspired and plausible models for various tasks.
Biological neural networks are composed of many massively interconnected primitive biological
neurons. Each neuron possesses axons and dendrites, finger-like projections that enable the
neuron to communicate with its neighboring neurons by transmitting and receiving electrical
and chemical signals. More or less resembling the structure of their counterparts, ANN are
composed of interconnected, simple processing elements called artificial neurons. In processing
information, the processing elements in an ANN operate concurrently and collectively in a
similar fashion to biological neurons. ANN possess some desirable traits similar to those of
biological neural networks, such as the capabilities of learning, self-organization, and fault
tolerance.
The formal study of ANN began with the pioneering work of McCulloch and Pitts in 1943.
Stimulated by results of biological experiments and observations, McCulloch and Pitts (1943)
introduced a simple model of a binary artificial neuron that captures some functions of a living
neuron. Considering information processing machines as a means for modeling the brain,
McCulloch and Pitts built their neural networks model using a large number of interconnected
binary artificial neurons. Led by a school of researchers, neural network research was quite
popular in the late 1950s and early 1960s.

Notes After a thorough analysis of an early neural network model (called the perceptron,
which used no hidden layer) as well as a pessimistic evaluation of the research potential
by Minsky and Papert in 1969, the interest in neural networks diminished.
During the past two decades, there has been an exciting resurgence in the studies of ANN due to
the introduction of new network topologies, new activation functions, and new learning
algorithms, as well as progress in neuroscience and cognitive science. On the one hand, advances
in theory and methodology have overcome many obstacles that hindered neural network research
a few decades ago. Evidenced by the appealing results of numerous studies, neural networks are
gaining acceptance and popularity. On the other hand, as complex problems solvers, ANN have
been applied to solve numerous problems in a variety of application settings. The desirable
features in neural information processing make neural networks attractive for solving complex

178 LOVELY PROFESSIONAL UNIVERSITY