Page 214 - DCAP208_Management Support Systems

Unit 12: Applications of Neural Network

Notes
each model are shown. Increasing number of HLs show an improvement in performance,
as seen in plots for MLP- 1-B-L and MLP-2_B-L. Plots for best performing network, MLP-2-
O-M is also shown. Very good correlation was obtained for this network Highest accuracy
of 97-100% was obtained for LR-0-B-L/MLP- 2-O-M NNs.
A sensitivity analysis (SA) was performed on the results. SA is a valid tools for characterizing
uncertainty associated with a model. It orders by importance the strength and relevance of
inputs to determine the variation in output.
Question
Discuss the process of designing and training an MLP.

Source: http://psrcentre.org/images/extraimages/0112244.pdf
12.3 Summary

Neural networks outperformed regression analysis and other mathematical modeling
tools in predicting bond rating and profitability.

In general, ANN are suitable for problems whose inputs are both categorical and numeric,
and where the relationships between inputs and outputs are not linear or the input data
are not normally distributed.
Pattern recognition aims to classify data (patterns) based either on a priori knowledge or
on statistical information extracted from the patterns.

Artificial neural nets can be used for pattern recognition.
Although the chase behaviors are genuine data, the 3D structures, surface physics, and
shading are all purely for illustrative effect.

In photo realistic Virtual Reality (VR) environments, the need for quick feedback based on
user actions is crucial.

The goal of speech-driven facial animation is to synthesize realistic video sequences from
acoustic speech.
Galapagos is a fantastic and dangerous place where up and down have no meaning, where
rivers of iridescent acid and high-energy laser mines are beautiful but deadly artifacts of
some other time.

12.4 Keywords

Galapagos: Galapagos is a fantastic and dangerous place where up and down have no meaning,
where rivers of iridescent acid and high-energy laser mines are beautiful but deadly artifacts of
some other time.

Mendel: Mendel is a synthetic organism that can sense infrared radiation and tactile stimulus.
Neural Classifier: A neural classifier detects visibility of teeth edges and other attributes.
Pattern Recognition: Pattern Recognition can be defined as the act of taking in raw data and
taking an action based on the category of the pattern.
Pixel Map: The pixel map is a two dimensional function with two input variables: pixel position
and one output variable.

Radiosity: Radiosity models the actual interaction between the lights and the environment.

LOVELY PROFESSIONAL UNIVERSITY 207