Abstract
Preprocessing the data is an important step while creating neural network (NN) applications because this step usually has a significant effect on the prediction performance of the model. This paper compares different data processing strategies for NNs for prediction of Boolean function complexity (BFC). We compare NNs' predictive capabilities with (1) no preprocessing (2) scaling the values in different curves based on every curve's own peak and then normalizing to [0, 1] range (3) applying z-score to values in all curves and then normalizing to [0, 1] range, and (4) logarithmically scaling all curves and then normalizing to [0, 1] range. The efficiency of these methods was measured by comparing RMS errors in NN-made BFC predictions for numerous ISCAS benchmark circuits. Logarithmic preprocessing method resulted in the best prediction statistics as compared to other techniques.
Original language | English |
---|---|
Pages (from-to) | 519-526 |
Number of pages | 8 |
Journal | Expert Systems with Applications |
Volume | 36 |
Issue number | 1 |
DOIs | |
Publication status | Published - Jan 2009 |
Keywords
- Boolean function complexity
- Computer-aided design
- Data preprocessing
- Feed-forward neural network
- Machine learning
- Pattern recognition
ASJC Scopus subject areas
- Engineering(all)
- Computer Science Applications
- Artificial Intelligence