Innovative Neural Networks technologies:
1. Constructing baseline probability with auto-search logistic regression.
2. Handling complex problems with clustering analysis.
3. Improving training by escaping most of local minima.
4. Preventing overfit by monitoring MLP's free parameters.
5. Fast training to generate acceptable models.
6. Scalable.
Publications:
1. Chen H.H., Manry, M.T.: Improving Healthcare Predictive Modeling using NeuroSequences. In: 16th Federal Forecasters Conference, in press (2008)
2. Chen, H.H., The Turning Points on MLP’s Surface, Lecture Notes in Computer Sciences 5263: ISNN 2008, Part I, 2008, pp. 512-520.
3. Chen, H.H., Monitoring MLP’s Free Parameters for Generalization, accepted by The 8th WSEAS International Conference on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING and DATA BASES (AIKED'09).
4. Chen, H.H., Fast Training MLP Networks with Lo-Shu Data Sampling, accepted by The 8th WSEAS International Conference on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING and DATA BASES (AIKED'09).
Presentations:
1. Improving Healthcare Predictive Modeling using NeuroSequences.
2. The Turning Points on MLP’s Surface