Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks and classification techniques. Rather than adjusting the weights in a network of predefined topology, Cascade-Correlation begins with a minimal network and it automatically trains, adds new hidden units one after the other by creating a multi-layer structure. As soon as a new hidden unit has been added to the network, its input-side weights are getting fixed. After that these unit then becomes a permanent feature-identifier in the network, present for producing outputs, then cascade-correlation is behaves as more complex feature detectors. The Cascade-Correlation networks have several benefits over existing algorithms as it learns very fast. It determines its own size and topology fast. It maintains the structures which it has built even after the training set changes, and it doesn't need back-propagation of error signals through the connections of the network and its component. Cascade Correlation Neural Network (CCNN) types such as recurrent CCNN, evolving CCNN, genetic CCNN are used to predict software effort from Use Case diagrams in advance manner which helps further for software cost estimation. The use case diagrams are developed in the early stages of the software development and they are used for input. This paper is an overview of cascade-correlation neural networks in which we study different types of cascade-correlation neural network. They are based on a special architecture which autonomously adapts to the application and makes the training much more efficient than the widely used backpropagation algorithm. This review focuses on different types of CCNN and also describes the cascade-correlation architecture variants.

1. Kurt Hornik, Maxwell Stinchcombe, and Halbert White. Multilayer Feedforward Networks Are Universal Approximators. Neural Networks Vol. 2, Issue 5, pages 359–366, 1989
2. Scott E. Fahlman. Faster-Learning Variations on Back-Propagation: An Empirical Study. Proceedings1988 Connectionist Models Summer School, pages 38–51, 1988.
3. Scott E. Fahlman and Christian Lebiere. The Cascade- Correlation Learning Architecture. D. S. Touretzky (ed. ), Advances in Neural Information Processing Systems 2, pages 524–532, 1990.
4. Jean-Philippe Thivierge, Fracois Rivest, and Thomas R. Schultz. A Dual-Phase Technique for Pruning Constructive Networks. Proceedings of the International Joint Conference on Neural Networks, 2003.
5. Steffen Nissen. Large Scale Reinforcement Learning using Q-SARSA and Cascading Neural Networks. MSc Thesis, University of Copenhagen, 2007.
6. Dale Schuurmans and Finnegan Southey. Metric-Based Methods for Adaptive Model Selection and Regularization. Machine Learning, 48, pages 51–84, 2002.
7. Shumeet Baluja and Scott E. Fahlman. Reducing Network Depth in the Cascade-Correlation Network Architecture. Technical Report CMU-CS-94-209, 1994.
8. Scott E. Fahlman. The Recurrent Cascade-Correlation Architecture. D. S. Touretzky (ed. ), Advances in Neural Information Processing Systems 3, pages 190–196, 1991.
9. Schetinin, V. : Polynomial neural networks for classifying EEG signals, In: Proceedings of NIMIA-SC2001 NATO Advanced Study Institute on Neural Networks for Instrumentation, Measurement, and Related Industrial Applications, Crema, Italy, 2001.
10. Müller JA, Lemke F. Self-Organizing Data Mining: Extracting Knowledge from Data. Trafford Publishing, Canada, 2003
11. Thomas R. Schultz, Francois Rivest, L´aszl´o Egri, Jean-Philippe Thivierge, and Fr´ed´eric Dandurand. Could Knowledge-based Neural Learning Be Useful in Developmental Robotics? The Case of KBCC. International Journal of Humanoid Robotics Vol. 4, No. 2, pages 245–279, 2007
12. M. Azzeh, D. Neagu and P. Cowling, "Fuzzy grey relational analysis for software effort estimation," Empirical Software Engineering, vol. 15, pp. 60-90, 2010.
13. M. Azzeh, D. Neagu and P. I. Cowling, "Analogy-based software effort estimation using Fuzzy numbers," Journal of Systems and Software, vol. 84, pp. 270-284, 2011.
14. A. Idri, A. Zakrani and A. Zahi, "Design of Radial Basis Function Neural Networks for Software Effort Estimation," International Journal of Computer Science Issues, vol. 7, pp. 11-17, 2010.
15. C. Lopez-Martin, "A fuzzy logic model for predicting the development effort of short scale programs based upon two independent variables," Applied Soft Computing, vol. 11, pp. 724- 732, 1, 2011.
16. C. Lopez-Martin, "Applying a general regression neural network for predicting development effort of short-scale programs," Neural Computing & Applications, vol. 20, pp. 389- 401, 2011.
17. C. Lopez-Martin, C. Isaza and A. Chavoya, "Software development effort prediction of industrial projects applying a general regression neural network," Empirical Software Engineering, vol. 17, pp. 1-19, 2011.
18. W. L. Du, D. Ho and L. F. Capretz, "Improving Software Effort Estimation Using Neuro-Fuzzy Model with SEER-SEM," Global Journal of Computer Science and Technology, vol. 10, pp. 52-64, 2010.
19. Y. Li, M. Xie and T. Goh, "Adaptive ridge regression system for software cost estimating on multi-collinear datasets," Journal of Systems and Software, vol. 83, pp. 2332-2343, 2010.
20. G. Kousiouris, T. Cucinotta and T. Varvarigou, "The effects of scheduling, workload type and consolidation scenarios on virtual machine performance and their prediction through optimized artificial neural networks," Journal of Systems and Software, vol. 84, pp. 1270-1291, 2011.
21. X. Huang, D. Ho, J. Ren and L. F. Capretz, "Improving the COCOMO model using a neuro-fuzzy approach," Appl. Soft Comput. , vol. 7, no. 1, pp. 29-40, 2007.
22. A. Mittal, K. Parkash and H. Mittal, "Software cost estimation using fuzzy logic," SIGSOFT Softw. Eng. Notes, vol. 35, no. 1, pp. 1-7, 2010.
23. A. B. Nassif, D. Ho and L. F. Capretz, "Regression model for software effort estimation based on the use case point method," in 2011 International Conference on Computer and Software Modeling, Singapore, 2011, pp. 117-121.
24. A. B. Nassif, L. F. Capretz and D. Ho, "Estimating software effort based on use case point model using sugeno fuzzy inference system," in 23rd IEEE International Conference on Tools with Artificial Intelligence, Florida, USA, 2011, pp. 393-398.
25. A. B. Nassif, L. F. Capretz and D. Ho, " Software Effort Estimation in the Early Stages of the Software Life Cycle Using a Cascade Correlation Neural Network Model," in 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, Las Vegas, U. S. A, 2012, pp. 393-398
26. Vitaly Schetinin, "A Learning Algorithm for Evolving Cascade Neural Networks," in TheorieLabor, Friedrich-Schiller University of Jena Ernst-Abbe-Platz 4, 07740 Jena, Germany
27. Vitaly Schetinin, "An Evolving Cascade Neural Network Technique for Cleaning Sleep Electroencephalograms," in Computer Science Department, University of Exeter, Exeter, EX4 4QF, UK
28. G´abor Bal´azs, "Cascade-Correlation Neural Networks: A Survey," in Department of Computing Science, University of Alberta, Edmonton, Canada
29. Mitchell A. Potter, "A Genetic Cascade-Correlation Learning Algorithm," in Computer Science Department George Mason University Fairfax, VA 22030 USA

Neural Network Cascade Architecture Evolving.