New Features of Release 4.0

Users already familiar with SNNS and its usage may be interested in the differences between the versions 3.3 and 4.0. New users of SNNS may skip this section and proceed with the next chapter.

New Features of Release 4.0:

1. A new distributed version of the kernel. SNNS can now be spread out in a workstation cluster for faster learning.`

2. Improved version of the C-code generator snns2c

3. Validation sets now can check on the performance of the network during training.

4. New error function in tool analyze that can handle single-output-unit-networks.

5. New statistic tool that can predict the generalization capabilities of the network.

6. New and improved remote panel.

7. New learning algorithm RBF_DDA

8. New learning algorithm simulated annealing

9. New learning algorithm Monte Carlo.

10. New learning algorithm Pruned-Cascade-Correlation

11. Key codes to bring up all the main panels of SNNS (e.g Alt-R for the remote panel).

12. Support for NeXT systems.

13. More information printed to the shell during training and with the INFO button.

14. Extensive debugging (as usual).