Next: Neural Network Terminology
Up: LicensingCopying and
Previous: Acknowledgments
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:
- A new distributed version of the kernel. SNNS can now be spread
out in a workstation cluster for faster learning.`
- Improved version of the C-code generator snns2c
- Validation sets now can check on the performance of the network
during training.
- New error function in tool analyze that can handle
single-output-unit-networks.
- New statistic tool that can predict the generalization
capabilities of the network.
- New and improved remote panel.
- New learning algorithm RBF_DDA
- New learning algorithm simulated annealing
- New learning algorithm Monte Carlo.
- New learning algorithm Pruned-Cascade-Correlation
- Key codes to bring up all the main panels of SNNS (e.g Alt-R for the
remote panel).
- Support for NeXT systems.
- More information printed to the shell during training and with
the INFO button.
- Extensive debugging (as usual).
Niels Mache
Wed May 17 11:23:58 MET DST 1995