What's new in NeuroSolutions 6.21
Jan 4, 2013
New in NeuroSolutions 6.20 (Nov 2, 2012)
- With the release of NeuroSolutions 6.2, NeuroDimension is proud to announce NeuroSolutions CUDA Pro! NeuroSolutions CUDA Pro is the next evolution to our standard NeuroSolutions CUDA add-on which allows users to train on multiple NVIDIA graphics cards (Up to 4 GPU's) and also deploy their solution through the Custom Solution Wizard as a Windows-based DLL's OR through C++ Code Generation (for Windows) in the Developers level of NeuroSolutions to their own application with NVIDIA CUDA!
- The possibility is now real for users to see training speed improvements of over 100 times faster on networks using Levenberg-Marquardt - the most powerful form of back-propagation learning available.
New in NeuroSolutions 6.02 (Jul 24, 2010)
- Faster Processing:
- Improved utilization of multi-core processors and optimized executable code results in significantly shorter training times!
- Input Projection:
- Further reduce input dimensions by automatically mapping multiple pieces of information to single inputs.
- Input Optimization:
- Automatically determine the most informative inputs through greedy search, back-elimination and other methods.
New in NeuroSolutions 6.00 (May 17, 2010)
- Faster Processing:
- Improved utilization of multi-core processors and optimized executable code results in significantly shorter training times! Input Projection
- Further reduce input dimensions by automatically mapping multiple pieces of information to single inputs.
- Input Optimization:
- Automatically determine the most informative inputs through greedy search, back-elimination and other methods.
- Input Projection:
- Further reduce input dimensions by automatically mapping multiple pieces of information to single inputs.