Technology

Sequentially Activated Neural Networking

sequentially activated neural network

*This software implements a sequentially activated neuronal input unsupervised learning algorithm. For an overview of BAI classical backpropagation ANN, see Classical Neural Networking.

BAI Sequentially Activated Neuronal Input technology includes the following features

  • Supports reading of networks from XML (computer/human readable format)
  • Supports unsupervised generation of SANI network from (textual) sequential input data
  • Supports definition of NLP combined syntactical-semantic parse trees
  • Operating system independent development - ISO C++ (currently available on Linux EL5/EL6/EL7/EL8/UB14/UB16/UB20 and Microsoft Windows XP/7/8/10)

For an overview of this technology, see the "Sequentially Activated Neuronal Input (SANI) neural network" video demonstration. This technology is not currently being maintained and it is recommended to use a modern vectorised and hardware accelerated implementation (e.g. TensorFlow/PyTorch).

Technology Name Support Source License Source Documentation
Sequentially Activated Neuronal Input (SANI) LinuxRed Hat LinuxUbuntu LinuxWin Proprietary (view source online) Auto Documentation