Semantia

Semantia is the k-nearest neighbor classifier (artificial neural network) that forms the central associative processing module of CORTEX artificial intelligence systems. This comprehensive framework aims to provide researchers in the fields of AI, linguistics and animal communication with a powerful autonomous tool that simultaneously recognizes and associates patterns from multiple parallel stimuli.

Semantia automatically generates a neural network based on observed conversations. All associations are saved and built upon each time the app is opened unless the button "Clear Data" is clicked.

Semantia is like a child with no knowledge -- she learns everything she knows by interacting with the user. As her knowledge base grows, her statements become more coherent and unexpected.

Enabling Conversation Mode allows Semantia to provide syntax-free, child-like speech and text feedback triggered by speech input (Click "Listen" or enable Continuous Listening) Enabling Continuous Listening allows Semantia to learn by "eavesdropping" on any speech input -- from the user, radio, television, etc.

If Semantia is left unattended, Conversation Mode should be disabled to maximize learning rate.
Use voice command "close" to automatically generate a text file containing neural weights, connections and activations (array.txt in top SD directory) which can be used to generate neural networks for conversational AI or imported into a network analysis tool such as NodeXL.