ORBAI files patent on NeuroCAD
15 Jun, 2019
11 June 2019: ORBAI filed a full patent on our NeuroCAD tools, and the process and methods for designing, training, and evolving spiking neural networks towards specific functions like vision, speech, cognition, and control.
APPARATUS AND METHOD FOR UTILIZING A PARAMETER GENOME CHARACTERIZING NEURAL NETWORK CONNECTIONS AS A BUILDING BLOCK TO CONSTRUCT A NEURAL NETWORK WITH FEEDFORWARD AND FEEDBACK PATHS
This invention is in the field of artificial neural networks. We disclose novel methods for characterizing the connectome of such neural networks with a compact parameter genome, methods for algorithmically expanding it to the full connectome, and training spiking neural networks with a novel feedback architecture, using both to do efficient genetic algorithms to evolve spiking neural networks to specific functionality. This uses genetic algorithms that rely upon biologically inspired operators, such as mutation, crossover and selection that are part of this process.