Runtime control of internal activation pathways in artificial neural networks

A method, performed by a processing device, comprising:

• receiving, during inference of an artificial neural network processing an input, activation data comprising intermediate numerical representations produced by one or more internal layers of the artificial neural network;
• determining, based on the activation data, an internal activation pathway within the artificial neural network, the internal activation pathway corresponding to a constraint set defining permissible activation behavior;
• and
• generating an output of the artificial neural network based at least in part on the activation data and the constraint set corresponding to the internal activation pathway.

A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

• receive, during inference of an artificial neural network processing an input, activation data comprising intermediate numerical representations produced by one or more internal layers of the artificial neural network;
• determine, based on the activation data, an internal activation pathway within the artificial neural network, the internal activation pathway corresponding to a constraint set defining permissible activation behavior;
• and
• generate an output of the artificial neural network based at least in part on the activation data and the constraint set corresponding to the internal activation pathway.