Extracting motion saliency features from video using a neurosynaptic system

A system for sense-response in a robotic environment, comprising:

• at least one processor;
• and
• a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform instructions including:
• utilizing one or more neurosynaptic core circuits to perform operations including:
• generating one or more neuronal firing events based on input data comprising one or more sensory inputs;
• extracting one or more saliency features from the input data based on the one or more neuronal firing events;
• and
• generating output data comprising one or more motor outputs based on the one or more saliency features;
• wherein each neurosynaptic core circuit comprises a plurality of electronic neurons, a plurality of electronic axons, and a plurality of electronic synapse devices interconnecting the electronic neurons with the electronic axons.

A computer-readable medium storing instructions that, when executed by at least one processor of a machine, cause the machine to perform a method for sense-response in a robotic environment, the method comprising:

• utilizing one or more neurosynaptic core circuits to perform operations including:
• generating one or more neuronal firing events based on input data comprising one or more sensory inputs;
• extracting one or more saliency features from the input data based on the one or more neuronal firing events;
• and
• generating output data comprising one or more motor outputs based on the one or more saliency features;
• wherein each neurosynaptic core circuit comprises a plurality of electronic neurons, a plurality of electronic axons, and a plurality of electronic synapse devices interconnecting the electronic neurons with the electronic axons.