Learning in time varying, dissipative electrical networks

A system, comprising:

• a dissipative learning network characterized by an action and having a trajectory corresponding to at least one input signal, the dissipative learning network including a plurality of neuron banks and a plurality of weighting arrays, at least one of the plurality of weighting arrays being between a first neuron bank and a second neuron bank of the plurality of neuron banks, at least one of the plurality of neuron banks or the plurality of weighting arrays including an electrical component that dissipates energy, the trajectory including a plurality of states of the dissipative learning network for a first plurality of times and being for at least one input signal;
• loss circuitry selectively connectable to the dissipative learning network, the loss circuitry providing a perturbed trajectory for the dissipative learning network based on a plurality of target outputs and the at least one input signal, the perturbed trajectory including a plurality of perturbed states of the dissipative learning network for a second plurality of times based on the plurality of target outputs and being for the at least one input signal;
• and
• gradient estimator coupled with the dissipative learning network, wherein the gradient estimator determines gradients for a portion of the dissipative learning network based on the trajectory and the perturbed trajectory and adjusts the portion of the dissipative learning network based on the gradients, the portion of the dissipative learning network including the plurality of weighting array.

A method, comprising:

• determining a trajectory for a dissipative learning network, the dissipative learning network including a plurality of neuron banks and a plurality of weighting arrays, at least one of the plurality of weighting arrays being between a first neuron bank and a second neuron bank of the plurality of neuron banks, at least one of the plurality of neuron banks or the at least one weighting array including an electrical component that dissipates energy, the trajectory including a plurality of states of a plurality of electrical components in the dissipative learning network for a first plurality of times and being in response to at least one input signal, the dissipative learning network being characterized by an action;
• determining a perturbed trajectory for the dissipative learning network based upon a loss function for a plurality of target outputs and the at least one input signal, the perturbed trajectory including a plurality of perturbed states of the plurality of electrical components in the dissipative learning network for a second plurality of times;
• and
• adjusting a portion of the dissipative learning network based on the trajectory and the perturbed trajectory such that a minimum of the action corresponds to a loss function minimum.