8.4 Training QNN with Particle Swarm Optimisation
Having specified the gradient descent scheme for training QNNs in the previous section, we now turn our attention to a non-differentiable learning method based on the powerful evolutionary search algorithm.
8.4.1 The Particle Swarm Optimisation algorithm
The Particle Swarm Optimisation (PSO) algorithm belongs to a wide class of evolutionary search heuristics where at each algorithm iteration ("generation" in the language of evolutionary algorithms), the population of solutions ("chromosomes" or "particles") is evaluated in terms of their fitness with respect to the environment. In the standard PSO formulation [258], a number of particles are placed in the solution space of some problem and each evaluates the fitness at its current location. Each particle then determines its movement through the solution space by combining some aspects of the history of its own fitness values with those of one or more...
