´Chaotic relaxation´ in concurrently asynchronous neurodynamics

A mathematical framework for reconditioning additive-type models is proposed, and a neuro-operator, based on the chaotic relaxation paradigm, whose resulting dynamics is neither concurrently synchronous nor sequentially asynchronous is derived. Necessary and sufficient conditions guaranteeing concurrent asynchronous convergence are established in terms of contracting operators. Lyapunov exponents are also computed to characterize the network dynamics and to ensure that throughput-limiting chaotic behavior in models reconditioned with concurrently asynchronous algorithms has been eliminated.<>