Stability and looping in connectionist models with asymmetric weights (Q1115639)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Stability and looping in connectionist models with asymmetric weights
scientific article

    Statements

    Stability and looping in connectionist models with asymmetric weights (English)
    0 references
    0 references
    1989
    0 references
    Recently, researchers in artificial intelligence have been actively investigating various connectionist models of computation. The model that is often studied is that of an asynchronous symmetric network, in which a global energy measure can be established and used to prove that the network totally stabilizes. We discuss asymmetric networks that might admit infinite activated computations. Within this framework, we define an operational semantics under a synchronous activation rule and similarly under a fair asynchronous rule. Using this semantics, we analyze flow properties of a circle-network with respect to a specification that characterizes oscillation. We further explore the complexity of the decidable question of whether or not a given asymmetric network totally stabilizes. It is shown that this problem is NP-hard, and is in PSPACE.
    0 references
    0 references
    neural networks
    0 references
    Hopfield model
    0 references
    stabilization of asymmetric network
    0 references
    decidability
    0 references
    connectionist models of computation
    0 references
    operational semantics
    0 references
    circle-network
    0 references
    NP-hard
    0 references
    PSPACE
    0 references
    0 references