Utilizing Time : Asynchronous Binding

Historically, connectionist systems have not excelled at representing and manipulating complex structures. How can a system composed of simple neuron-like computing elements encode complex relations? Recently, researchers have begun to appreciate that representations can extend in both time and space. Many researchers have proposed that the synchronous firing of units can encode complex representations. I identify the limitations of this approach and present an asynchronous model of binding that effectively represents complex structures. The asynchronous model extends the synchronous approach. I argue that our cognitive architecture utilizes a similar mechanism.