Neural Networks and Continuous Time
This addresses a gap in neural network modeling for continuous-time applications, but it is incremental as it builds on existing hybrid automata models.
The paper argues that standard neural networks cannot directly model continuous-time processes, which are common in technical, physical, and cognitive domains, and proposes using neural networks with continuous-time architectures to enable synthesis and analysis of such processes, such as for robot behavior.
The fields of neural computation and artificial neural networks have developed much in the last decades. Most of the works in these fields focus on implementing and/or learning discrete functions or behavior. However, technical, physical, and also cognitive processes evolve continuously in time. This cannot be described directly with standard architectures of artificial neural networks such as multi-layer feed-forward perceptrons. Therefore, in this paper, we will argue that neural networks modeling continuous time are needed explicitly for this purpose, because with them the synthesis and analysis of continuous and possibly periodic processes in time are possible (e.g. for robot behavior) besides computing discrete classification functions (e.g. for logical reasoning). We will relate possible neural network architectures with (hybrid) automata models that allow to express continuous processes.