A Solvable Molecular Switch Model for Stable Temporal Information Processing
This provides theoretical support for using dynamic molecular switches in neuromorphic architectures, potentially inspiring more general solvable models for brain-inspired computation.
The paper tackles the problem of stable temporal information processing in neuromorphic computing by analyzing an exactly solvable molecular switch model, showing it possesses convergence and fading memory properties that enable stable learning on sequential data.
This paper studies an input-driven one-state differential equation model initially developed for an experimentally demonstrated dynamic molecular switch that switches like synapses in the brain do. The linear-in-the-state and nonlinear-in-the-input model is exactly solvable, and it is shown that it also possesses mathematical properties of convergence and fading memory that enable stable processing of time-varying inputs by nonlinear dynamical systems. Thus, the model exhibits the co-existence of biologically-inspired behavior and desirable mathematical properties for stable learning on sequential data. The results give theoretical support for the use of the dynamic molecular switches as computational units in deep cascaded/layered feedforward and recurrent architectures as well as other more general structures for neuromorphic computing. They could also inspire more general exactly solvable models that can be fitted to emulate arbitrary physical devices which can mimic brain-inspired behaviour and perform stable computation on input signals.