Self-learning physical reservoir computer.

A self-learning physical reservoir computer is demonstrated using an adaptive oscillator. Whereas physical reservoir computing repurposes the dynamics of a physical system for computation through machine learning, adaptive oscillators can innately learn and store information in plastic dynamic states. The adaptive state(s) can be used directly as physical node(s), but these plastic states can also be used to self-learn the optimal reservoir parameters for more complex tasks requiring virtual nodes from the base oscillator.

Multiplex-free physical reservoir computing with an adaptive oscillator.

Nonlinear oscillators can often be used as physical reservoir computers, in which the oscillator's dynamics simultaneously performs computation and stores information. Typically, the dynamic states are multiplexed in time, and then machine learning is used to unlock this stored information into a usable form. This time multiplexing is used to create virtual nodes, which are often necessary to capture enough information to perform different tasks, but this multiplexing procedure requires a relatively high sampling rate.

Hopf physical reservoir computer for reconfigurable sound recognition.

The Hopf oscillator is a nonlinear oscillator that exhibits limit cycle motion. This reservoir computer utilizes the vibratory nature of the oscillator, which makes it an ideal candidate for reconfigurable sound recognition tasks. In this paper, the capabilities of the Hopf reservoir computer performing sound recognition are systematically demonstrated.

Field-programmable analog array (FPAA) based four-state adaptive oscillator for analog frequency analysis.

Adaptive oscillators are a subset of nonlinear oscillators that can learn and encode information in dynamic states. By appending additional states onto a classical Hopf oscillator, a four-state adaptive oscillator is created that can learn both the frequency and amplitude of an external forcing frequency. Analog circuit implementations of nonlinear differential systems are usually achieved by using operational amplifier-based integrator networks, in which redesign procedures of the system topology is time consuming.

Genetic algorithm shape optimization to manipulate the nonlinear response of a clamped-clamped beam.

Dynamical systems, which are described by differential equations, can have an enhanced response because of their nonlinearity. As one example, the Duffing oscillator can exhibit multiple stable vibratory states for some external forcing frequencies. Although discrete systems that are described by ordinary differential equations have helped to build fundamental groundwork, further efforts are needed in order to tailor nonlinearity into distributed parameter, continuous systems, which are described by partial differential equations.

Dynamic effects on reservoir computing with a Hopf oscillator.

Limit cycle oscillators have the potential to be resourced as reservoir computers due to their rich dynamics. Here, a Hopf oscillator is used as a physical reservoir computer by discarding the delay line and time-multiplexing procedure. A parametric study is used to uncover computational limits imposed by the dynamics of the oscillator using parity and chaotic time-series prediction benchmark tasks.

A Hopf physical reservoir computer.

Physical reservoir computing utilizes a physical system as a computational resource. This nontraditional computing technique can be computationally powerful, without the need of costly training. Here, a Hopf oscillator is implemented as a reservoir computer by using a node-based architecture; however, this implementation does not use delayed feedback lines.

A four-state adaptive Hopf oscillator.

Adaptive oscillators (AOs) are nonlinear oscillators with plastic states that encode information. Here, an analog implementation of a four-state adaptive oscillator, including design, fabrication, and verification through hardware measurement, is presented. The result is an oscillator that can learn the frequency and amplitude of an external stimulus over a large range.