A Hopf physical reservoir computer

Physical Reservoir Computing Using van der Waals Ferroelectrics for Acoustic Keyword Spotting

Acoustic keyword spotting (KWS) plays a pivotal role in the voice-activated systems of artificial intelligence (AI), allowing for hands-free interactions between humans and smart devices through information retrieval of the voice commands. The cloud computing technology integrated with the artificial neural networks has been employed to execute the KWS tasks, which however suffers from propagation delay and the risk of privacy breach. Here, we report a single-node reservoir computing (RC) system based on the CuInP2S6 (CIPS)/graphene heterostructure planar device for implementing the KWS task with low computation cost. Through deliberately tuning the Schottky barrier height at the ferroelectric CIPS interfaces for the thermionic injection and transport of the electrons, the typical nonlinear current response and fading memory characteristics are achieved in the device. Additionally, the device exhibits diverse synaptic plasticity with an excellent separation capability of the temporal information. We construct a RC system through employing the ferroelectric device as the physical node to spot the acoustic keywords, i.e., the natural numbers from 1 to 9 based on simulation, in which the system demonstrates outstanding performance with high accuracy rate (>94.6%) and recall rate (>92.0%). Our work promises physical RC in single-node configuration as a prospective computing platform to process the acoustic keywords, promoting its applications in the artificial auditory system at the edge.

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. Both this self-learning property for reconfigurable computing and the morphable logic gate property of the adaptive oscillator make this an ideal candidate for a multipurpose neuromorphic processor.

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. Adaptive oscillators, which are a subset of nonlinear oscillators, have plastic states that learn and store information through their dynamics in a human readable form, without the need for machine learning. Highlighting this ability, adaptive oscillators have been used as analog frequency analyzers, robotic controllers, and energy harvesters. Here, adaptive oscillators are considered as a physical reservoir computer without the cumbersome time multiplexing procedure. With this multiplex-free physical reservoir computer architecture, the fundamental logic gates can be simultaneously calculated through dynamics without modifying the base oscillator.

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. This work shows that the Hopf reservoir computer can offer superior sound recognition accuracy compared to legacy approaches (e.g., a Mel spectrum + machine learning approach). More importantly, the Hopf reservoir computer operating as a sound recognition system does not require audio preprocessing and has a very simple setup while still offering a high degree of reconfigurability. These features pave the way of applying physical reservoir computing for sound recognition in low power edge devices.

Distinguishing artificial spin ice states using magnetoresistance effect for neuromorphic computing

Artificial spin ice (ASI) consisting patterned array of nano-magnets with frustrated dipolar interactions offers an excellent platform to study frustrated physics using direct imaging methods. Moreover, ASI often hosts a large number of nearly degenerated and non-volatile spin states that can be used for multi-bit data storage and neuromorphic computing. The realization of the device potential of ASI, however, critically relies on the capability of transport characterization of ASI, which has not been demonstrated so far. Using a tri-axial ASI system as the model system, we demonstrate that transport measurements can be used to distinguish the different spin states of the ASI system. Specifically, by fabricating a tri-layer structure consisting a permalloy base layer, a Cu spacer layer and the tri-axial ASI layer, we clearly resolve different spin states in the tri-axial ASI system using lateral transport measurements. We have further demonstrated that the tri-axial ASI system has all necessary required properties for reservoir computing, including rich spin configurations to store input signals, nonlinear response to input signals, and fading memory effect. The successful transport characterization of ASI opens up the prospect for novel device applications of ASI in multi-bit data storage and neuromorphic computing.

Reservoir computing with noise

This paper investigates in detail the effects of measurement noise on the performance of reservoir computing. We focus on an application in which reservoir computers are used to learn the relationship between different state variables of a chaotic system. We recognize that noise can affect the training and testing phases differently. We find that the best performance of the reservoir is achieved when the strength of the noise that affects the input signal in the training phase equals the strength of the noise that affects the input signal in the testing phase. For all the cases we examined, we found that a good remedy to noise is to low-pass filter the input and the training/testing signals; this typically preserves the performance of the reservoir, while reducing the undesired effects of noise.

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. Resonance, frequency ratios from the Farey sequence, and Arnold tongues were found to strongly affect the computation ability of the reservoir. These results provide insights into fabricating physical reservoir computers from limit cycle systems.

Enhancing the Recognition Task Performance of MEMS Resonator-Based Reservoir Computing System via Nonlinearity Tuning

Reservoir computing (RC) is a potential neuromorphic paradigm for physically realizing artificial intelligence systems in the Internet of Things society, owing to its well-known low training cost and compatibility with nonlinear devices. Micro-electro-mechanical system (MEMS) resonators exhibiting rich nonlinear dynamics and fading behaviors are promising candidates for high-performance hardware RC. Previously, we presented a non-delay-based RC using one single micromechanical resonator with hybrid nonlinear dynamics. Here, we innovatively introduce a nonlinear tuning strategy to analyze the computing properties (the processing speed and recognition accuracy) of the presented RC. Meanwhile, we numerically and experimentally analyze the influence of the hybrid nonlinear dynamics using the image classification task. Specifically, we study the transient nonlinear saturation phenomenon by fitting quality factors under different vacuums, as well as searching the optimal operating point (the edge of chaos) by the static bifurcation analysis and dynamic vibration numerical models of the Duffing nonlinearity. Our results in the optimal operation conditions experimentally achieved a high classification accuracy of (93 ± 1)% and several times faster than previous work on the handwritten digits recognition benchmark, profit from the perfect high signal-to-noise ratios (quality factor) and the nonlinearity of the dynamical variables.