Fully Analog Resonant Recurrent Neural Network via Metacircuit
Physical neural networks offer a transformative route to edge intelligence, providing superior inference speed and energy efficiency compared to conventional digital architectures. However, realizing scalable, end-to-end, fully analog recurrent neural networks for temporal information processing remains challenging due to the difficulty of faithfully mapping trained network models onto physical hardware. Here we present a fully analog resonant recurrent neural network (R$^2$NN) implemented via a metacircuit architecture composed of coupled electrical local resonators. A reformulated mechanical-electrical analogy establishes a direct mapping between the R$^2$NN model and metacircuit elements, enabling accurate physical implementation of trained neural network parameters. By integrating jointly trainable global resistive coupling and local resonances, which generate effective frequency-dependent negative resistances, the architecture shapes an impedance landscape that steers currents along frequency-selective pathways. This mechanism enables direct extraction of discriminative spectral features, facilitating real-time temporal classification of raw analog inputs while bypassing analog-to-digital conversion. We demonstrate the cross-domain versatility of this framework using integrated hardware for tactile perception, speech recognition, and condition monitoring. This work establishes a scalable, fully analog paradigm for intelligent temporal processing and paves the way for low-latency, resource-efficient physical neural hardware for edge intelligence.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech RecognitionSimilar Papers 제목 키워드 기반
A case study of sending graph neural networks back to the test bench for applications in high-energy particle physics
In high-energy particle collisions, the primary collision products usually decay further resulting in tree-like, hierarchical structures with a priori unknown multiplicity. At the stable-particle level all decay products…
Comparative Study of State-based Neural Networks for Virtual Analog Audio Effects Modeling
Analog electronic circuits are at the core of an important category of musical devices, which includes a broad range of sound synthesizers and audio effects. The development of software that simulates analog musical devi…
Audio Effects ModelingAudio Signal ProcessingState Space ModelsPredicting resonant properties of plasmonic structures by deep learning
Deep learning can be used to extract meaningful results from images. In this paper, we used convolutional neural networks combined with recurrent neural networks on images of plasmonic structures and extract absorption d…
Deep LearningWave Physics as an Analog Recurrent Neural Network
Analog machine learning hardware platforms promise to be faster and more energy-efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate for building analog proces…
BIG-bench Machine LearningVowel ClassificationLLC type galvanic isolated resonant converter
Resonant converters are often being used for high power and high voltage applications to achieve high efficiency, high power density and low EMI. In this paper, we will use a resonant converter for a completely different…