Neuromorphic Neural Engineering Framework-Inspired Online Continuous Learning with Analog Circuitry

פרסום מחקרי: פרסום בכתב עתמאמרביקורת עמיתים


Neuromorphic hardware designs realize neural principles in electronics to provide highperforming, energy-efficient frameworks for machine learning. Here, we propose a neuromorphic analog design for continuous real-time learning. Our hardware design realizes the underlying principles of the neural engineering framework (NEF). NEF brings forth a theoretical framework for the representation and transformation of mathematical constructs with spiking neurons, thus providing efficient means for neuromorphic machine learning and the design of intricate dynamical systems. Our analog circuit design implements the neuromorphic prescribed error sensitivity (PES) learning rule with OZ neurons. OZ is an analog implementation of a spiking neuron, which was shown to have complete correspondence with NEF across firing rates, encoding vectors, and intercepts. We demonstrate PES-based neuromorphic representation of mathematical constructs with varying neuron configurations, the transformation of mathematical constructs, and the construction of a dynamical system with the design of an inducible leaky oscillator. We further designed a circuit emulator, allowing the evaluation of our electrical designs on a large scale. We used the circuit emulator in conjunction with a robot simulator to demonstrate adaptive learning-based control of a robotic arm with six degrees of freedom.

שפה מקוריתאנגלית
מספר המאמר4528
כתב עתApplied Sciences (Switzerland)
מספר גיליון9
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - 1 מאי 2022

הערה ביבליוגרפית

Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Neuromorphic Neural Engineering Framework-Inspired Online Continuous Learning with Analog Circuitry'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי