Conference paper Open Access

Phase Transition Adaptation

Gallicchio, Claudio; Micheli, Alessio; Silvestri, Luca

JSON-LD ( Export

  "description": "<p>Artificial Recurrent Neural Networks are a powerful information processing abstraction, and Reservoir Computing provides an efficient strategy to build robust implementations by projecting external inputs into high dimensional dynamical system trajectories. In this paper, we propose an extension of the original approach, a local unsupervised learning mechanism we call Phase Transition Adaptation, designed to drive the system dynamics towards the `edge of stability&#39;. Here, the complex behavior exhibited by the system elicits an enhancement in its overall computational capacity. We show experimentally that our approach consistently achieves its purpose over several datasets.</p>", 
  "license": "", 
  "creator": [
      "affiliation": "University of Pisa", 
      "@type": "Person", 
      "name": "Gallicchio, Claudio"
      "affiliation": "University of Pisa", 
      "@type": "Person", 
      "name": "Micheli, Alessio"
      "@type": "Person", 
      "name": "Silvestri, Luca"
  "headline": "Phase Transition Adaptation", 
  "image": "", 
  "datePublished": "2021-08-25", 
  "url": "", 
  "keywords": [
    "Reservoir Computing", 
    "Recurrent Neural Networks", 
    "Echo State Networks", 
    "Edge of stability", 
    "Lyapunov Stability"
  "@context": "", 
  "identifier": "", 
  "@id": "", 
  "@type": "ScholarlyArticle", 
  "name": "Phase Transition Adaptation"
All versions This version
Views 1717
Downloads 1212
Data volume 4.2 MB4.2 MB
Unique views 1212
Unique downloads 1212


Cite as