Felder, Daniel ; Linkhorst, John ; Wessling, Matthias (2023)
Spiking Neural Networks Compensate Weight Drift in Organic Neuromorphic Device Networks.
In: Neuromorphic Computing and Engineering, 3
doi: 10.1088/2634-4386/accd90
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
Organic neuromorphic devices can accelerate neural networks and integrate with biological systems. Devices based on the biocompatible and conductive polymer PEDOT:PSS are fast, require low amounts of energy and perform well in crossbar simulations. However, parasitic electrochemical reactions lead to self-discharge and the fading of learned conductance states over time. This limits a neural network's operating time and requires complex compensation mechanisms. Spiking neural networks take inspiration from biology to implement local and always-on learning. We show that these spiking neural networks can function on organic neuromorphic hardware and compensate for self-discharge by continuously relearning and reinforcing forgotten states. In this work, we use a high-resolution charge transport model to describe the behavior of organic neuromorphic devices and create a computationally-efficient surrogate model. By integrating the surrogate model into a Brian 2 simulation, we can describe the behavior of spiking neural networks on organic neuromorphic hardware. A biologically-plausible two-layer network for recognizing 28x28 pixel MNIST images is trained and observed during self-discharge. The network achieves, for its size, competitive recognition results up to 82.5%. Building the network with forgetful devices yields superior accuracy during training with 84.5% compared to ideal devices. However, the trained networks without active spike-timing-dependent plasticity quickly lose their predictive performance. We show that online learning can keep the performance at a steady level close to the initial accuracy, even for idle rates of up to 90%. This performance is maintained when the output neuron's labels are not revalidated for up to 24 hours. These findings reconfirm the potential of organic neuromorphic devices for brain-inspired computing. Their biocompatibility and the demonstrated adaptability to spiking neural networks open the path toward close integration with multi-electrode arrays, drug-delivery devices, and other bio-interfacing systems as either full organic or hybrid organic-inorganic systems.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Felder, Daniel ; Linkhorst, John ; Wessling, Matthias |
| Art des Eintrags: | Bibliographie |
| Titel: | Spiking Neural Networks Compensate Weight Drift in Organic Neuromorphic Device Networks |
| Sprache: | Englisch |
| Publikationsjahr: | 2023 |
| Verlag: | IOP Publishing Ltd |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Neuromorphic Computing and Engineering |
| Jahrgang/Volume einer Zeitschrift: | 3 |
| DOI: | 10.1088/2634-4386/accd90 |
| Kurzbeschreibung (Abstract): | Organic neuromorphic devices can accelerate neural networks and integrate with biological systems. Devices based on the biocompatible and conductive polymer PEDOT:PSS are fast, require low amounts of energy and perform well in crossbar simulations. However, parasitic electrochemical reactions lead to self-discharge and the fading of learned conductance states over time. This limits a neural network's operating time and requires complex compensation mechanisms. Spiking neural networks take inspiration from biology to implement local and always-on learning. We show that these spiking neural networks can function on organic neuromorphic hardware and compensate for self-discharge by continuously relearning and reinforcing forgotten states. In this work, we use a high-resolution charge transport model to describe the behavior of organic neuromorphic devices and create a computationally-efficient surrogate model. By integrating the surrogate model into a Brian 2 simulation, we can describe the behavior of spiking neural networks on organic neuromorphic hardware. A biologically-plausible two-layer network for recognizing 28x28 pixel MNIST images is trained and observed during self-discharge. The network achieves, for its size, competitive recognition results up to 82.5%. Building the network with forgetful devices yields superior accuracy during training with 84.5% compared to ideal devices. However, the trained networks without active spike-timing-dependent plasticity quickly lose their predictive performance. We show that online learning can keep the performance at a steady level close to the initial accuracy, even for idle rates of up to 90%. This performance is maintained when the output neuron's labels are not revalidated for up to 24 hours. These findings reconfirm the potential of organic neuromorphic devices for brain-inspired computing. Their biocompatibility and the demonstrated adaptability to spiking neural networks open the path toward close integration with multi-electrode arrays, drug-delivery devices, and other bio-interfacing systems as either full organic or hybrid organic-inorganic systems. |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Verfahrenstechnik elektrochemischer Systeme (VES) |
| Hinterlegungsdatum: | 13 Sep 2023 11:13 |
| Letzte Änderung: | 13 Sep 2023 11:13 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum