TY - JOUR

T1 - Energy-Performance Assessment of Oscillatory Neural Networks Based on VO2 Devices for Future Edge AI Computing

AU - Delacour, Corentin

AU - Carapezzi, Stefania

AU - Abernot, Madeleine

AU - Todri-Sanial, Aida

PY - 2024/7

Y1 - 2024/7

N2 - Oscillatory neural network (ONN) is an emerging neuromorphic architecture composed of oscillators that implement neurons and are coupled by synapses. ONNs exhibit rich dynamics and associative properties, which can be used to solve problems in the analog domain according to the paradigm let physics compute. For example, compact oscillators made of VO $_2$ material are good candidates for building low-power ONN architectures dedicated to AI applications at the edge, like pattern recognition. However, little is known about the ONN scalability and its performance when implemented in hardware. Before deploying ONN, it is necessary to assess its computation time, energy consumption, performance, and accuracy for a given application. Here, we consider a VO $_2$ -oscillator as an ONN building block and perform circuit-level simulations to evaluate the ONN performances at the architecture level. Notably, we investigate how the ONN computation time, energy, and memory capacity scale with the number of oscillators. It appears that the ONN energy grows linearly when scaling up the network, making it suitable for large-scale integration at the edge. Furthermore, we investigate the design knobs for minimizing the ONN energy. Assisted by technology computer-aided design (TCAD) simulations, we report on scaling down the dimensions of VO $_2$ devices in crossbar (CB) geometry to decrease the oscillator voltage and energy. We benchmark ONN versus state-of-the-art architectures and observe that the ONN paradigm is a competitive energy-efficient solution for scaled VO $_2$ devices oscillating above 100 MHz. Finally, we present how ONN can efficiently detect edges in images captured on low-power edge devices and compare the results with Sobel and Canny edge detectors.

AB - Oscillatory neural network (ONN) is an emerging neuromorphic architecture composed of oscillators that implement neurons and are coupled by synapses. ONNs exhibit rich dynamics and associative properties, which can be used to solve problems in the analog domain according to the paradigm let physics compute. For example, compact oscillators made of VO $_2$ material are good candidates for building low-power ONN architectures dedicated to AI applications at the edge, like pattern recognition. However, little is known about the ONN scalability and its performance when implemented in hardware. Before deploying ONN, it is necessary to assess its computation time, energy consumption, performance, and accuracy for a given application. Here, we consider a VO $_2$ -oscillator as an ONN building block and perform circuit-level simulations to evaluate the ONN performances at the architecture level. Notably, we investigate how the ONN computation time, energy, and memory capacity scale with the number of oscillators. It appears that the ONN energy grows linearly when scaling up the network, making it suitable for large-scale integration at the edge. Furthermore, we investigate the design knobs for minimizing the ONN energy. Assisted by technology computer-aided design (TCAD) simulations, we report on scaling down the dimensions of VO $_2$ devices in crossbar (CB) geometry to decrease the oscillator voltage and energy. We benchmark ONN versus state-of-the-art architectures and observe that the ONN paradigm is a competitive energy-efficient solution for scaled VO $_2$ devices oscillating above 100 MHz. Finally, we present how ONN can efficiently detect edges in images captured on low-power edge devices and compare the results with Sobel and Canny edge detectors.

KW - Oscillators

KW - Computer architecture

KW - Performance evaluation

KW - Couplings

KW - Resistance

KW - Biological neural networks

KW - Image edge detection

KW - Hopfield neural network (HNN)

KW - vanadium dioxide (VO<inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX

KW - Edge AI

KW - image edge detection

KW - oscillatory neural network (ONN)

UR - http://www.scopus.com/inward/record.url?scp=85148421826&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2023.3238473

DO - 10.1109/TNNLS.2023.3238473

M3 - Article

C2 - 37022082

SN - 2162-237X

VL - 35

SP - 10045

EP - 10058

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 7

M1 - 10026654

ER -