An Oscillatory Neural Network with Programmable Resistive Synapses in 28 Nm CMOS

Jackson, Thomas C.; Pagliarini, Samuel; Pileggi, Lawrence T.

doi:10.1109/icrc.2018.8638600

Cited by 22 publications

(28 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though the concept is very interesting and promising, the Hopfield network that this technique envisions comprises between 256 and 2,024 neurons. However, the physical demonstrations of oscillatory neural networks features maximum 100 oscillators as neurons with standard Phase Locked Loop or equivalent CMOS technology ( Jackson et al, 2018 ). The technological challenge in the physical realization of large oscillatory neural networks resides in the complex dynamics of the oscillators’ frequency and phase synchronization when the electrical components are affected by variability.…”

Section: Introductionmentioning

confidence: 99%

Coupled VO2 Oscillators Circuit as Analog First Layer Filter in Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

In this work we present an in-memory computing platform based on coupled VO2 oscillators fabricated in a crossbar configuration on silicon. Compared to existing platforms, the crossbar configuration promises significant improvements in terms of area density and oscillation frequency. Further, the crossbar devices exhibit low variability and extended reliability, hence, enabling experiments on 4-coupled oscillator. We demonstrate the neuromorphic computing capabilities using the phase relation of the oscillators. As an application, we propose to replace digital filtering operation in a convolutional neural network with oscillating circuits. The concept is tested with a VGG13 architecture on the MNIST dataset, achieving performances of 95% in the recognition task.

show abstract

Section: Introductionmentioning

confidence: 99%

Coupled VO2 Oscillators Circuit as Analog First Layer Filter in Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…We develop a digital ONN as a proof of concept of the computing in phase paradigm to explore ONN architectures and AI at-theedge applications. We present an ONN digital design inspired by hybrid analog-digital work from Jackson et al (2019) but without analog components.…”

Section: Digital Onn Designmentioning

confidence: 99%

Digital Implementation of Oscillatory Neural Network for Image Recognition Applications

et al. 2021

View full text Add to dashboard Cite

Computing paradigm based on von Neuman architectures cannot keep up with the ever-increasing data growth (also called “data deluge gap”). This has resulted in investigating novel computing paradigms and design approaches at all levels from materials to system-level implementations and applications. An alternative computing approach based on artificial neural networks uses oscillators to compute or Oscillatory Neural Networks (ONNs). ONNs can perform computations efficiently and can be used to build a more extensive neuromorphic system. Here, we address a fundamental problem: can we efficiently perform artificial intelligence applications with ONNs? We present a digital ONN implementation to show a proof-of-concept of the ONN approach of “computing-in-phase” for pattern recognition applications. To the best of our knowledge, this is the first attempt to implement an FPGA-based fully-digital ONN. We report ONN accuracy, training, inference, memory capacity, operating frequency, hardware resources based on simulations and implementations of 5 × 3 and 10 × 6 ONNs. We present the digital ONN implementation on FPGA for pattern recognition applications such as performing digits recognition from a camera stream. We discuss practical challenges and future directions in implementing digital ONN.

show abstract

“…The case when oscillators synchronize corresponds to positive inference (recognition) and the case when they do not, corresponds to a lack of recognition. Chips with PSK CMOS oscillators have been fabricated [14], but neural information processing has not yet been demonstrated. Coupled beyond-CMOS oscillators based on metal-insulator transitions [15] or spin-torque have been proposed for speech recognition and fabricated [16].…”

Section: E Nikonov H LI and I A Young Are With Components Rementioning

confidence: 99%

“…Applications of CMOS oscillators to Hopfield nets [4] and image recognition [5] were proposed. Fabricated CMOS oscillator chips [6] show functional circuits, but not the actual neural computing. "Beyond-CMOS" device oscillator arrays, e.g.…”

mentioning

confidence: 99%

Convolution Inference via Synchronization of a Coupled CMOS Oscillator Array

Nikonov

Kurahashi

Ayers

et al. 2020

IEEE J. Explor. Solid-State Comput. Devices Circuits

View full text Add to dashboard Cite

Oscillator neural networks (ONN) are a promising hardware option for artificial intelligence. With an abundance of theoretical treatments of ONNs, few experimental implementations exist to date. In contrast to prior publications of only building block functionality, we report a practical experimental demonstration of neural computing using an ONN. The arrays contain 26 CMOS ring oscillators in the GHz range of frequencies tuned by image data and filters. Synchronization of oscillators results in an analog output voltage approximating convolution neural network operation.

show abstract

An Oscillatory Neural Network with Programmable Resistive Synapses in 28 Nm CMOS

Cited by 22 publications

References 5 publications

Coupled VO2 Oscillators Circuit as Analog First Layer Filter in Convolutional Neural Networks

Coupled VO2 Oscillators Circuit as Analog First Layer Filter in Convolutional Neural Networks

Digital Implementation of Oscillatory Neural Network for Image Recognition Applications

Convolution Inference via Synchronization of a Coupled CMOS Oscillator Array

Contact Info

Product

Resources

About