An RRAM-based Oscillatory Neural Network

Jackson, Thomas C.; Sharma, Abhishek; Bain, James A.; Weldon, Jeffrey A.; Pileggi, Lawrence T.

doi:10.1109/lascas.2015.7250481

Cited by 7 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, there is a recent interest to exploit ONN for large-scale associative memory applications. While there is a lot of ongoing research on devices and analog architectures to implement ONN efficiently (Csaba and Porod, 2013;Jackson et al, 2015;Shi et al, 2016;Kumar and Mohanty, 2017;Corti et al, 2019;Velichko et al, 2019), we focus on addressing a more fundamental problem-can we perform relevant AI applications such as image recognition with ONN? We explore ONN at smallscale (up to 60 coupled oscillators) as a first attempt to show phase computation in the digital domain.…”

Section: Introductionmentioning

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

Section: Introductionmentioning

confidence: 99%

Digital Implementation of Oscillatory Neural Network for Image Recognition Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[3][4][5]. Hardware implementations of oscillatory neural networks are based both on current CMOS devices (e.g., phase-locked loop circuits [6] or Van der Pol oscillators [7]) and on emerging new devices, such as, spin-torque nano-oscillators [8], switches based on materials with metal-insulator [1,9] or charge density wave [10,11] transitions, and oxide RRAM [12,13].…”

Section: Introductionmentioning

confidence: 99%

“…In an ONN, an elementary cell comprises an oscillator circuit, and the cells are locally coupled by resistors or capacitors [9][10][11][12][13]. Also, in the work [7], the variable resistive coupling via a memristive device has been proposed.…”

Section: Introductionmentioning

confidence: 99%

Thermal coupling and effect of subharmonic synchronization in a system of two VO2 based oscillators

Velichko

Belyaev

Putrolaynen

et al. 2018

Solid-State Electronics

View full text Add to dashboard Cite

We explore a prototype of an oscillatory neural network (ONN) based on vanadium dioxide switching devices. The model system under study represents two oscillators based on thermally coupled VO2 switches. Numerical simulation shows that the effective action radius RTC of coupling depends both on the total energy released during switching and on the average power. It is experimentally and numerically proved that the temperature change ΔT commences almost synchronously with the released power peak and T-coupling reveals itself up to a frequency of about 10 kHz. For the studied switching structure configuration, the RTC value varies over a wide range from 4 to 45 μm, depending on the external circuit capacitance C and resistance Ri, but the variation of Ri is more promising from the practical viewpoint. In the case of a "weak" coupling, synchronization is accompanied by attraction effect and decrease of the main spectra harmonics width. In the case of a "strong" coupling, the number of effects increases, synchronization can occur on subharmonics resulting in multilevel stable synchronization of two oscillators. An advanced algorithm for synchronization efficiency and subharmonic ratio calculation is proposed. It is shown that of the two oscillators the leading one is that with a higher main frequency, and, in addition, the frequency stabilization effect is observed. Also, in the case of a strong thermal coupling, the limit of the supply current parameters, for which the oscillations exist, expands by ~ 10 %. The obtained results have a universal character and open up a new kind of coupling in ONNs, namely, T-coupling, which allows for easy transition from 2D to 3D integration. The effect of subharmonic synchronization hold promise for application in classification and pattern recognition.

show abstract

“…An artificial neural network is one of the most promising approaches for development of the next generation computing architectures realizing the brain-inspired massively parallel computing paradigm [3]. Hardware implementations of ONNs are based both on current CMOS devices (e.g., phase-locked loop circuits [4] or Van der Pol oscillators [5]) and on emerging new devices, such as, spin-torque nano-oscillators [6], switches based on materials with metal-toinsulator transitions [1,3,7] or charge-density-wave transitions [8], and oxide RRAM [9].…”

Section: Introductionmentioning

confidence: 99%

“…In an ONN, an elementary cell comprises an oscillator circuit, and the cells are locally coupled by resistors or capacitors [7][8][9]. Also, in the work [5], the variable resistive coupling via a memristive device has been proposed.…”

Section: Introductionmentioning

confidence: 99%

Electrical switching and oscillations in vanadium dioxide

Pergament

Velichko

Belyaev

et al. 2018

Physica B: Condensed Matter

View full text Add to dashboard Cite

We have studied electrical switching with S-shaped I-V characteristics in two-terminal MOM devices based on vanadium dioxide thin films. The switching effect is associated with the metal-insulator phase transition. Relaxation oscillations are observed in circuits with VO2-based switches. Dependences of the oscillator critical frequency Fmax, threshold power and voltage, as well as the time of current rise, on the switching structure size are obtained by numerical simulation. The empirical dependence of the threshold voltage on the switching region dimensions and film thickness is found. It is shown that, for the VO2 channel sizes of 10×10 nm, Fmax can reach the value of 300 MHz at a film thickness of ~20 nm. Next, it is shown that oscillatory neural networks can be implemented on the basis of coupled VO2 oscillators. For the weak capacitive coupling, we revealed the dependence of the phase difference upon synchronization on the coupling capacitance value. When the switches are scaled down, the limiting time of synchronization is reduced to Ts ~13 μs, and the number of oscillation periods for the entering to the synchronization mode remains constant, Ns ~ 17. In the case of weak thermal coupling in the synchronization mode, we observe in-phase behavior of oscillators, and there is a certain range of parameters of the supply current, in which the synchronization effect becomes possible. With a decrease in dimensions, a decrease in the thermal coupling action radius is observed, which can vary in the range from 0.5 to 50 μm for structures with characteristic dimensions of 0.1 to 5 μm, respectively. Thermal coupling may have a promising effect for realization of a 3D integrated oscillatory neural network.

show abstract

An RRAM-based Oscillatory Neural Network

Cited by 7 publications

References 14 publications

Digital Implementation of Oscillatory Neural Network for Image Recognition Applications

Digital Implementation of Oscillatory Neural Network for Image Recognition Applications

Thermal coupling and effect of subharmonic synchronization in a system of two VO2 based oscillators

Electrical switching and oscillations in vanadium dioxide

Contact Info

Product

Resources

About