Phase-encoded oscillating neural networks offer compelling advantages over metal-oxide-semiconductor-based technology for tackling complex optimization problems, with promising potential ultralow power consumption and exceptionally rapid computational performance. In this work, we investigate the ability of these to solve problems belonging nondeterministic polynomial time complexity class using nanoscale vanadium-dioxide-based oscillators integrated onto a Silicon platform. Specifically,...

Brain-inspired computing employs devices and architectures that emulate biological functions for more adaptive energy-efficient systems. Oscillatory neural networks (ONNs) are an alternative approach in emulating of the human brain suitable solving large complex associative problems. In this work, we investigate dynamics coupled oscillators to implement such ONNs. By harnessing oscillatory systems, forge a novel computation model-information is encoded phase oscillations. Coupled...

A comprehensive analysis of tunable transconductor topologies based on passive resistors is presented. Based this analysis, a new CMOS designed, which features high linearity, simplicity, and robustness against geometric parametric mismatches. novel tuning technique using just MOS transistor in the triode region allows adjustment transconductance wide range without affecting voltage-to-current conversion core. Measurement results fabricated 0.5- mum technology confirm linearity predicted. As...

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 applications. An alternative approach artificial neural networks uses oscillators compute or Oscillatory Neural Networks (ONNs). ONNs can perform computations efficiently be used build a more extensive neuromorphic...

A systematic comparison of flipped voltage followers circuits is presented. Two new versions the follower are introduced. They characterized by very low output impedance, high bandwidth speed, wide signal swing. All structures can be easily modified for class AB operation. Simulation results show that newly introduced have optimal characteristics

Nano-oscillators based on phase-transition materials are being explored for the implementation of different non-conventional computing paradigms. In particular, vanadium dioxide (VO 2 ) devices used to design autonomous non-linear oscillators from which oscillatory neural networks (ONNs) can be developed. this work, we propose a new architecture ONNs in sub-harmonic injection locking (SHIL) is exploited ensure that phase information encoded each neuron only take two values. sense, neurons...

A simple modification of the MOS voltage follower is introduced that provides it with efficient class-AB operation. The modified circuit has dynamic output currents and bandwidth are essentially larger than conventional follower. This achieved same static power dissipation, very small additional complexity lower distortion. Experimental verification all these characteristics provided.

Sigma-delta Modulators (SigmaDeltaMs) are cornerstone elements in oversampled analog-to-digital converters and digital-to-analog (DAC). Although transistor-level simulation is the most accurate approach known for these components, this method becomes impractical complex systems due to its long computational time requirements. Behavioral modeling has become a viable solution problem. In paper, we study styles issues of low-power, high-speed SigmaDeltaMs introduce two new behavioral models...

Class-AB circuits, which are able to deal with currents several orders of magnitude larger than their quiescent current, good candidates for low-power analog design. This paper presents a new, simple, low-voltage class-AB unity-gain buffer, based on the flipped voltage follower cell. Simulation and experimental results provided

Neuromorphic computing aims to emulate biological neural functions overcome the memory bottleneck challenges with current Von Neumann paradigm by enabling efficient and low-power computations.In recent years, there has been a tremendous engineering effort bring neuromorphic for processing at edge.Oscillatory Neural Networks (ONNs) are braininspired networks made of oscillators mimic neuronal brain waves, typically visible on Electroencephalograms (EEG).ONNs provide massive parallelism using...

Coupled nano-oscillators are attracting increasing interest because of their potential to perform computation efficiently, enabling new applications in computing and information processing. The phase transition devices for such dynamical systems has recently been recognized. This paper investigates the implementation coupled VO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -based oscillator networks solve combinatorial optimization...

A new, simple, low-voltage class-AB unity-gain buffer is presented. The proposed approach combines use of floating-gate transistors with the flipped voltage follower to create a compact topology. Experimental results are provided that prove approach.

This paper presents the design of a low voltage, dropout (LDO) regulator with two different output voltages (1V or 1.8V). The basic function an LDO is to optimize battery life portable devices and provide constant voltage drive small sub-circuits. proposed was designed using 0.35/spl mu/m CMOS technology. able load up 50mA maximum only 200mV. A quiescent current (at no load) approximately 23/spl mu/A, makes this power design.

This paper presents a new CMOS transconductor amplifier able to achieve 90dB of SFDR. It is based in the creation low impedance nodes using local feedback drive degeneration resistor. Then, current generated at resistor delivered directly output source coupled pairs. The proposed does not rely on mirrors or cancellation nonlinear terms, thus improving significantly linearity and robustness against mismatch. Simulation results are provided that show THD 91 dB an IM3 81 10MHz with 2Vpp...

Transistors incorporating phase change materials (Phase Change FETs) are being investigated to obtain steep switching and a boost in the I <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ON</sub> /I xmlns:xlink="http://www.w3.org/1999/xlink">OFF</sub> ratio and, thus, solve power energy limitations of CMOS technologies. In addition replacement transistors conventional static logic circuits, distinguishing features Phase FETs can be exploited...

Hybrid-phase-transition FETs (HyperFETs), built by connecting a phase transition material (PTM) to the source terminal of FET, are able increase ON-to- OFF current ratio. In this article, we describe comprehensive study carried out explore potential these devices for low-power and energy-limited logic applications. HyperFETs with different ON-OFF tradeoffs evaluated at circuit level. The results show limited improvement over conventional transistors in terms power energy. However, based on...

Measuring and quantifying reverse recovery parameters in high speed LDMOS devices is an important task their characterization.A robust automated procedure required to achieve accurate repeatable parameter quantification.This work focuses the development of a virtual instrumentation setup perform extraction manner.We define architectural functional requirements such environment then introduce our proposed solution.The design was developed LabVIEW TM for low-cost instrument platform its...

In this paper, we describe device-circuit co-design experiments for Hybrid Phase Transition FETs (HyperFETs). HyperFET transistors, built by connecting a phase transition material (PTM) to the source terminal of FET, are able increase ON current without triggering OFF current. This enables reducing supply voltage and so power consumption. HyperFETs with different ON-OFF currents tradeoffs analyzed. Inverter chains ring oscillators them evaluated in terms compared reference designs using...

Coupled nano-oscillators are attracting increasing interest because of their potential to perform computation efficiently, enabling new applications in computing and information processing. The phase transition devices for such dynamical systems has recently been recognized. This paper investigates the implementation coupled VO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> based oscillators networks solving Max-Cut combinatorial...

Alternative paradigms to the von Neumann computing scheme are currently arousing huge interest. Oscillatory neural networks (ONNs) using emerging phase-change materials like VO 2 constitute an energy-efficient, massively parallel, brain-inspired, in-memory approach. The encoding of information in phase pattern frequency-locked, weakly coupled oscillators makes it possible exploit their rich non-linear dynamics and synchronization phenomena for computing. A single fully connected ONN layer...

Oscillatory neural networks (ONNs) exhibit a high potential for energy-efficient computing. In ONNs, neurons are implemented with oscillators and synapses resistive and/or capacitive coupling between pairs of oscillators. Computing is carried out on the basis rich, complex, non-linear synchronization dynamics system coupled The exploited phenomena in ONNs an example fully parallel collective A fast system's convergence to stable states, which correspond desired processed information, enables...