Stanisa Dautovic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Stanisa Dautovic has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Natasa Samardzic
Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia
5 shared publications - Anamarija Juhas
Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia
3 shared publications A. Juhas
Univ Novi Sad, Fac Tech Sci, Dept Power Elect & Telecommun Engn, Trg Dositeja Obradovica 6, Novi Sad 21101, Serbia
1 shared publication- Alexander Toschev
Kazan Federal University, Kazan, Russia
1 shared publication - Alexey N. Mikhaylov
Research and Education Center “Physics of Solid-State Nanostructures”, National Research Lobachevsky State University of Nizhny Novgorod, 603022 Nizhny Novgorod, Russia
1 shared publication Alina Fedorova
B-Rain Ark FZ-LLC
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 60535-60556
Critical Analysis of Energy Consumption in Neuro-Computational Systems
This article presents a unified benchmark of energy consumption per synaptic event across five classes of neuro-computational substrates: graphics processing units, neural processing units, field-programmable gate arrays, digital spiking processors, and in-memory/memristive devices, with biological synapses used as reference bands. The main contribution is methodological as well as empirical. Methodologically, we introduce a common event-level metric that makes heterogeneous systems directly comparable despite major differences in architecture, coding scheme, and learning dynamics. Empirically, we combine measurements obtained by the authors with carefully normalized literature data to map the present energy landscape of artificial and biological neural computation. The results reveal three robust regimes. Dense von Neumann ANN implementations on GPUs, NPUs, and FPGA operate mainly in the $10^{5}$ to $10^{8}$ fJ range per synaptic event. Digital spiking processors reduce this requirement to about $10^{3}$ to $10^{4}$ fJ per event. Memristive and transistor-based artificial synapses span a much broader interval, from array-level values near $10^{6}$ fJ down to a few femtojoules in the most efficient device-level realizations. In particular, the best organic PANI memristive samples approach ~2 fJ per synaptic event, entering the biological vicinity and, in some cases, surpassing the rat reference range. Taken together, the benchmarked landscape spans up to ten orders of magnitude across the full set of systems considered in this study. This result clarifies where current AI hardware stands relative to biological efficiency, identifies event-driven and in-memory computation as the most promising routes toward sustainable AI, and provides a quantitatively grounded reference framework for future neuromorphic benchmarking. INDEX TERMS Artificial neural networks, energy consumption, energy efficiency, memristive devices, neuromorphic computing, spiking neural networks, sustainable AI.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 60535-60556
Open AccessCritical Analysis of Energy Consumption in Neuro-Computational Systems
This article presents a unified benchmark of energy consumption per synaptic event across five classes of neuro-computational substrates: graphics processing units, neural processing units, field-programmable gate arrays, digital spiking processors, and in-memory/memristive devices, with biological synapses used as reference bands. The main contribution is methodological as well as empirical. Methodologically, we introduce a common event-level metric that makes heterogeneous systems directly comparable despite major differences in architecture, coding scheme, and learning dynamics. Empirically, we combine measurements obtained by the authors with carefully normalized literature data to map the present energy landscape of artificial and biological neural computation. The results reveal three robust regimes. Dense von Neumann ANN implementations on GPUs, NPUs, and FPGA operate mainly in the $10^{5}$ to $10^{8}$ fJ range per synaptic event. Digital spiking processors reduce this requirement to about $10^{3}$ to $10^{4}$ fJ per event. Memristive and transistor-based artificial synapses span a much broader interval, from array-level values near $10^{6}$ fJ down to a few femtojoules in the most efficient device-level realizations. In particular, the best organic PANI memristive samples approach ~2 fJ per synaptic event, entering the biological vicinity and, in some cases, surpassing the rat reference range. Taken together, the benchmarked landscape spans up to ten orders of magnitude across the full set of systems considered in this study. This result clarifies where current AI hardware stands relative to biological efficiency, identifies event-driven and in-memory computation as the most promising routes toward sustainable AI, and provides a quantitatively grounded reference framework for future neuromorphic benchmarking. INDEX TERMS Artificial neural networks, energy consumption, energy efficiency, memristive devices, neuromorphic computing, spiking neural networks, sustainable AI.
- 27 September 2025
- Published by Wiley in International Journal of Circuit Theory and Applications
- Vol. 54 (5) , 2853-2863
Implementation of Direct Feedback Alignment Through Time Algorithm in Training of Shallow Fully Memristive Spiking Neural Networks
In this paper, we present shallow architectures of memristive spiking neural networks (MSNNs) with a single hidden layer and a simple memristive leaky integrate‐and‐fire (LIF) neuron. The SPICE‐based model is used to describe the response of a volatile memristor within LIF, whose intrinsic reset to the initial state eliminates the need for additional electronic components for discharging the membrane capacitance. The direct feedback alignment through time (DFATT) algorithm was implemented for the first time for the training of MSNNs. The deployment of the DFATT learning algorithm on two MSNN architectures resulted in average training times per epoch that were reduced by factors of 2.1 and 2.7 compared to equivalent architectures trained with the backpropagation through time (BPTT) algorithm, with comparable accuracy on MNIST and FMNIST datasets. The reported results indicate the possibility of combining memristive technology with the bioplausible DFATT algorithm toward building energy‐efficient hardware.
- 27 September 2025
- Published by Wiley in International Journal of Circuit Theory and Applications
- Vol. 54 (5) , 2853-2863
Implementation of Direct Feedback Alignment Through Time Algorithm in Training of Shallow Fully Memristive Spiking Neural Networks
In this paper, we present shallow architectures of memristive spiking neural networks (MSNNs) with a single hidden layer and a simple memristive leaky integrate‐and‐fire (LIF) neuron. The SPICE‐based model is used to describe the response of a volatile memristor within LIF, whose intrinsic reset to the initial state eliminates the need for additional electronic components for discharging the membrane capacitance. The direct feedback alignment through time (DFATT) algorithm was implemented for the first time for the training of MSNNs. The deployment of the DFATT learning algorithm on two MSNN architectures resulted in average training times per epoch that were reduced by factors of 2.1 and 2.7 compared to equivalent architectures trained with the backpropagation through time (BPTT) algorithm, with comparable accuracy on MNIST and FMNIST datasets. The reported results indicate the possibility of combining memristive technology with the bioplausible DFATT algorithm toward building energy‐efficient hardware.
- Open Access
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 94870-94884
Analytical Solutions for Charge and Flux in HP Ideal Generic Memristor Model With Joglekar and Prodromakis Window Functions
This paper presents, for the first time, analytical solutions for the charge and flux as a function of the state variable in the case of the HP memristor, modeled as an ideal generic memristor with Joglekar and Prodromakis window functions for a general value of the control parameter. The solutions are in the closed form of finite sums for an arbitrary positive integer values of the control parameter. Our approach is based on the decomposition of original problems using appropriate pairs of smooth hinge functions. The generalization of this approach allows us to define a novel window function based on smooth hinge functions, which brings simpler analytical expressions for charge and flux as a function of the state variable, and faster simulations when the model is used.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 94870-94884
Open AccessAnalytical Solutions for Charge and Flux in HP Ideal Generic Memristor Model With Joglekar and Prodromakis Window Functions
This paper presents, for the first time, analytical solutions for the charge and flux as a function of the state variable in the case of the HP memristor, modeled as an ideal generic memristor with Joglekar and Prodromakis window functions for a general value of the control parameter. The solutions are in the closed form of finite sums for an arbitrary positive integer values of the control parameter. Our approach is based on the decomposition of original problems using appropriate pairs of smooth hinge functions. The generalization of this approach allows us to define a novel window function based on smooth hinge functions, which brings simpler analytical expressions for charge and flux as a function of the state variable, and faster simulations when the model is used.
- Open Access
- 13 March 2022
- Published by MDPI AG in Electronics
- Vol. 11 (6) , 894
Volatile Memristor in Leaky Integrate-and-Fire Neurons: Circuit Simulation and Experimental Study
In this paper, circuit implementation of a leaky integrate-and-fire neuron model with a volatile memristor was proposed and simulated in the SPICE simulation environment. We demonstrate that simple leaky integrate-and-fire (LIF) neuron models composed of: volatile memristor, membrane capacitance and neuron resistance can mimic spatial and temporal integration, firing function and signal decay. The existing leaky term originates from the recovery of the initial resistive state in the memristor in the spontaneous reset cycle, which is essential for emulating the forgetting process in all-memristive neural networks (MNNs). Furthermore, a diffusive perovskite memristor was used to validate the model where intrinsic memristors’ capacitance acts as neuron membrane capacitance. Good agreement with experimental and simulation results was observed. Volatility, as an inherent property of specific memristors, eliminates the need for usage of an additional peripheral circuit which will reinitialize device state, thus allowing the development of energy-efficient, large scale complex memristive neural networks. The presented circuit level model of LIF neurons can facilitate the design of MNNs.
- 13 March 2022
- Published by MDPI AG in Electronics
- Vol. 11 (6) , 894
Open AccessVolatile Memristor in Leaky Integrate-and-Fire Neurons: Circuit Simulation and Experimental Study
In this paper, circuit implementation of a leaky integrate-and-fire neuron model with a volatile memristor was proposed and simulated in the SPICE simulation environment. We demonstrate that simple leaky integrate-and-fire (LIF) neuron models composed of: volatile memristor, membrane capacitance and neuron resistance can mimic spatial and temporal integration, firing function and signal decay. The existing leaky term originates from the recovery of the initial resistive state in the memristor in the spontaneous reset cycle, which is essential for emulating the forgetting process in all-memristive neural networks (MNNs). Furthermore, a diffusive perovskite memristor was used to validate the model where intrinsic memristors’ capacitance acts as neuron membrane capacitance. Good agreement with experimental and simulation results was observed. Volatility, as an inherent property of specific memristors, eliminates the need for usage of an additional peripheral circuit which will reinitialize device state, thus allowing the development of energy-efficient, large scale complex memristive neural networks. The presented circuit level model of LIF neurons can facilitate the design of MNNs.
- 23 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Simscape approximative PWL models of Jo and HP ideal memristors
In this paper, the linear combination of two-segment PWL functions is used to approximate flux-charge nonlinear characteristics of Jo and HP ideal memristors. It is shown that the used approximation is canonical. Described approximative PWL method avoids the so-called terminal state problem and it can be used to model an arbitrary ideal memristor, enabling a tradeoff between time and accuracy of numerical simulation. The models are implemented in Simscape environment for simulating multidomain physical systems.
- 23 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Simscape approximative PWL models of Jo and HP ideal memristors
In this paper, the linear combination of two-segment PWL functions is used to approximate flux-charge nonlinear characteristics of Jo and HP ideal memristors. It is shown that the used approximation is canonical. Described approximative PWL method avoids the so-called terminal state problem and it can be used to model an arbitrary ideal memristor, enabling a tradeoff between time and accuracy of numerical simulation. The models are implemented in Simscape environment for simulating multidomain physical systems.
- 14 April 2020
- Published by Brno University of Technology in Radioengineering
- Vol. 29 (1) , 147-158
Takacs Model of Hysteresis in Mathematical Modeling of Memristors
- 14 April 2020
- Published by Brno University of Technology in Radioengineering
- Vol. 29 (1) , 147-158
Takacs Model of Hysteresis in Mathematical Modeling of Memristors
- 3 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 66 (4) , 677-681
Computation of Pinched Hysteresis Loop Area From Memristance-vs-State Map
The voltage-current characteristic of memristor driven by sinusoidal signal has the shape of hysteresis loop pinched at the origin. The lobe area of the hysteresis loop has been computed so far either from the voltage-current plane for all types of memristors or from the constitutive relation in the flux-charge plane of ideal memristor. In this brief, we provide an alternative approach in computing the lobe area from the memristance-versus-state map of ideal and ideal generic memristors driven by sinusoidal or periodic continuous piecewise linear signal with zero dc component. The applicability of the proposed approach is demonstrated through a number of examples.
- 3 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 66 (4) , 677-681
Computation of Pinched Hysteresis Loop Area From Memristance-vs-State Map
The voltage-current characteristic of memristor driven by sinusoidal signal has the shape of hysteresis loop pinched at the origin. The lobe area of the hysteresis loop has been computed so far either from the voltage-current plane for all types of memristors or from the constitutive relation in the flux-charge plane of ideal memristor. In this brief, we provide an alternative approach in computing the lobe area from the memristance-versus-state map of ideal and ideal generic memristors driven by sinusoidal or periodic continuous piecewise linear signal with zero dc component. The applicability of the proposed approach is demonstrated through a number of examples.
- Open Access
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
On Optimal Truncated Biharmonic Current Waveforms for Class‐F and Inverse Class‐F Power Amplifiers
In this paper, two‐parameter families of periodic current waveforms for class‐F and inverse class‐F power amplifiers (PAs) are considered. These waveforms are obtained by truncating cosine waveforms composed of dc component and fundamental and either second (k = 2) or third (k = 3) harmonic. In each period, waveforms are truncated to become zero outside of a prescribed interval (so‐called conduction angle). The considered families of waveforms include both discontinuous and continuous waveforms. Fourier series expansion of truncated waveform contains an infinite number of harmonics, although a number of harmonics may be missing. Taking into account common assumptions that for class‐F PA the third (n = 3) harmonic is missing in current waveform and for inverse class‐F PA the second (n = 2) harmonic is missing in current waveform, we consider the following four cases: (i) n = k = 3, (ii) n = 3, k = 2, (iii) n = k = 2, and (iv) n = 2, k = 3. We show that, in each of these cases, current waveform enabling maximal efficiency (optimal waveform) of class‐F and inverse class‐F PA is continuous for all conduction angles of practical interest. Furthermore, we provide closed‐form expressions for parameters of optimal current waveforms and maximal efficiency of class‐F (inverse class‐F) PA in terms of conduction angle only. Two case studies of practical interest for PA design, involving suboptimal current waveforms, along with the results of nonlinear simulation of inverse class‐F PA, are also presented.
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Open AccessOn Optimal Truncated Biharmonic Current Waveforms for Class‐F and Inverse Class‐F Power Amplifiers
In this paper, two‐parameter families of periodic current waveforms for class‐F and inverse class‐F power amplifiers (PAs) are considered. These waveforms are obtained by truncating cosine waveforms composed of dc component and fundamental and either second (k = 2) or third (k = 3) harmonic. In each period, waveforms are truncated to become zero outside of a prescribed interval (so‐called conduction angle). The considered families of waveforms include both discontinuous and continuous waveforms. Fourier series expansion of truncated waveform contains an infinite number of harmonics, although a number of harmonics may be missing. Taking into account common assumptions that for class‐F PA the third (n = 3) harmonic is missing in current waveform and for inverse class‐F PA the second (n = 2) harmonic is missing in current waveform, we consider the following four cases: (i) n = k = 3, (ii) n = 3, k = 2, (iii) n = k = 2, and (iv) n = 2, k = 3. We show that, in each of these cases, current waveform enabling maximal efficiency (optimal waveform) of class‐F and inverse class‐F PA is continuous for all conduction angles of practical interest. Furthermore, we provide closed‐form expressions for parameters of optimal current waveforms and maximal efficiency of class‐F (inverse class‐F) PA in terms of conduction angle only. Two case studies of practical interest for PA design, involving suboptimal current waveforms, along with the results of nonlinear simulation of inverse class‐F PA, are also presented.
- 16 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 32 (11) , 1829-1833
Recursive Boolean Formula Minimization Algorithms for Implication Logic
In this paper are given two novel algorithms for minimization of recursive Boolean formula (RBF), which is adequate for implementation of N-input 1-output Boolean functions (BFs) over basis {imply, false} using two memristors. Both of our algorithms are direct consequence of necessary and sufficient conditions related to regular ordering of positive product terms within recursive formula. The results demonstrate how developed algorithms provide up to 26% gain in average number of implications and shorter recursive Boolean formula length in up to 77% of problem instances than previously published algorithms, tested on the set of all 4-input 1-output BFs.
- 16 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 32 (11) , 1829-1833
Recursive Boolean Formula Minimization Algorithms for Implication Logic
In this paper are given two novel algorithms for minimization of recursive Boolean formula (RBF), which is adequate for implementation of N-input 1-output Boolean functions (BFs) over basis {imply, false} using two memristors. Both of our algorithms are direct consequence of necessary and sufficient conditions related to regular ordering of positive product terms within recursive formula. The results demonstrate how developed algorithms provide up to 26% gain in average number of implications and shorter recursive Boolean formula length in up to 77% of problem instances than previously published algorithms, tested on the set of all 4-input 1-output BFs.