Aleksandr Iliasov

Aleksandr Iliasov

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 July 2023 in Neural Networks
Verified
Journal Article
Closed access
DVDanila Vlasov
Danila Vlasov
AMAnton Minnekhanov
Anton Minnekhanov
RRRoman Rybka
Roman Rybka
YDYury Davydov
Yury Davydov
ASAlexander Sboev
Alexander Sboev
VDVyacheslav Demin
Vyacheslav Demin

14 December 2023 in Nanoscale Horizons
Verified
Journal Article
Open access
PDF file
AIAleksandr Iliasov
Aleksandr Iliasov
AMAnna Matsukatova
Anna Matsukatova
Andrey V EmelyanovAndrey V Emelyanov
Andrey V Emelyanov
PSPavel S. Slepov
Pavel S. Slepov
KNKristina E. Nikiruy
Kristina E. Nikiruy
VRVladimir Rylkov
Vladimir Rylkov
MLP-Mixer based on multilayer perceptrons (MLPs) is a novel architecture of a neuromorphic computing system (NCS) introduced for image classification tasks without convolutional layers. Its software realization demonstrates high classification accuracy, although the number of trainable weights is relatively low. One more promising way of improving the NCS performance, especially in terms of power consumption, is its hardware realization using memristors. Therefore, in this work, we proposed an NCS with an adapted MLP-Mixer architecture and memristive weights. For this purpose, we used a passive crossbar array of (Co–Fe–B)x(LiNbO3)100−x memristors. Firstly, we studied the characteristics of such memristors, including their minimal resistive switching time, which was extrapolated to be in the picosecond range. Secondly, we created a fully hardware NCS with memristive weights that are capable of classification of simple 4-bit vectors. The system was shown to be robust to noise introduction in the input patterns. Finally, we used experimental memristive characteristics to simulate an adapted MLP-Mixer architecture that demonstrated a classification accuracy of (94.7 ± 0.3)% on the Modified National Institute of Standards and Technology (MNIST) dataset. The obtained results are the first steps toward the realization of memristive NCS with a promising MLP-Mixer architecture.

3 October 2022 in Nanomaterials
Verified
Journal Article
Open access
PDF file
AMAnna Matsukatova
Anna Matsukatova
AIAleksandr Iliasov
Aleksandr Iliasov
KNKristina E. Nikiruy
Kristina E. Nikiruy
EKElena Kukueva
Elena Kukueva
AVAlexander Vasiliev
Alexander Vasiliev
Andrey V EmelyanovAndrey V Emelyanov
Andrey V Emelyanov
Convolutional neural networks (CNNs) have been widely used in image recognition and processing tasks. Memristor-based CNNs accumulate the advantages of emerging memristive devices, such as nanometer critical dimensions, low power consumption, and functional similarity to biological synapses. Most studies on memristor-based CNNs use either software models of memristors for simulation analysis or full hardware CNN realization. Here, we propose a hybrid CNN, consisting of a hardware fixed pre-trained and explainable feature extractor and a trainable software classifier. The hardware part was realized on passive crossbar arrays of memristors based on nanocomposite (Co-Fe-B)x(LiNbO3)100−x structures. The constructed 2-kernel CNN was able to classify the binarized Fashion-MNIST dataset with ~ 84% accuracy. The performance of the hybrid CNN is comparable to the other reported memristor-based systems, while the number of trainable parameters for the hybrid CNN is substantially lower. Moreover, the hybrid CNN is robust to the variations in the memristive characteristics: dispersion of 20% leads to only a 3% accuracy decrease. The obtained results pave the way for the efficient and reliable realization of neural networks based on partially unreliable analog elements.

1 February 2022 in Nanobiotechnology Reports
Verified
Journal Article
Closed access
PDF file
AIAleksandr Iliasov
Aleksandr Iliasov
KNK. E. Nikiruy
K. E. Nikiruy
Andrey V EmelyanovAndrey V Emelyanov
Andrey V Emelyanov
KCK. Yu. Chernoglazov
K. Yu. Chernoglazov
ASA. V. Sitnikov
A. V. Sitnikov
VDV. A. Demin
V. A. Demin
Memristors are promising devices for use as synapses in hardware-based artificial formal and spiking neural networks. Their use can increase the energy efficiency of such networks when solving various cognitive tasks. At the same time, for the implementation of hardware-based neural networks, a large number of rather densely packed structures are required, which can be achieved by creating memristive matrices in a crossbar architecture. Crossbar arrays of nanocomposite memristors on silicon substrates with protection against edge effects are developed and manufactured, their resistive switching is investigated, a formal neural network is created on their basis, which is capable of recognizing simple patterns after loading a pretrained weight map, and the possibility of precise adjustment of the conductivity of the crossbar memristors by various means applicable in the creation of more complex spiking and formal neural networks is demonstrated.

1 April 2023 in Nanobiotechnology Reports
Verified
Journal Article
Open access
PDF file
VDVyacheslav Demin
Vyacheslav Demin
AIAleksandr Iliasov
Aleksandr Iliasov
VRV. V. Rylkov
V. V. Rylkov
PKP. K. Kashkarov
P. K. Kashkarov
MKM. V. Kovalchuk
M. V. Kovalchuk
Many applications, including learning neuromorphic computing systems, require the analogue or, at least, multilevel resistive switching (RS) of memristor devices. In metal–insulator–metal (MIM) structures it is often associated with the creation of a large number of conductive channels, or filaments, but in the majority of cases, especially for the vacancy mechanism of RS, the direct observation of many filaments is difficult or impossible. In this work, a model of the explicit filament conductivity distribution for a nanocomposite (NC) LiNbO 3 -based memristor, that nonetheless may be applicable to other types of MIM memristors with hopping conductivity over dangling bonds in an amorphous insulator layer, is derived from physical principles. This model, in addition to indirect evidence from magnetic and capacitance measurements, reaffirms the multifilamentary RS mechanism by the approximation of experimental data on synaptic plasticity, i.e., a change in the conductivity of a memristor by a pair of pulses applied to it. The results of this research offer opportunities to study RS in MIM structures at the macroscopic level using model filament distributions and substantiates the possibility of successfully applying the considered NC memristors as synaptic elements of neuromorphic networks.

21 August 2025 in Journal of Physics D: Applied Physics
Verified
Journal Article
Closed access
AIAleksandr Iliasov
Aleksandr Iliasov
Andrey V EmelyanovAndrey V Emelyanov
Andrey V Emelyanov
VRVladimir Rylkov
Vladimir Rylkov
AMAnna N. Matsukatova
Anna N. Matsukatova
EKElena V. Kukueva
Elena V. Kukueva
MKMikhail Kovalchuk
Mikhail Kovalchuk
This study investigates the properties and applications of Cu/(Co-Fe-B)x(SiOz)100-x/LiNbOy/Cu (y ~ z ~ 1.4) nanocomposite (NC) memristors, with active layers acquired via ion-beam sputtering of stoichiometric LiNbO3 and compound Co40Fe40B20-SiO2 targets on the sitall substrate without external heating during the synthesis process. The devices exhibit quasi-analog resistive switching (RS), alongside high endurance exceeding 10000 cycles between 2 states and 25000 cycles between 50 states, which are advantageous for neuromorphic computing systems. RS behavior is established to be attributed to the Li+ intercalation and the forming of the self-organized Cu clusters inside the LiNbO1.4 layer, as well as the presence of the Li-accumulating membrane (SiO1.1 layer) between NC and LiNbO1.4. These factors explain both the multi-level (analogous) nature of the resistive states and their long retention time. To assess their practical viability, a two-layer memristive network was simulated for classification of handwritten digits from the MNIST dataset. Results revealed that the conductance state range significantly influences network performance, with broader ranges yielding superior accuracy. The conductance state variations also substantially diminish classification performance, emphasizing the necessity for meticulous selection of training parameters. The study concludes that employing long-term depression and long-term potentiation curves with the same pulses (with handpicked parameters) is preferable for energy-efficient neuromorphic computing, as opposed to a write-verify algorithm or long-lasting fine-tuning of states, which, while effective, incur higher complexity, as well as time and energy costs.