Memristors are promising candidates for synapse emulation in brain-inspired neuromorphic computing systems. The main obstacle to their usage in such systems is high variability of memristive characteristics and its severe negative effect on the neural network training. This paper addresses the issue from two points of view on the example of the parylene-based memristors: (i) the methods of the memristor internal stochasticity decrease and (ii) the methods of the memristive neural network architecture simplification. The introduction of an optimal Ag nanoparticle concentration (3 vol.%–6 vol.%) to the memristive structure leads to a statistically significant decrease in the switching voltage variation and endurance increase. Moreover, it is shown that post-fabrication annealing improves memristive characteristics, e.g., resistive switching window increases by an order of magnitude and exceeds 106, the switching voltage variation decreases by a factor of 2 (down to 7% for the set and 17% for the reset voltage), and thermostability is improved. Additional transmission electron microscopy and impedance spectroscopy analysis allowed establishing a multifilamentary resistive switching mechanism for nanocomposite parylene-based memristors. The simulation of the formal neural network based on these memristors demonstrates high classification accuracy with low variation for an important biomedical task, heart disease prediction, after careful feature selection and network architecture simplification. Future prospects of the controlled incorporation of the nanocomposite parylene-based memristors in neural networks are brightened by their scaling possibility in crossbar geometry.
This work was supported by the Russian Science Foundation (project No. 18-79-10253). A. N. M. thanks the Theoretical Physics and Mathematics Advancement Foundation “BASIS” (No. 19-2-6-57-1) for support in the memristive characteristics investigation part and acknowledges financial support from the Non-commercial Foundation for the Advancement of Science and Education INTELLECT in the neural network simulation part.
Authors are thankful to Dr. V. V. Rylkov, Dr. A. A. Minnekhanov, Dr. A. L. Vasiliev (NRC “Kurchatov Institute”), and Dr. M. N. Martyshov (Lomonosov Moscow State University) for fruitful discussions and to Yu. V. Grishchenko (NRC “Kurchatov Institute”) for lithographic patterning of the bottom electrodes of crossbar structures.
Measurements were carried out with the equipment of the Resource Centres (NRC “Kurchatov Institute”).
Reprints and Permission requests may be sought directly from editorial office.