Mukhutdinov, D., Filchenkov, A., Shalyto, A. & Vyatkin, V., Multi-agent deep learning for simultaneous optimization for time and energy in distributed routing system, 1 May 2019, In : Future Generation Computer Systems. 94, p. 587-600 14 p
This paper is the first attempt to design agents as neural networks for multi-agent control of modular systems, such as airport baggage handling systems. A constellation of such agents learns from examples of material flows through the system after which starts routing as the distributed Bellman-Ford algorithm!
C. Giovanelli, S. Sierla, R. Ichise, V. Vyatkin. Exploiting Artificial Neural Networks for the Prediction of Ancillary Energy Market Prices. In Energies, July 2018, 11(7):1906.
This paper presents a novel model for predictions of electricity market prices that are substantially more accurate than other machine learning methods.
D. Kleyko, E. Osipov, N. Papakonstantinou, V. Vyatkin, Hyperdimensional computing in industrial systems: the use-case of distributed fault isolation in a power plant, IEEE Access, 2018
More accurate than classic machine-learning, the hyperdimensional vectors approach also promises higher energy efficiency and real-time performance.