no code implementations • 9 Nov 2023 • Mikhail Kiselev
In the context of SNNs, events are represented as spikes emitted by network neurons or input nodes.
no code implementations • 15 Sep 2023 • Mikhail Kiselev, Denis Larionov, Andrey Urusov
Causal relationship recognition is a fundamental operation in neural networks aimed at learning behavior, action planning, and inferring external world dynamics.
no code implementations • 20 Sep 2022 • Mikhail Kiselev
In this paper, the question how spiking neural network (SNN) learns and fixes in its internal structures a model of external world dynamics is explored.
Model-based Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 25 May 2022 • Dmitry Ivanov, Aleksandr Chezhegov, Andrey Grunin, Mikhail Kiselev, Denis Larionov
Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain.
no code implementations • 9 Apr 2022 • Mikhail Kiselev
At present, implementation of learning mechanisms in spiking neural networks (SNN) cannot be considered as a solved scientific problem despite plenty of SNN learning algorithms proposed.
no code implementations • 7 Jan 2022 • Dmitry Ivanov, Mikhail Kiselev, Denis Larionov
This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks.
no code implementations • 12 Nov 2021 • Mikhail Kiselev
Spiking neural networks (SNN) are considered as a perspective basis for performing all kinds of learning tasks - unsupervised, supervised and reinforcement learning.