Zobrazeno 1 - 10
of 273
pro vyhledávání: '"Kiselev, Mikhail"'
Publikováno v:
Известия высших учебных заведений: Прикладная нелинейная динамика, Vol 32, Iss 5, Pp 589-605 (2024)
Purpose. Causal relationship recognition is a fundamental operation in neural networks aimed at learning behavior, action planning, and inferring external world dynamics. This operation is particularly crucial for reinforcement learning (RL). In the
Externí odkaz:
https://doaj.org/article/ce8c07821ab54c838435152ce95863f6
Autor:
Kiselev, Mikhail
In the present paper, it is shown how the columnar/layered CoLaNET spiking neural network (SNN) architecture can be used in supervised learning image classification tasks. Image pixel brightness is coded by the spike count during image presentation p
Externí odkaz:
http://arxiv.org/abs/2409.07833
Autor:
Kiselev, Mikhail
In the present paper, I describe a spiking neural network (SNN) architecture which, can be used in wide range of supervised learning classification tasks. It is assumed, that all participating signals (the classified object description, correct class
Externí odkaz:
http://arxiv.org/abs/2409.01230
Autor:
Kiselev, Mikhail
In the reinforcement learning (RL) tasks, the ability to predict receiving reward in the near or more distant future means the ability to evaluate the current state as more or less close to the target state (labelled by the reward signal). In the pre
Externí odkaz:
http://arxiv.org/abs/2311.05210
Causal relationship recognition is a fundamental operation in neural networks aimed at learning behavior, action planning, and inferring external world dynamics. This operation is particularly crucial for reinforcement learning (RL). In the context o
Externí odkaz:
http://arxiv.org/abs/2309.08476
Autor:
Kiselev, Mikhail
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. This question is important for implementation of the model-based reinforcement learning (RL), the
Externí odkaz:
http://arxiv.org/abs/2209.09572
Publikováno v:
Scientific Reports 18386 (2023)
Quantum mechanics increasingly penetrates modern technologies but, due to its non-deterministic nature seemingly contradicting our classical everyday world, our comprehension often stays elusive. Arguing along the correspondence principle, classical
Externí odkaz:
http://arxiv.org/abs/2207.09296
Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain. This article discusses such limitations and the ways they can be mitigated. Next, it presents a
Externí odkaz:
http://arxiv.org/abs/2205.13037
Autor:
Kiselev, Mikhail
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. It is also true for SNN implementation of reinforcement learnin
Externí odkaz:
http://arxiv.org/abs/2204.04431
This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes it possible
Externí odkaz:
http://arxiv.org/abs/2201.02571