Výsledky vyhledávání

Report

Initialisation and Network Effects in Decentralised Federated Learning

Autor: Badie-Modiri, Arash, Boldrini, Chiara, Valerio, Lorenzo, Kertész, János, Karsai, Márton

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids central coordin

Externí odkaz: http://arxiv.org/abs/2403.15855

Zobrazit plný text záznamu

Report

Crowdsourcing subjective annotations using pairwise comparisons reduces bias and error compared to the majority-vote method

Autor: Narimanzadeh, Hasti, Badie-Modiri, Arash, Smirnova, Iuliia, Chen, Ted Hsuan Yun

Publikováno v: Proceedings of the ACM on Human-Computer Interaction, CSCW2 (2023) 1-29

How to better reduce measurement variability and bias introduced by subjectivity in crowdsourced labelling remains an open question. We introduce a theoretical framework for understanding how random error and measurement bias enter into crowdsourced

Externí odkaz: http://arxiv.org/abs/2305.20042

Zobrazit plný text záznamu

Report

Control of synaptic plasticity via the fusion of reinforcement learning and unsupervised learning in neural networks

Autor: Modiri, Mohammad

The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and arti

Externí odkaz: http://arxiv.org/abs/2303.14705

Zobrazit plný text záznamu

Report

Control of synaptic plasticity in neural networks

Autor: Modiri, Mohammad

The brain is a nonlinear and highly Recurrent Neural Network (RNN). This RNN is surprisingly plastic and supports our astonishing ability to learn and execute complex tasks. However, learning is incredibly complicated due to the brain's nonlinear nat

Externí odkaz: http://arxiv.org/abs/2303.07273

Zobrazit plný text záznamu

Akademický článek

Combining evolutionary computation with machine learning technique for improved short-term prediction of UT1-UTC and length-of-day

Autor: Sujata Dhar, Robert Heinkelmann, Santiago Belda, Sadegh Modiri, Harald Schuh, Sonia Guessoum, José Manuel Ferrándiz, Nagarajan Balasubramanian, Onkar Dikshit

Publikováno v: Earth, Planets and Space, Vol 76, Iss 1, Pp 1-21 (2024)

Abstract Over the years, prediction techniques for the highly variable angular velocity of the Earth represented by Earth's rotation (UT1-UTC) and length-of-day (LOD) have been continuously improved. This is because many applications like navigation,

Externí odkaz: https://doaj.org/article/231dbdac8c46420580438fd2a27a75ae

Zobrazit plný text záznamu

Akademický článek

Findings on celestial pole offsets predictions in the second earth orientation parameters prediction comparison campaign (2nd EOP PCC)

Publikováno v: Earth, Planets and Space, Vol 76, Iss 1, Pp 1-21 (2024)

Abstract In 2021, the International Earth Rotation and Reference Systems Service (IERS) established a working group tasked with conducting the Second Earth Orientation Parameters Prediction Comparison Campaign (2nd EOP PCC) to assess the current accu

Externí odkaz: https://doaj.org/article/4d751497cbf947a49cdf6836cce80ee8

Zobrazit plný text záznamu

Report

Reticula: A temporal network and hypergraph analysis software package

Autor: Badie-Modiri, Arash, Kivelä, Mikko

Publikováno v: SoftwareX 21 (2023) 101301

In the last decade, temporal networks and static and temporal hypergraphs have enabled modelling connectivity and spreading processes in a wide array of real-world complex systems such as economic transactions, information spreading, brain activity a

Externí odkaz: http://arxiv.org/abs/2207.10771

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání