[PDF][PDF] Randomized Machine Learning Approaches: Recent Developments and Challenges.

C Gallicchio, JD Martín-Guerrero, A Micheli… - ESANN, 2017 - researchgate.net
Randomness has always been present in one or other form in Machine Learning (ML)
models. The last few years have seen a change of role in the use of randomness, which is …

icompass at arabic hate speech 2022: Detect hate speech using qrnn and transformers

MA Bennessir, M Rhouma, H Haddad… - … on Qur'an QA and Fine …, 2022 - aclanthology.org
This paper provides a detailed overview of the system we submitted as part of the
OSACT2022 Shared Tasks on Fine-Grained Hate Speech Detection on Arabic Twitter, its …

Data-driven multiobjective predictive optimal control of refining process with non-Gaussian stochastic distribution dynamics

M Li, P Zhou, L Wang, Y Yuan - IEEE Transactions on Industrial …, 2021 - ieeexplore.ieee.org
The fiber length and the Canadian standard freeness (CSF) are two key indices in
measuring pulp quality of the refining process with non-Gaussian stochastic distribution …

Using sub-character level information for neural machine translation of logographic languages

L Zhang, M Komachi - Transactions on Asian and Low-Resource …, 2021 - dl.acm.org
Logographic and alphabetic languages (eg, Chinese vs. English) have different writing
systems linguistically. Languages belonging to the same writing system usually exhibit more …

Data-driven predictive probability density function control of fiber length stochastic distribution shaping in refining process

M Li, P Zhou, Y Liu, H Wang - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Pulp is the most important raw material in paper industries, whose fiber length stochastic
distribution (FLSD) shaping directly determines the energy consumption and paper quality of …

Artificial neural networks with random weights for incomplete datasets

DPP Mesquita, JPP Gomes, LR Rodrigues - Neural Processing Letters, 2019 - Springer
In this paper, we propose a method to design Neural Networks with Random Weights in the
presence of incomplete data. We present a method, under the general assumption that the …

Generalized entropy cost function in neural networks

K Gajowniczek, LJ Chmielewski, A Orłowski… - … Conference on Artificial …, 2017 - Springer
Artificial neural networks are capable of constructing complex decision boundaries and over
the recent years they have been widely used in many practical applications ranging from …

Voting based q-generalized extreme learning machine

D Stosic, D Stosic, T Ludermir - Neurocomputing, 2016 - Elsevier
A novel approach to extreme learning machine (ELM) ensembles is proposed. It
incorporates majority voting into the recently proposed q-generalized random neural …

An efficient approach for data-imbalanced hate speech detection in Arabic social media

MS Mohamed, H Elzayady, KM Badran… - Journal of Intelligent …, 2023 - content.iospress.com
The use of hateful language in public debates and forums is becoming more common.
However, this might result in antagonism and conflicts among individuals, which is …

Simulation study on the application of the generalized entropy concept in artificial neural networks

K Gajowniczek, A Orłowski, T Ząbkowski - Entropy, 2018 - mdpi.com
Artificial neural networks are currently one of the most commonly used classifiers and over
the recent years they have been successfully used in many practical applications, including …