Evolution Of Activation Functions for Neural Architecture Search by Nader, Andrew

“…However, to the best of our knowledge, the design of new activation functions has mostly been done by hand. In this work, we propose the use of a self-adaptive evolutionary algorithm that searches for new activation functions using a genetic programming approach, and we compare the performance of the obtained activation functions to ReLU. …”
Get full text
Get full text
Get full text

Genetic and heuristic algorithms for regrouping service sites. (c2000) by Tabbara, Hiba

Get full text
Get full text

Defense against adversarial attacks: robust and efficient compressed optimized neural networks by Insaf Kraidia (19198012)

“…A cumulative updating loss function was employed for overall optimization, demonstrating remarkable superiority over traditional optimization techniques. …”

Cortical EEG Source Localization of Focal Epilepsy by Siyam, Wisal Elfatih Mohamed

Get full text

R-CONV++: uncovering privacy vulnerabilities through analytical gradient inversion attacks by Tamer Ahmed Eltaras (22565414)

“…The first algorithm presents a novel data leakage method that efficiently exploits convolutional layer gradients, demonstrating that even with non-fully invertible activation functions, such as ReLU, training samples can be analytically reconstructed directly from gradients without the need to reconstruct intermediate layer outputs. …”

Autonomous Robot Navigation Based On Recurrent Neural Networks by Al-Sagban, Mariam Qusai

Get full text

The Use of Enumerative Techniques in Topological Optimization of Computer Networks Subject to Fault Tolerance and Reliability by Abd-El-barr, Mostafa

“…A fault tolerant network is able to function even in the presence of some faults in the network. …”
Get full text

Prediction of biogas production from chemically treated co-digested agricultural waste using artificial neural network by Fares Almomani (12585685)

“…<p dir="ltr">The present study evaluates the effect of co-digestion of agricultural solid wastes (ASWs), cow manure (CM), and the application of chemical pre-treatment with NaHCO₃ on the performance of anaerobic digestion (AD) process. …”

Large language models for code completion: A systematic literature review by Rasha Ahmad Husein (19744756)

“…This is achieved by predicting subsequent tokens, such as keywords, variable names, types, function names, operators, and more. Different techniques can achieve code completion, and recent research has focused on Deep Learning methods, particularly Large Language Models (LLMs) utilizing Transformer algorithms. …”

DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins by Samir Brahim, Belhaouari

“…ObjectiveThis study utilized various classical machine learning techniques, such as support vector machines, k-nearest neighbors, and random forests, in conjunction with a modified deep learning approach called DeepRaman. These algorithms were employed to distinguish and categorize bacterial endotoxins, following appropriate spectral pre-processing, which involved novel filtering techniques and advanced feature extraction methods. …”
Get full text
Get full text
Get full text