Author: Mahmoud Ghorbel

Mahmoud Ghorbel
110 POSTS0 COMMENTS
Mahmoud is a PhD researcher in machine learning. He also holds a bachelor's degree in physical science and a master's degree in telecommunications and networking systems. His current areas of research concern computer vision, stock market prediction and deep learning. He produced several scientific articles about person re- identification and the study of the robustness and stability of deep networks.

Large Language Models LLMs for OCR Post-Correction

Optical Character Recognition (OCR) converts text from images into editable data, but it often produces errors due to issues like poor image quality or...

AI in Medical Imaging: Balancing Performance and Fairness Across Populations

As AI models become more integrated into clinical practice, assessing their performance and potential biases towards different demographic groups is crucial. Deep learning has...

Assessing Noise Impact on Machine Learning Models for Voice Disorder Evaluation

Deep learning has become a powerful tool for classifying pathological voices, particularly in the GRBAS (Grade, Roughness, Breathiness, Asthenia, Strain) scale assessment. The GRBAS...

Future-Proofing the Past: AI’s Role in Protecting Cultural Legacies

The world's cultural heritage faces mounting peril from escalating conflicts and natural disasters, jeopardizing ancient sites and artifacts worldwide. Wars, earthquakes, and floods pose...

DoRM: A Brain-Inspired Approach to Generative Domain Adaptation

Few-shot Generative Domain Adaptation (GDA) is a machine learning and domain adaptation concept that addresses the challenge of adapting a model trained on a...

Navigating the Challenges of Selective Classification Under Differential Privacy: An Empirical Study

In machine learning, differential privacy (DP) and selective classification (SC) are essential for safeguarding sensitive data. DP adds noise to preserve individual privacy while...

Boosting Classification Accuracy: Integrating Transfer Learning and Data Augmentation for Enhanced Machine Learning Performance

Transfer learning is particularly beneficial when there is a distribution shift between the source and target datasets and a scarcity of labeled samples in...

FAMO: A Fast Optimization Method for Multitask Learning (MTL) that Mitigates the Conflicting Gradients using O(1) Space and Time

Multitask learning (MLT) involves training a single model to perform multiple tasks simultaneously, leveraging shared information to enhance performance. While beneficial, MLT poses challenges...

Towards Fairer AI: Strategies for Instance-Wise Unlearning Without Retraining

The increasing reliance on machine learning models in critical applications raises concerns about their susceptibility to manipulation and exploitation. Once trained on a dataset,...

Continual Adapter Tuning (CAT): A Parameter-Efficient Machine Learning Framework that Avoids Catastrophic Forgetting and Enables Knowledge Transfer from Learned ASC Tasks to New ASC...

Aspect Sentiment Classification (ASC) is a critical task aimed at discerning sentiment polarity within specific domains, such as product reviews, where the sentiment toward...

Revolutionizing Robotic Surgery with Neural Networks: Overcoming Catastrophic Forgetting through Privacy-Preserving Continual Learning in Semantic Segmentation

Deep Neural Networks (DNNs) excel in enhancing surgical precision through semantic segmentation and accurately identifying robotic instruments and tissues. However, they face catastrophic forgetting...

Enhancing Underwater Image Segmentation with Deep Learning: A Novel Approach to Dataset Expansion and Preprocessing Techniques

Underwater image processing combined with machine learning offers significant potential for enhancing the capabilities of underwater robots across various marine exploration tasks. Image segmentation,...