Yalcinselcuk·Oct 19, 2025Convolutional Neural Networks: AlexNet, U-Net, ResNet and DenseNet ArchitecturesIf you’ve ever wondered how machines can recognise cats in photos, detect tumours in scans, or even make sense of videos, the secret often…
Yalcinselcuk·Sep 5, 2025Thrustworthy Machine Learning: Concept-Based Models: Testing with Concept Activation Vector (TCAV)Understanding the behaviour of modern machine learning (ML) models, especially deep neural networks, remains one of the central challenges…
Yalcinselcuk·Sep 3, 2025Trustworthy Machine Learning: From Black-Box Models to Transparent and Responsible AITrustworthy AI refers to artificial intelligence systems that are explainable, fair, interpretable, robust, transparent, safe, and secure…
Yalcinselcuk·Aug 25, 2025Entropy, KL Divergence, and Binary Cross-Entropy: An Information-Theoretic View of LossIn the field of machine learning, loss functions are more than just mathematical tools; they are the language that models use to learn from…
Yalcinselcuk·Aug 5, 2025Information Processing and Communication: A Beginner’s Guide to Information ProcessingIn a world flooded with information from voice assistants recognising our speech to algorithms sorting our photos, how do machines make…
Yalcinselcuk·Jul 18, 2025Thrustworthy Machine Learning: Gradient/Decomposition-based XAI: GradCAMGrad-CAM (Gradient-weighted Class Activation Mapping) is a technique designed to produce ‘visual explanations’ for decisions made by a wide…
Yalcinselcuk·Jul 8, 2025Thrustworthy Machine Learning: Gradient/Decomposition-based XAI: Saliency MapsA saliency map is a visualization method used to identify the most influential regions of an input image that contribute to a deep…A response icon1A response icon1
Yalcinselcuk·Jul 6, 2025Thrustworthy Machine Learning Score Estimation: Nested Cross-ValidationNested cross-validation is a trustworthy method for model evaluation and score estimation.
Yalcinselcuk·Jul 4, 2025Thrustworthy Machine Learning Score Estimation: Cross-ValidationCross-validation, like holdout set evaluation or the bootstrapping method, is a widely used score estimation technique in machine learning…