Vol. 6 No. 2 (2026): July-Dec 2026

Articles

• When uncertainty sampling backfires: A benchmark of active learning query strategies on real image datasets

  Kelvin Lleins Rojas-Córdova, Monica Gabriela Leveau-Paredes, Jhosep Sánchez-Flores

  1-14

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.1.14

  • PDF
  • XML
  • Video Summary
• Equally accurate, differently explained: Stability of permutation feature importance across machine learning classifiers on clinical tabular data

  Surjeet Dalal, Mohd Akbar

  15-31

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.15.31

  • PDF
  • XML
  • Video Summary
• Same accuracy, different failures: Robustness of pixel-based, gradient-feature and augmented classifiers to common image corruptions

  Bilal Öztürk, Kelvin Lleins Rojas-Córdova

  32-43

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.32.43

  • PDF
  • XML
  • Video Summary
• No single winner: Forecast combination versus neural and tree-based learners on short monthly time series

  Heri Nurdiyanto, Abid Khan

  44-55

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.44.55

  • PDF
  • XML
  • Video Summary
• Do saliency maps find the defect? A ground-truth evaluation of explainable AI for safety-critical magnetic tile inspection

  Heri Nurdiyanto, Nuno Alexandre Soares Domingues

  56-72

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.56.72

  • PDF
  • XML
  • Video Summary
• Numbers keep the spam out: Robustness of word- and character-level SMS spam filters to obfuscation and good-word attacks

  Muntaser Syed, Salahddine Krit

  73-83

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.73.83

  • PDF
  • XML
  • Video Summary
• Learning before memorising: How far does early stopping protect multilayer perceptrons from label noise?

  Muntaser Syed, Hidayath Ali Baig Mohammed

  84-97

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.84.97

  • PDF
  • XML
  • Video Summary
• Stability and robustness of explainable artificial intelligence methods in clinical prediction models: Protocol for a systematic review

  Surjeet Dalal, Danish Ather

  98-105

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.98.105

  • PDF
  • XML
  • Video Summary
• Calibrated but not safe: Conformal prediction intervals for turbofan remaining useful life near end of life and under operating shift

  Nuno Alexandre Soares Domingues, Danish Ather

  106-119

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.106.119

  • PDF
  • XML
  • Video Summary
• Tuned on paper, not in practice: How much does hyperparameter tuning improve classifiers on small tabular datasets?

  Parvinder S. Sandhu, Jhosep Sánchez-Flores

  120-133

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0 Video Summary downloaded: 0

  DOI : 10.55529/jaimlnn.62.120.133

  • PDF
  • XML
  • Video Summary
• Matched, mismatched and blind: How well does a patch-based neural denoiser trained on six photographs generalise across noise levels and image domains?

  Bilal Öztürk

  134-145

  Abstract viewed: 0 PDF downloaded: 0 XML downloaded: 0

  DOI : 10.55529/jaimlnn.62.134.145

  • PDF
  • XML