Browse Articles

Understanding the impossibility of machine learning fairness with data examples

Pillutla et al. | Sep 04, 2026

Understanding the impossibility of machine learning fairness with data examples

Machine learning systems are often expected to make fair decisions, yet the most widely used fairness criteria—independence, separation, and sufficiency—cannot generally be satisfied at the same time. In this study, students tested these criteria using a logistic regression model on a real-world student performance dataset and found that each criterion was met only at different prediction thresholds, with no threshold satisfying all three simultaneously. These results illustrate the inherent trade-offs in algorithmic fairness and highlight why achieving perfectly fair machine learning models is often impossible in practice.

Read More...

Assessing machine learning model efficacy for brain tumor MRI classification: a multi-model approach

Dhingra et al. | Mar 14, 2026

Assessing machine learning model efficacy for brain tumor MRI classification: a multi-model approach
Image credit: Dhingra and Dhingra

This manuscript explores the performance of five different machine learning models in classifying brain tumors from a dataset of MRI scans. The authors find that several of the models showed >90% accuracy. Thus, the authors suggest that machine learning models demonstrate potential for effective implementation in clinical settings, including as a diagnostic tool that can be used to complement the expertise of neuroradiologists.

Read More...

Deep learning for pulsar detection: Investigating hyperparameter effects on TensorFlow classification accuracy

Upadhyay et al. | Jan 31, 2026

Deep learning for pulsar detection: Investigating hyperparameter effects on TensorFlow classification accuracy

This study investigates how the hyperparameters epochs and batch size affect the classification accuracy of a convolutional neural network (CNN) trained on pulsar candidate data. Our results reveal that accuracy improves with increasing number of epochs and smaller batch sizes, suggesting that with optimized hyperparameters, high accuracy may be achievable with minimal training. These findings offer insights that could help create more efficient machine learning classification models for pulsar signal detection, with the potential of accelerating pulsar discovery and advancing astrophysical research.

Read More...

Evaluating the performance of Q-learning-based AI in auctions

Liu et al. | Nov 09, 2025

Evaluating the performance of Q-learning-based AI in auctions
Image credit: Liu and Liu

Advertising platforms like Google Ads use AI to drive the algorithms used to maximize advertisers benefits. This study shows that AI does not adjust it strategy based on auction type and highlights the limitations of AI running without explicit guidance.

Read More...

Machine learning predictions of additively manufactured alloy crack susceptibilities

Gowda et al. | Nov 12, 2024

Machine learning predictions of additively manufactured alloy crack susceptibilities

Additive manufacturing (AM) is transforming the production of complex metal parts, but challenges like internal cracking can arise, particularly in critical sectors such as aerospace and automotive. Traditional methods to assess cracking susceptibility are costly and time-consuming, prompting the use of machine learning (ML) for more efficient predictions. This study developed a multi-model ML pipeline that predicts solidification cracking susceptibility (SCS) more accurately by considering secondary alloy properties alongside composition, with Random Forest models showing the best performance, highlighting a promising direction for future research into SCS quantification.

Read More...