Histogram plots of the optimized temperature parameter values during the calibration
Congratulations to Farhad Pourkamali-Anaraki on the acceptance of his research paper at the SIAM International Conference on Data Mining (SDM 2026), taking place in Salt Lake City, Utah, this November.
Also, with an acceptance rate of just 26% this year, making it very competitive.
His paper, "Aerial Image Classification in Scarce and Unconstrained Environments via Conformal Prediction," explores how conformal prediction can provide reliable uncertainty estimates for aerial image classification in challenging, data-scarce environments. The work offers valuable insights into improving the trustworthiness of AI models while examining the impact of calibration techniques on prediction reliability and efficiency.
Congratulations to Farhad on this outstanding achievement and best wishes for future endeavors!