← Search

Nona Rajabi

2 accepted papers

2025

Deep Learning Amplified Early Stopping Bias: Overestimating Performance on Small Datasets

ICASSP 2025accepted

Cross-validation is commonly used to estimate machine learning model performance on new samples. However, using it for both hyperparameter selection and error estimation can lead to overestimating model performance, especially with extensive hyperparameter searches that overly tailor models to valid…

Cited by 0SourceScholar
2025

Human-Aligned Image Models Improve Visual Decoding from the Brain

ICML 2025poster

Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches align the representation spaces of images and brain activity to enable visual decoding. In this paper, we introduce the…

Cited by 0SourcePDFScholar