The widespread adoption of deep-learning models in data-driven applications has drawn attention to the potential risks associated with biased datasets and models. Neglected or hidden biases within datasets and models can lead to unexpected results. This study addresses the challenges of dataset bias and explores “shortcut learning” or “Clever Hans effect” in binary classifiers. We propose a novel framework for analyzing the black-box classifiers and for examining the impact of both training and test data on classifier scores. […]

Ver mais

I was prototyping a 2D Side Scroller game in Unity a week ago and started implementing an Inventory System (Equipments, slots, etc…). Unfortunately, Unity didn’t have a Context Menu out of the box so I searched a bit and found this, which helped me get an idea of how to implement one as well as make it completely mouseless, since my game was mouseless itself.

Ver mais

Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected samples. In this study, we propose a novel loss function that estimates the confidence of each sample based on the entropy of its predicted probability distribution and applies confidence-based adaptive weighting. This approach enables pseudo-label assignment even to samples that were previously excluded from training and facilitates contrastive learning that […]

Ver mais

arXiv:2601.03276v1 Announce Type: new Abstract: Topic segmentation using generative Large Language Models (LLMs) remains relatively unexplored. Previous methods use semantic similarity between sentences, but such models lack the long range dependencies and vast knowledge found in LLMs. In this work, we propose an overlapping and recursive prompting strategy using sentence enumeration. We also support the adoption of the boundary similarity evaluation metric. Results show that LLMs can be more effective segmenters than existing methods, but issues remain to […]

Ver mais

Discussions and questions about methods, approaches, and tools for estimating (relative) binding free energies of protein-ligand complexes are quite popular, and even the simplest tools can be quite tricky to use. Here, I want to briefly summarize the idea of molecular docking, and give a short overview about how we can use AutoDock 4.2’s hybrid approach for evaluating binding affinities.

Ver mais

This blog post was initiated by Dr. Vince Calhoun, director of the Tri-institutional Center for Translational Research in Neuroimaging and Data Science and of Georgia State University, Georgia Institute of Technology, and Emory University. Vince shot me an email asking if I saw this editorial in Brain by Dimitri Kullman (Brain, Volume 143, Issue 4, April 2020, Page 1045) https://academic.oup.com/brain/article/143/4/1045/5823483. He also made the suggestion that we write something together as a counterpoint. I heartily agreed. While there […]

Ver mais