May 16, 2024, 4:43 a.m. | Caroline Mazini Rodrigues (LRDE, LIGM), Nicolas Boutry (LRDE), Laurent Najman (LIGM)

cs.LG updates on

arXiv:2401.14434v2 Announce Type: replace-cross
Abstract: The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations. Gradient-based methodologies, exemplified by Integrated Gradients (IG), effectively demonstrate the significance of these features. Nevertheless, the conversion of these explanations into images frequently yields considerable noise. Presently, we introduce GAD (Gradient Artificial Distancing) as a supportive framework for gradient-based techniques. Its primary objective is to accentuate …

abstract arxiv challenges cnn complexity conversion convolutional convolutional neural networks correlations cs.lg features gradient images interpretation networks neural networks pixels replace significance through type xai

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US