10 citations · 11 across the 6 of their papers we have counts for
4 papers · 1 filter
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration
Gianluca Carloni
This work aligns deep learning (DL) with human reasoning capabilities and needs to enable more efficient, interpretable, and robust image classification. We approach this from thre…
Connectivity-Inspired Network for Context-Aware Recognition
Gianluca Carloni, Sara Colantonio
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neura…
Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRI
Gianluca Carloni, Eva Pachetti, Sara Colantonio
In this paper, we present a novel method to automatically classify medical images that learns and leverages weak causal signals in the image. Our framework consists of a convolutio…
Exploiting Causality Signals in Medical Images: A Pilot Study with Empirical Results
Gianluca Carloni, Sara Colantonio
We present a novel technique to discover and exploit weak causal signals directly from images via neural networks for classification purposes. This way, we model how the presence o…