Work

Quantifying the Knowledge in Deep Neural Networks: An Overview

Year: 2026

Type: article

Abstract: Deep Neural Networks (DNNs) have proven to be extremely effective at learning a wide range of tasks. Due to their complexity and inexplicable internal state, DNNs are difficult to analyze. Several attempts to interpret their operation have been made, but analyzing them from the perspective of the knowledge encoded in their layers is a promising research direction. The purpose of this survey is two-fold: (a) to review the concept of DNN knowledge quantification and highlight it as an important near-future challenge, and (b) to provide a brief account of the scant existing methods attempting to actually quantify DNN knowledge.

Source: ACM Computing Surveys

DOI: 10.1145/3845595

Authors: Ioanna Valsamara, Ioannis Mademlis, Ioannis Pitas

Institution: Aristotle University of Thessaloniki

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Horizon 2020 Framework Programme

Award: G4397263494