Redirigiendo al acceso original de articulo en 22 segundos...
Inicio  /  Information  /  Vol: 11 Par: 2 (2020)  /  Artículo
ARTÍCULO
TITULO

On the Integration of Knowledge Graphs into Deep Learning Models for a More Comprehensible AI?Three Challenges for Future Research

Giuseppe Futia and Antonio Vetrò    

Resumen

Deep learning models contributed to reaching unprecedented results in prediction and classification tasks of Artificial Intelligence (AI) systems. However, alongside this notable progress, they do not provide human-understandable insights on how a specific result was achieved. In contexts where the impact of AI on human life is relevant (e.g., recruitment tools, medical diagnoses, etc.), explainability is not only a desirable property, but it is -or, in some cases, it will be soon-a legal requirement. Most of the available approaches to implement eXplainable Artificial Intelligence (XAI) focus on technical solutions usable only by experts able to manipulate the recursive mathematical functions in deep learning algorithms. A complementary approach is represented by symbolic AI, where symbols are elements of a lingua franca between humans and deep learning. In this context, Knowledge Graphs (KGs) and their underlying semantic technologies are the modern implementation of symbolic AI?while being less flexible and robust to noise compared to deep learning models, KGs are natively developed to be explainable. In this paper, we review the main XAI approaches existing in the literature, underlying their strengths and limitations, and we propose neural-symbolic integration as a cornerstone to design an AI which is closer to non-insiders comprehension. Within such a general direction, we identify three specific challenges for future research?knowledge matching, cross-disciplinary explanations and interactive explanations.

 Artículos similares

       
 
Meng-Leong How and Sin-Mei Cheah    
The fusion of quantum computing and artificial intelligence (AI) heralds a transformative era for Industry 4.0, offering unprecedented capabilities and challenges. This paper delves into the intricacies of quantum AI, its potential impact on Industry 4.0... ver más
Revista: AI

 
Rola R. Hassan, Manar Abu Talib, Fikri Dweiri and Jorge Roman    
Implementing the European Foundation for Quality Management (EFQM) business excellence model in organizations is time- and cost-consuming. The integration of artificial intelligence (AI) into the EFQM business excellence model is a promising approach to ... ver más
Revista: Applied Sciences

 
Ziyi Wang, Xinran Li, Luoyang Sun, Haifeng Zhang, Hualin Liu and Jun Wang    
Efficient yet sufficient exploration remains a critical challenge in reinforcement learning (RL), especially for Markov Decision Processes (MDPs) with vast action spaces. Previous approaches have commonly involved projecting the original action space int... ver más
Revista: Algorithms

 
Dibo Dong, Shangwei Wang, Qiaoying Guo, Yiting Ding, Xing Li and Zicheng You    
Predicting wind speed over the ocean is difficult due to the unequal distribution of buoy stations and the occasional fluctuations in the wind field. This study proposes a dynamic graph embedding-based graph neural network?long short-term memory joint fr... ver más

 
Liushuai Cao, Yanyan Pan, Gang Gao, Linjie Li and Decheng Wan    
Wakes produced by underwater vehicles, particularly submarines, in density-stratified fluids play a pivotal role across military, academic, and engineering domains. In comparison to homogeneous fluid environments, wakes in stratified flows exhibit distin... ver más