Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Citations
2,827 citations
1,602 citations
Cites background from "Peeking Inside the Black-Box: A Sur..."
...Although some recent surveys [8, 13, 10, 14, 15, 16, 17] summarize the upsurge of activity in XAI across sectors and disciplines, this overview aims to cover the creation of a complete unified framework of categories and concepts that allow for scrutiny and understanding of the field of XAI methods....
[...]
...One of the last surveys very briefly introduced the idea of algorithm property and trade secrets [14]....
[...]
813 citations
Cites background or methods from "Peeking Inside the Black-Box: A Sur..."
...The main goal is to create a suite of interpretable models and methods that produce more explainable models whilst preserving high predictive performance levels [2]....
[...]
...important decisions to a system that cannot explain itself and cannot be explained by humans presents evident dangers [2]....
[...]
...According to Adadi and Berrada, only 5% of the papers they have studied for their XAI survey focus on this particular issue of assessing interpretability methods [2]....
[...]
...Whether the presence is in our daily life, with examples ranging from movie recommendation systems to personal voice assistants, or in highly regulated domains involving decisions of great impact, such as mortgage approval models or healthcare decision support systems, the democratization of Artificial Intelligence (AI) in our society is undeniable [2]....
[...]
...Following this example, it is important to take into consideration that, given the number of existing interpretability methods, the need for comparing, validating, quantifying, and thus evaluating these methods arises [2]....
[...]
808 citations
543 citations
References
24,012 citations
"Peeking Inside the Black-Box: A Sur..." refers background in this paper
...Though it could be significantly complex and costly, most recent works done in XAI field belong to post-hoc class, it includes natural language explanations [71], visualizations of learned models [72], and explanations by example [73]....
[...]
12,857 citations
Additional excerpts
...Distillation is a model compression to transfer information (dark knowledge) from deep networks (the ‘‘teacher’’) to shallow networks (the ‘‘student’’) [121], [122]....
[...]
12,783 citations
11,104 citations
7,818 citations
"Peeking Inside the Black-Box: A Sur..." refers background in this paper
...For example, given that AlphaGo Zero [40] can excel at the game of Go much better than human players, it would be desirable that the machine can explain its learned strategy (knowledge) to us....
[...]