Results 21 to 30 of about 64,893 (276)

Explaining Explaining

Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods
Explanation is key to people having confidence in high-stakes AI systems. However, machine-learning-based systems -- which account for almost all current AI -- can't explain because they are usually black boxes. The explainable AI (XAI) movement hedges this problem by redefining "explanation".
Nirenburg, Sergei, McShane, Marjorie, Goodman, Kenneth W., Oruganti, Sanjay   +3 more
openaire   +2 more sources

Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization

, 2019
One obstacle that so far prevents the introduction of machine learning models primarily in critical areas is the lack of explainability. In this work, a practicable approach of gaining explainability of deep artificial neural networks (NN) using an ...
Huber, Marco F., Maucher, Johannes, Schaaf, Nina   +2 more
core   +1 more source

X-OODM: Explainable Object-Oriented Design Methodology

IEEE Access
In software applications and decision-making systems, the explainability features can be instrumental for explicating internal working, accountability, understanding, fairness, and interpretation of decisions, processes, and data.
Abqa Javed, Muhammad Shoaib, Abdul Jaleel   +2 more
doaj   +1 more source

LIMEtree: Interactively Customisable Explanations Based on Local Surrogate Multi-output Regression Trees [PDF]

, 2020
Systems based on artificial intelligence and machine learning models should be transparent, in the sense of being capable of explaining their decisions to gain humans' approval and trust.
Flach, Peter, Sokol, Kacper
core   +1 more source

Explaining Latent Factor Models for Recommendation with Influence Functions

, 2018
Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation.
Bilgic Mustafa, He Xiangnan, Kingma Diederik, Koh Pang Wei, Lee Daniel D., Martens James, Rendle Steffen, Zhang Yongfeng   +7 more
core   +1 more source

The role of explainability throughout the MLOps lifecycle: review and research agenda

Frontiers in Computer Science
As Machine Learning Operations (MLOps) adoption accelerates, systematic integration of explainability is imperative for reliability, transparency, and continuous quality assurance.
Sule Tekkesinoglu, Matthias Wagner, Per Runeson   +2 more
doaj   +1 more source

The Multi-Lane Capsule Network (MLCN)

, 2019
We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost.
Borin, Edson, Breternitz Jr, Mauricio, Rosario, Vanderson Martins do   +2 more
core   +1 more source

Explaining Young Mortality [PDF]

SSRN Electronic Journal, 2011
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
O’Hare, Colin, Li, Youwei, O'Hare, Colin   +2 more
openaire   +3 more sources

Sirolimus for Extracranial Arteriovenous Malformations: A Scoping Review of the Evidence in Syndromic and Non‐Syndromic Cases

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Arteriovenous malformations (AVMs) are rare, high‐flow, vascular anomalies that can occur either sporadically or as part of a genetic syndrome. AVMs can progress with serious morbidity and even mortality if left unchecked. Sirolimus is an mTOR inhibitor that is effective in low‐flow vascular malformations; however, its role in AVMs is unclear.
Will Swansson, Ingrid Winship, Gary Hammerschlag, Laura Scardamaglia   +3 more
wiley   +1 more source

Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulation

, 2019
Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence.
Beyret, Benjamin, Faisal, A. Aldo, Shafti, Ali   +2 more
core   +1 more source