Word of the Day: explainable AI

Word of the Day: Daily updates on the latest technology terms

Word of the Day Daily updates on the latest technology terms | November 8, 2019 explainable AI Explainable AI (XAI) is artificial intelligence that is programmed to describe its purpose, rationale and decision-making process in a way that can be understood by the average person. XAI is often discussed in relation to deep learning and plays an important role in the FAT ML model (fairness, accountability and transparency in machine learning). XAI provides general information about how an AI program makes a decision by disclosing: The program's strengths and weaknesses. The specific criteria the program uses to arrive at a decision. Why a program makes a particular decision as opposed to alternatives. The level of trust that's appropriate for various types of decisions. What types of errors the program is prone to. How errors can be corrected.   An important goal of XAI is to provide algorithmic accountability. Until recently, AI systems have essentially been black boxes. Even if the inputs and outputs are known, the algorithms used to arrive at a decision are often proprietary or not easily understood, even when the inner-workings of the programming are open source and made freely available. As artificial intelligence becomes increasingly prevalent, it is becoming more important than ever to disclose how bias and the question of trust are being addressed. The EU's General Data Protection Regulation (GDPR), for example, includes a right to explanation clause. Quote of the Day "Once you get on the wrong side of an algorithm, your life immediately becomes more difficult." - Greg Satell Related Terms artificial intelligence deep learning algorithmic accountability machine learning bias AI governance black box AI AI democratization Learning Center As more push for explainable AI, companies add features As businesses demand more explainable AI, vendors such as IBM and DarwinAI are introducing new features to help break down for business users how AI systems work. Hiring vendor says gender-based AI bias is pervasive Gender bias in AI algorithms for recruiting and hiring is a big problem, according to the head of Job.com. With a new hire, the company is planning to change that. New AI laws could impact how HR operates Federal, state and local governments are turning its attention to the use of AI in all aspects of life. This includes how HR is using automated decision support systems. Explainability is no solution to problem of bias in AI Explainability has been touted as a solution to the problem of biased AI models, but experts say that approach only gets you part of the way to bias-free applications. Quiz Yourself From customized hardware to APIs, public cloud providers now tout a wide range of machine learning and AI technologies. How well have you kept up with this rapidly evolving market? Take the quiz and find out!     Stay in Touch For feedback about any of our definitions or to suggest a new definition, please contact us at: editor@whatIs.com FOLLOW US About This E-Newsletter The Word of the Day is published by TechTarget, Inc., 275 Grove Street, Newton, Massachusetts, 02466 US. Click to: Unsubscribe. You are receiving this email because you are a member of TechTarget. When you access content from this email, your information may be shared with the sponsors or future sponsors of that content and with our Partners, see up-to-date Partners List, as described in our Privacy Policy. For additional information, please contact: webmaster@techtarget.com. © 2019 TechTarget, Inc. all rights reserved. Designated trademarks, brands, logos, and service marks are the property of their respective owners. Privacy Policy | Partners List