The key advantage of artificial intelligence (AI) is its ability to simulate human reasoning and react quickly to large volumes of many different inputs. This is also its drawback, however, since the complexity of the AI decision-making process is often not transparent. Complex machine learning models in AI, such as deep neural networks, are often black boxes. The lack of transparency is known as an explainability problem and can lead to trust and ethical issues. Technology Magazine brought this interesting information to our attention in their article, “Combining AI and blockchain for the future of data analytics.”
Some key features of blockchain — like immutable, transparent, digital records and decentralized data storage — could offer insights into the inner workings of AI. But it is no secret that most organizations have little knowledge regarding AI systems’ decision making and, as a result, it’s no surprise that the results are applied haphazardly and to little effect.
Explainable AI allows users to comprehend and trust the results and output created by machine learning algorithms. Explainable AI is used to describe an AI model, its expected impact, and its potential biases. Why is this important? Because explainability becomes critical when the results can have an impact on data security or safety.
Melody K. Smith
| Data Harmony is an award-winning semantic suite that leverages explainable AI. |
|
Sponsored by Access Innovations, the intelligence and the technology behind world-class explainable AI solutions.
