explainable AI

explainable AI, Google, OpenAI

OpenAI and Google researchers have created activation atlases, which is a new technique for visualizing what interactions between neurons can represent. As AI systems are deployed in increasingly sensitive contexts,…

Guide for making black box models explainable

March 8, 2019

Christoph Molnar, explainable AI

Machine learning has great potential for improving products, processes and research. But computers usually do not explain their predictions which is a barrier to the adoption of machine learning. This…

Google publishes AI ethics white paper calling for global standards

February 22, 2019

AI ethics, explainable AI, Google

Google has published a white paper highlighting five specific areas where concrete, context-specific guidance from governments and civil society would help to advance the legal and ethical development of AI:…

ZestFinance tackles explainable AI with Microsoft Azure

January 11, 2019

explainable AI, fintech credit, Microsoft Azure, ZestFinance

ZestFinance announced a strategic collaboration with Microsoft to deploy Zest’s machine learning (ML) software tools directly on Microsoft Azure and Machine Learning Server platforms to deliver the first fully explainable…

Lux regulator warns that AI should be explainable by design

January 6, 2019

AI ethics, artificial intelligence, CSSF, explainable AI, Luxembourg, machine learning

Institutions should implement measures to ensure explainability of their artificial intelligence and machine learning systems from the design phase, according to a recent publication from Commission de Surveillance du Secteur Financier…

2018 year in review: what happened in advanced (fin)tech

December 18, 2018

Artificial Intelligence, Technology

artificial intelligence, explainable AI, Quantum Computing

2018 was predicted to be the year of AI by many experts across a variety of sectors, and it was. But it’s also the year that quantum computing started to…

Dataiku: intro to machine learning interpretability

December 4, 2018

Dataiku, explainable AI, machine learning

Understanding and trusting models and their results is a hallmark of good science. Scientists, engineers, physicians, researchers, and humans in general have the need to understand and trust models and…

Nvidia boasts deep learning hardware breakthroughs, but early days for finance (Premium)

October 23, 2018

Artificial Intelligence, Technology

deep learning, explainable AI, hardware acceleration, neural networks, Nvidia, Optimizing Mind

Nvidia has been getting a lot of attention for its GPU strategy in an era of artificial intelligence, not least due to the atmospheric rise of its stock price over…

FICO launches cloud-based analytics with explainable AI

September 14, 2018

explainable AI, FICO, regtech

FICO said its made artificial intelligence explainable (xAI) in the latest release of its Analytics workbench. Its built for data scientists but also business users and provides automated regulatory audit…

Raytheon making neural network that explains itself

August 30, 2018

DARPA, explainable AI, Raytheon