Miscellaneous

[Airicist]

Article "The problem of AI explainability - can we overcome it?"
Profile picture for user Neil Raden

by Neil Raden
February 6, 2020

[Airicist]

Explainable AI - Methods, Applications & Recent Developments - Dr. Wojciech Samek | ODSC Europe 2019

Feb 12, 2020

Dr. Wojciech Samek discusses methods, applications and recent developments of Explainable AI, in particular, demonstrates the effectivity of explanation techniques such as Layer-wise Relevance Propagation (LRP) when applied to various datatypes (images, text, audio, video, EEG/fMRI signals) and neural architectures (ConvNets, LSTMs). LRP provides information about individual predictions, e.g., heatmaps visualizing which pixels have been most relevant for the model to arrive at its decision. The talk will finish with a discussion of challenges and open questions in the field of explainable AI.

Dr. Wojciech Samek has founded and is heading the Machine Learning Group at Fraunhofer Heinrich Hertz Institute since 2014. He studied computer science at Humboldt University of Berlin, Heriot-Watt University and University of Edinburgh from 2004 to 2010 and received the Dr. rer. nat. degree with distinction (summa cum laude) from the Technical University of Berlin in 2014.

[Airicist]

Article "How Explainable AI Is Helping Algorithms Avoid Bias"

by Simon Chandler
February 18, 2020

[Airicist]

Article "What explainable AI really means and what it means for your business (VB Live)"

February 19, 2020

[Airicist]

Article "Preparing For AI Ethics And Explainability In 2020"

by Maribel Lopez
January 21, 2020

[Airicist]

Article "People prefer robots to explain themselves – and a brief summary doesn’t cut it"

by Tommy Ton
February 26, 2020

[Airicist]

Article "People prefer robots to explain themselves – and a brief summary doesn’t cut it"

by Mark Edmonds and Yixin Zhu
February 28, 2020

[Airicist]

Article "Weighing the trade-offs of explainable AI"
It’s hard to audit an algorithm if you don’t understand how it thinks. But the answer isn’t always making things simpler.

by Brian Nordli
February 28, 2020

[Airicist]

"Dark AI and the Promise of Explainability (Part I)"

"Dark AI and the Promise of Explainability (Part II)"

by Sheldon Fernandez
March 3, 2020

[Airicist]

Opening the black box with explainable A.I | TC Sessions: Robotics + AI 2020

Mar 5, 2020

Machine learning and AI models can be found in nearly every aspect of society today, but their inner workings are often as much a mystery to their creators as to those who use them. UC Berkeley’s Trevor Darrell, Krishna Gade of Fiddler Labs, and Karen Myers from SRI International will discuss what we’re doing about it and what still needs to be done.