RI: How can machines learn human values?

Basingstoke IVC Science Cafe invite you to this free Royal Institution talk titled "The alignment problem: how can machines learn human values?"

Please re-register for the event via this link: 

https://www.rigb.org/whats-on/events-2021/january/public-how-can-machines-learn-human

We will have the replay of the video available for 72 hours after the event for those of you that can’t make the new date. It will also be uploaded to YouTube in the future.

SUMMARY
Recent years have seen an eruption of concern about machine learning. When the systems we attempt to teach don’t do what we want or what we expect, ethical and potentially existential risks emerge.

In this talk, Brian Christian discusses the inherent biases in algorithms and the varying complexities of the systems that are making potentially life-changing decisions.  

Join Brian as he explores everything that goes wrong when we build AI systems and the people that will fix them.

ABOUT THE SPEAKER
Brian Christian is the author of 'The Most Human Human', which was named a Wall Street Journal bestseller, a New York Times Editors’ Choice, and a New Yorker favourite book of the year. He is the author, with Tom Griffiths, of 'Algorithms to Live By', a #1 Audible bestseller, Amazon best science book of the year and MIT Technology Review best book of the year.

His third book, 'The Alignment Problem', has just been published in the US and is forthcoming in the UK and in translation in 2021.

Born in Wilmington, Delaware, Christian holds degrees in philosophy, computer science, and poetry from Brown University and the University of Washington. A Visiting Scholar at the University of California, Berkeley, he lives in San Francisco.

Christian’s writing has been translated into nineteen languages, and has appeared in The New Yorker, The Atlantic, Wired, The Wall Street Journal, The Guardian, The Paris Review, and in scientific journals such as Cognitive Science. Christian has been featured on The Daily Show with Jon Stewart, Radiolab, and The Charlie Rose Show, and has lectured at Google, Facebook, Microsoft, the Santa Fe Institute, and the London School of Economics. His work has won several awards, including fellowships at Yaddo and the MacDowell Colony, publication in Best American Science & Nature Writing, and an award from the Academy of American Poets.