Building Safe AI: A Tutorial on Homomorphically Encrypted Deep Learning

TLDR: In this blogpost, we’re going to train a neural network that is fully encrypted during training (trained on unencrypted data). The result will be a neural network with two beneficial properties. First, the neural network’s intelligence is protected … Read more

Similar

AI Alignment: Why It’s Hard, and Where to Start

Back in May, I gave a talk at Stanford University for the Symbolic Systems Distinguished Speaker series, titled “The AI Alignment Problem: Why It’s Hard, And Where To Start.” The video for this talk is now available on Youtube:     We have an appr...

Read more »

AI FAQ Index

[By Archive-name | By Author | By Category | By Newsgroup | Forum archive] [Home | Latest Updates | Archive Stats | Search | Help] (more…)

Read more »

The Godfather of AI Was Almost a Carpenter

He is an Engineering Fellow at Google, managing Brain Team Toronto, the Chief Scientific Adviser of the Vector Institute, and Emeritus Professor at the University of Toronto. His name is Geoffrey Hinton, and this Bloomberg 50 profile of him takes a peek i... (more…)

Read more »