Home > TERATEC FORUM > Program

Forum Teratec 2022
Plenary session
Tuesday 14 June 2022

Digital Simulation for High Performance, Big Data and Machine Learning (AI): Technology challenges and diversity of use

The compute requirements of developing super-human cognition
Phil Brown
VP Scaled Systems, Graphcore

The true potential of AI rests on super-human learning capacity, and on the ability to selectively draw on that learning. Both of these properties – scale and selectivity – challenge the design of AI computers and the tools used to program them.  A rich pool of new ideas is emerging, driven by a new breed of computing company, according to Phil Brown.

In his talk, Paul discusses the creation of the Intelligence Processing Unit (IPU) – a new type of processor, specifically designed for AI computation. He looks ahead, towards the development of AIs with super-human cognition, and explores the nature of computation systems needed to make powerful AI an economic everyday reality.




© Ter@tec - All rights reserved - Lawful mention