Original article was published on Artificial Intelligence on Medium
Nicole Junkermann presents an A-Z of AI: C = Chips
While the transformational potential of AI on the wider economy may grab the headlines, behind the scene, artificial intelligence is also driving a revolution in chip design.
Machine learning means processing vast volumes of simultaneous calculations and conventional CPU chips are not designed for the task.
The repurposing of existing GPU (graphical processing units) and FPGA (field programmable gate array) chips for AI systems led to huge gains in speed and efficiency.
Now the race is on to develop a new generation of ASIC (application specific integrated circuit) chips purpose-built for AI.
Taking the field are innovative start-ups like Groq and Cerebus, alongside tech giants like Google and Intel.
A potential multi-billion dollar market is at stake.
Tesla, Facebook and Amazon all have in-house AI chip programs.
Nicole Junkermann, NJF Capital founder, presents an A-Z of Artificial Intelligence — a series of short videos focused on key areas of interest in this hugely topical and consequential field.