OCW, Vishal Sikka Keynote – Live updates

by | Oct 18, 2022

Live from the event

Can’t watch the event? (https://www.oracle.com/cloudworld) We’ve got you covered. Follow along to our updates below.

4:32 PDT: Try out the performance optimization of your model, yourself: Http://bit.ly/Vianai 

4:29 PDT: Demonstrate 100X improvement for Schneider Electric.

 

4:28 PDT: Edge machines live for decades… You need to run high-quality models on these, but usually they’re too big. Shrink down an AI model, and have them run on the device. Accelerated predictive maintenance by 1,000X. 

4:26 PDT: Accelerated tabular data — we accelerated inference time by more than 100X, and shrank the footprint of the model by 300X. 

4:25 PDT: Our acceleration is in software, regardless of the hardware that it’s running. 10X acceleration of inference for a semiconductor system, reduced the size by 27X. 

4:23 PDT: Accelerate the performance of a model on an autonomous vehicle — created a 4X improvement on inference acceleration and shrank the size to 1/5 of it. 

4:21 PDT: Performance of AI — the third part of my talk. As the models have become larger. GPT had 175 billion parameters. Google released a 540 billion parameter model called PaLM. 

 4:19 PDT: Payment processor processing thousands of events per second — the breakthrough for us is the sheer scale. Tested on 95 billion transactions in a quarter. 

 4:17 PDT: Bias, fairness, make it actionable — requires monitoring. This is our platform. This is designed for massive scale.

 3:55 PDT: The video just started up and we’re tuned in. Keep an eye on the blog for more updates! 

We have the ability and
opportunity to change the world.

Home

Who We Are

What We Do

Noteworthy

Contact Us

Career

Home

Who We Are

What We Do

Noteworthy

Contact Us

Career

© Vianai Systems, Inc. Privacy