PodParley PodParley
PodParley
Optimizing Model Performance with Deci - CitC Episode 286 episode artwork

EPISODE · Nov 18, 2022 · 13 MIN

Optimizing Model Performance with Deci - CitC Episode 286

from Intel CitC · host Intel Corporation

Yonatan Geifman, Co-Founder & CEO at Deci, joins host Jake Smith to talk about how Deci’s AutoNAC (Automated Neural Architecture Construction) engine enables developers to redesign their deep learning models to significantly improve latency performance while preserving the model's accuracy. Yonatan further explained that improving latency and accuracy would allow developers to shorten the development cycle and deploy the optimized model to production environments faster. Yonatan shared with Jake the close and deep partnership Deci has developed with Intel in engineering collaboration and ecosystem programs. When asked about his thought on the future of AI, Yonatan said while it would take more time for AI to be everywhere, AI is being democratized by startups, large companies, and open-source communities, so more and more people will be able to build AI applications in the future. For more information, visit: https://deci.ai/ Follow Jake on Twitter at: https://twitter.com/jakesmithintel

Episode metadata supplied by the publisher feed · Published Nov 18, 2022

What this episode covers

Yonatan Geifman, Co-Founder & CEO at Deci, joins host Jake Smith to talk about how Deci’s AutoNAC (Automated Neural Architecture Construction) engine enables developers to redesign their deep learning models to significantly improve latency performance while preserving the model's accuracy. Yonatan further explained that improving latency and accuracy would allow developers to shorten the development cycle and deploy the optimized model to production environments faster. Yonatan shared with Jake the close and deep partnership Deci has developed with Intel in engineering collaboration and ecosystem programs. When asked about his thought on the future of AI, Yonatan said while it would take more time for AI to be everywhere, AI is being democratized by startups, large companies, and open-source communities, so more and more people will be able to build AI applications in the future. For more information, visit: https://deci.ai/ Follow Jake on Twitter at: https://twitter.com/jakesmithintel

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

Optimizing Model Performance with Deci - CitC Episode 286

0:00 13:14

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

China's Cyber Crews Go Shopping: Volt Typhoon Slides Into US Power Grids While APT31 Swipes Corporate Passwords

Jun 22, 2026 ·3m

Volt Typhoon is Back and They're Coming for Your VPN: Why Beijing is Mapping US Infrastructure Like a Heist Movie

Jun 21, 2026 ·4m

Intel Stock Surges 260 Percent: AI Boom or Speculative Bubble?

Jun 20, 2026 ·3m

Intel's Stunning Turnaround: From Forgotten Chip Maker to Momentum Stock

Jun 19, 2026 ·4m

Beijing's Data Plumbing Inspector and the Credential Thieves Who Never Sleep

Jun 19, 2026 ·3m

Intel's Turnaround Trap: Execution Bet at 120 Dollars

Jun 18, 2026 ·4m

Similar Podcasts

Intel Conversations in the Cloud Intel Intel Conversations in the Cloud is a weekly podcast with IT leaders who are driving the future of a software-defined infrastructure based data center. Featuring members of the Intel Builders programs, Intel experts, and industry analysts, this recurring podcast series provides information on delivering, deploying, and managing cloud computing, technology, and services in the data center and enterprise. Code Together Code Together Code Together is an interview series that explores challenges at the forefront of cross-architecture development. We’ll talk with those at Intel and across the industry who are forging a path on this often treacherous journey through an increasingly diverse, data-centric world. Join the conversation at oneapi.com. Intel Intel Intel consistently challenges the laws of physics as it advances chip technology, leading the industry in advances in technology, education, culture, manufacturing and social responsibility. From behind-the-scenes looks into building the latest chips to breaking news updates on the products that will take advantage of the newest advances in chip technology, find out directly from the experts at Intel. Bird Flu Intel: Facts, Not Fear, on H5N1 Inception Point AI This is your Bird Flu Intel: Facts, Not Fear, on H5N1 podcast.Bird Flu Intel: Facts, Not Fear on H5N1 is your go-to podcast for reliable and evidence-based information on the avian influenza virus. In a world where misinformation spreads rapidly, it’s vital to separate fact from fiction, and this podcast is dedicated to doing just that. Hosted by experts and structured to debunk myths surrounding H5N1, each episode features a concise, rational examination of common misconceptions about the virus.Through engaging dialogues between our [FACT CHECKER] and [SCIENTIST], you’ll gain clarity on myths such as the exaggerated spread of H5N1 to humans or misunderstanding its actual impact. Hear scientific evidence that dispels these myths, making the complex simple and accessible. Learn about the mechanisms of misinformation, how it can multiply fear, and the harm it causes. Equip yourself with powerful tools to evaluate the quality of information, ensuring you can discern credible sources fro

Frequently Asked Questions

How long is this episode of Intel CitC?

This episode is 13 minutes long.

When was this Intel CitC episode published?

This episode was published on November 18, 2022.

What is this episode about?

Yonatan Geifman, Co-Founder & CEO at Deci, joins host Jake Smith to talk about how Deci’s AutoNAC (Automated Neural Architecture Construction) engine enables developers to redesign their deep learning models to significantly improve latency...

Can I download this Intel CitC episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!