fish fry
Subscribe Now

Faster AI! Go! Go!

How Deeplite’s Ultra-Compact Quantization is Making AI Smarter, Faster and Smaller

We are covering one of my favorite subjects this week: Artificial Intelligence! My guest is Nick Romano, Co-Founder & CEO of Deeplite AI. We investigate their new Deeplite Runtime which makes AI models smaller and faster in production deployment, why smart manufacturing is a great application for Deeplite AI, and why ultra-compact quantization is key to making AI smarter, faster, and smaller than ever before. Also this week, I examine “Raw Zero-Shot” – a new AI learning method developed by a team of researchers at Kyushu University that has potential to make AI more robust and reliable in the future.

 

 

Click here to download this episode

Links for July 8, 2022

More information about Deeplite AI

Breaking AIs to make them better: Researchers investigate ways to make AIs more robust by studying patterns in their answers when faced with the unknown (Kyushu University)

Transferability of features for neural networks links to adversarial attacks and defences (PLOS ONE)

Click here to check out the Fish Fry Archive.

Click here to subscribe to Fish Fry via Podbean

Click here to get the Fish Fry RSS Feed

Click here to subscribe to Fish Fry via Apple Podcasts

Click here to subscribe to Fish Fry via Spotify

 

Fish Fry Executive Interviews

Anupam Bakshi, CEO – Agnisys

Dave Kleidermacher, CTO – Green Hills Software

Robert Blake, CEO – Achronix

Jack Harding, CEO – eSilicon

Michiel Ligthart, COO – Verific

Simon Davidmann, CEO – Imperas

Jessica Gomez – Rogue Valley Microdevices

Shishpal Rawat, Chairman – Accellera Systems Initiative

Kevin Bromber, CEO – myDevices

Daniel Hansson, CEO – Verifyter

Mark Papermaster, CTO – AMD

David Fried, CTO – Coventor

Dr. Steven LeBoeuf, President – Valencell

David Dutton, CEO – Silvaco

Bob Niemiec, CEO – TwistThink

Allan Martinson, COO – Starship Technologies

Zhihong Liu, Chairman and CEO – ProPlus Solutions

Taher Madraswala, CEO and President – Open-Silicon

Kapil Shankar, CEO and Director – AnDAPT

Dan Fox, CTO – Local Motors

Kim Rowe, Founder and CEO — RoweBots

Lawrence Cooke, Founder and CEO — NovaSolix

Gregg Recupero, CTO — Performance-IP

Alan Grau, CEO — Icon Labs

Carl Alberty, Vice President – Cirrus Logic

Maximilian Odendahl, CEO — Silexica

Finbarr Moynihan, General Manager — MediaTek

Sanjay Pillay, CEO — Austemper

Louis Parks, CEO – SecureRF

Harold Blomquist, CEO – Helix Semiconductor

Dale Dougherty and Sherry Huss, Co-Founders – Maker Faire

David Su, CEO – Atomic Technologies

Mung Chiang, EVP and Dean of Engineering College – Purdue University

Clay Johnson, CEO – CacheQ

Andy Hock, Vice President, Product – Cerebras Systems

Dan Goehl, Co-founder and Chief Business Officer – UltraSense Systems

Charlie Green, Chief Operating & Technical Officer – Powercast

 

 

 

Leave a Reply

featured blogs
Dec 19, 2024
Explore Concurrent Multiprotocol and examine the distinctions between CMP single channel, CMP with concurrent listening, and CMP with BLE Dynamic Multiprotocol....
Dec 20, 2024
Do you think the proton is formed from three quarks? Think again. It may be made from five, two of which are heavier than the proton itself!...

Libby's Lab

Libby's Lab - Scopes Out Littelfuse's SRP1 Solid State Relays

Sponsored by Mouser Electronics and Littelfuse

In this episode of Libby's Lab, Libby and Demo investigate quiet, reliable SRP1 solid state relays from Littelfuse availavble on Mouser.com. These multi-purpose relays give engineers a reliable, high-endurance alternative to mechanical relays that provide silent operation and superior uptime.

Click here for more information about Littelfuse SRP1 High-Endurance Solid-State Relays

featured chalk talk

Accelerating Tapeouts with Synopsys Cloud and AI
Sponsored by Synopsys
In this episode of Chalk Talk, Amelia Dalton and Vikram Bhatia from Synopsys explore how you can accelerate your next tapeout with Synopsys Cloud and AI. They also discuss new enhancements and customer use cases that leverage AI with hybrid cloud deployment scenarios, and how this platform can help CAD managers and engineers reduce licensing overheads and seamlessly run complex EDA design flows through Synopsys Cloud.
Jul 8, 2024
44,217 views