#232 Sepp Hochreiter: How LSTMs Power Modern AI System's
Eye On A.I.22 Jan 2025

#232 Sepp Hochreiter: How LSTMs Power Modern AI System's

In this special episode of the Eye on AI podcast, Sepp Hochreiter, the inventor of Long Short-Term Memory (LSTM) networks, joins Craig Smith to discuss the profound impact of LSTMs on artificial intelligence, from language models to real-time robotics.

Sepp reflects on the early days of LSTM development, sharing insights into his collaboration with Jürgen Schmidhuber and the challenges they faced in gaining recognition for their groundbreaking work.

He explains how LSTMs became the foundation for technologies used by giants like Amazon, Apple, and Google, and how they paved the way for modern advancements like transformers. Topics include:

- The origin story of LSTMs and their unique architecture.
- Why LSTMs were crucial for sequence data like speech and text.
- The rise of transformers and how they compare to LSTMs.
- Real-time robotics: using LSTMs to build energy-efficient, autonomous systems.

The next big challenges for AI and robotics in the era of generative AI. Sepp also shares his optimistic vision for the future of AI, emphasizing the importance of efficient, scalable models and their potential to revolutionize industries from healthcare to autonomous vehicles.

Don't miss this deep dive into the history and future of AI, featuring one of its most influential pioneers.

(00:00) Introduction: Meet Sepp Hochreiter
(01:10) The Origins of LSTMs
(02:26) Understanding the Vanishing Gradient Problem
(05:12) Memory Cells and LSTM Architecture
(06:35) Early Applications of LSTMs in Technology
(09:38) How Transformers Differ from LSTMs
(13:38) Exploring XLSTM for Industrial Applications
(15:17) AI for Robotics and Real-Time Systems
(18:55) Expanding LSTM Memory with Hopfield Networks
(21:18) The Road to XLSTM Development
(23:17) Industrial Use Cases of XLSTM
(27:49) AI in Simulation: A New Frontier
(32:26) The Future of LSTMs and Scalability
(35:48) Inference Efficiency and Potential Applications
(39:53) Continuous Learning and Adaptability in AI
(42:59) Training Robots with XLSTM Technology
(44:47) NXAI: Advancing AI in Industry

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(376)

In 5 to 10 Years, Using Weapons Without AI Will Be Considered Unethical | Yaroslav Azhnyuk, The Fourth Law

In 5 to 10 Years, Using Weapons Without AI Will Be Considered Unethical | Yaroslav Azhnyuk, The Fourth Law

A Ukrainian entrepreneur who spent 14 years building cameras for pets pivoted to building cameras that down Shaheds, and is now building the autonomy software that could define how wars are fought for...

31 Aug 53min

Inside Ukraine's Azov Drone R&D: The Engineer Building AI Weapons 18 km From the Front Line | Alexander Palamarchuk

Inside Ukraine's Azov Drone R&D: The Engineer Building AI Weapons 18 km From the Front Line | Alexander Palamarchuk

The most consequential arms race in the world right now isn't nuclear, it's software. Craig Smith speaks with Alexander Palamarchuk, an engineer in the R&D department of Ukraine's Azov Brigade, callin...

27 Aug 41min

95% of AI Agent Projects Fail to Reach Production. Here's Why | Manoj Saxena, TrustWise

95% of AI Agent Projects Fail to Reach Production. Here's Why | Manoj Saxena, TrustWise

It takes a few hours to build an AI agent. It takes six to seven months to get it into production. Manoj Saxena - the executive who commercialized IBM Watson - built TrustWise around one thesis: intel...

24 Aug 1h 1min

From Zero to 150 Robots in Just 20 Months | Mike LeBlanc, Foundation Future Industries

From Zero to 150 Robots in Just 20 Months | Mike LeBlanc, Foundation Future Industries

Most humanoid robot companies are still running curated demos in replica environments. Foundation Future Industries is running 150 robots on real automotive production lines in Georgia, and heading to...

19 Aug 1h 6min

Why People Are Paying 10x More for AI - and What That Means for the Chip Market | Sid Sheth, d-Matrix

Why People Are Paying 10x More for AI - and What That Means for the Chip Market | Sid Sheth, d-Matrix

The AI chip market looks monolithic from the outside - NVIDIA dominates, and everyone else is fighting for scraps. But d-Matrix's CEO Sid Sheth argues that the market is quietly splitting into two dis...

17 Aug 50min

American Companies Have 36 Months to Go AI-Native or Get Left Behind | Drew Cukor, TWG AI

American Companies Have 36 Months to Go AI-Native or Get Left Behind | Drew Cukor, TWG AI

The same tools that slowed the U.S. military down in Afghanistan (PowerPoint, Excel, email, and Word) are now slowing American businesses down in the AI race. Drew Cukor spent 30 years as a Marine int...

13 Aug 58min

In 5 Years, 90% of What You Use AI For Will Run on Your Smartphone | Paolo Ardoino, Tether

In 5 Years, 90% of What You Use AI For Will Run on Your Smartphone | Paolo Ardoino, Tether

Hundreds of billions of dollars are flowing into AI data centers right now, and Paolo Ardoino, CEO of Tether - the company behind the world's most widely used stablecoin with 573 million users - think...

10 Aug 58min

AI Agents Fixing Your IT Before You Even Know Something Broke | Erhan Giral & Ryan Manning, BMC Helix

AI Agents Fixing Your IT Before You Even Know Something Broke | Erhan Giral & Ryan Manning, BMC Helix

Most enterprise IT teams spend the majority of their time fighting the same fires repeatedly. BMC Helix is building the AI system that handles those fires automatically, detecting anomalies, tracing r...

3 Aug 59min

Populärt inom Teknik

uppgang-och-fall
market-makers
rss-elektrikerpodden
skogsforum-podcast
rss-laddstationen-med-elbilen-i-sverige
natets-morka-sida
rss-technokratin
elbilsveckan
rss-en-ai-till-kaffet
 och-bilen-gar-bra
rss-veckans-ai
klocksnack-tillsammans-med-nymans-ur-1851
bilar-med-sladd
hej-bruksbil
bli-saker-podden
prova-programmering-av-distansakademin
rss-fabriken-2
rss-uppgang-och-fall
kodsnack
gubbar-som-tjotar-om-bilar