logo
episode-header-image
Apr 2023
35m 32s

The Power of Graph Neural Networks: Unde...

FRANCESCO GADALETA
About this episode
In this episode of our podcast, we dive deep into the fascinating world of Graph Neural Networks. First, we explore Hierarchical Networks, which allow for the efficient representation and analysis of complex graph structures by breaking them down into smaller, more manageable components. Next, we turn our attention to Generative Graph Models, which enable th ... Show More
Up next
Yesterday
There Is No AI. There's a Stateless Function on 10,000 GPUs Pretending to Know You (Ep. 299)
Right now, millions of people are simultaneously chatting with a system that remembers nothing, knows nothing, and resets after every message. The engineering keeping that illusion alive is actually the impressive part. ✨ Connect with us! Personal newsletter: https://defragzone.s ... Show More
39m 29s
Jan 30
Your Favorite AI Startup is Probably Bullshit (Ep. 298) [RB]
The brutal truth about why Silicon Valley is blowing billions on glorified autocomplete while pretending it's the next iPhone. We're diving deep into the AI investment circus where VCs who can't code are funding companies that barely understand their own technology. From blockcha ... Show More
12m 20s
Jan 28
Why AI Researchers Are Suddenly Obsessed With Whirlpools (Ep. 297) [RB]
VortexNet uses actual whirlpools to build neural networks. Seriously. By borrowing equations from fluid dynamics, this new architecture might solve deep learning's toughest problems—from vanishing gradients to long-range dependencies. Today we explain how vortex shedding, the Str ... Show More
33m 15s
Recommended Episodes
Aug 2023
Why Deep Networks and Brains Learn Similar Features with Sophia Sanborn - #644
Today we’re joined by Sophia Sanborn, a postdoctoral scholar at the University of California, Santa Barbara. In our conversation with Sophia, we explore the concept of universality between neural representations and deep neural networks, and how these principles of efficiency pro ... Show More
45m 15s
Jan 2015
Easily Fooling Deep Neural Networks
tail spinning
28m 25s
Apr 2024
Physics-Informed Neural Networks (PINNs) - Conor Daly | Podcast #120
💻 Full tutorial: • Physics-Informed Neural Networks (PIN... Physics-Informed Neural Networks (PINNs) integrate known physical laws into neural network learning, particularly for solving differential equations. They embed these laws into the network's loss function, guiding the l ... Show More
1h 5m
Aug 2017
[MINI] Recurrent Neural Networks
<p class="p1"><span class="s1">RNNs are a class of deep learning models designed to capture sequential behavior.<span class= "Apple-converted-space"> </span> An RNN trains a set of weights which depend not just on new input but also on the previous state of the neural network.<sp ... Show More
17m 6s
Dec 2023
SE Radio 594: Sean Moriarity on Deep Learning with Elixir and Axon
<p><strong>Sean Moriarity</strong>, creator of the Axon deep learning framework, co-creator of the Nx library, and author of <em>Machine Learning in Elixir</em> and <em>Genetic Algorithms in Elixir,</em> published by the Pragmatic Bookshelf, speaks with SE Radio host <a href= "ht ... Show More
57m 43s
Oct 2017
The Complexity of Learning Neural Networks
Over the past several years, we have seen many success stories in machine learning brought about by deep learning techniques. While the practical success of deep learning has been phenomenal, the formal guarantees have been lacking. Our current theoretical understanding of the ma ... Show More
38m 51s
Feb 2021
How Doc.ai is Accelerating Better Health Outcomes through Neural Nets and A.I.
<p>The best products and solutions are often born out of personal experiences. For <a href="https://www.linkedin.com/in/sam-de-brouwer-b0a34122/">Sam De Brouwer,</a> CEO and Co-Founder of <a href="https://doc.ai/">doc.ai,</a> her breakthrough moment occurred after her son was hos ... Show More
40m 36s
Feb 2020
Qu’est-ce que le Deep Learning ?
Le deep learning ou l’apprentissage profond est un type d'intelligence artificielle dérivé du machine learning qui signifie lui apprentissage automatique. Ici, la machine est capable d'apprendre par elle-même, contrairement à la programmation où elle se contente d'exécuter à la l ... Show More
5m 4s
Aug 2020
Introduction to GraphQL
<p>Tanmai Gopal (@tanmaigo, CEO Hasura) and Rajoshi Ghosh (@rajoshighosh, COO Hasura) talk about the evolution of GraphQL as an efficient way to engage with APIs and data models, and how Hasura Cloud helps simplify GraphQL for developers.</p><p><b>SHOW: </b>462<br/><br/><b>SHOW S ... Show More
40m 40s