MLG 009 Deep Learning

The 2025 generative AI image market is a trade-off between aesthetic quality, instruction-following, and user control. This episode analyzes the key platforms, comparing Midjourney's artistic output against the superior text generation and prompt adherence of GPT-4o and Imagen 4, ... Show More

Auto encoders are neural networks that compress data into a smaller "code," enabling dimensionality reduction, data cleaning, and lossy compression by reconstructing original inputs from this code. Advanced auto encoder types, such as denoising, sparse, and variational auto encod ... Show More

At inference, large language models use in-context learning with zero-, one-, or few-shot examples to perform new tasks without weight updates, and can be grounded with Retrieval Augmented Generation (RAG) by embedding documents into vector databases for real-time factual lookup ... Show More

It seems like every day there's more and more machine learning problems that involve learning on text data, but text itself makes for fairly lousy inputs to machine learning algorithms.  That's why there are text vectorization algorithms, which re-format text data so it's ready f ... Show More

Bryan Catanzaro, vice president for applied deep learning research at NVIDIA, talks about how we know an AI technology is working, the potential for AI-powered speech, and where we’ll see the next deep learning breakthroughs. 

In this episode I make a non exhaustive list of machine learning tools and frameworks, written in Rust. Not all of them are mature enough for production environments. I believe that community effort can change this very quickly. To make a comparison with the Python ecosystem I wi ... Show More

Go to www.brilliant.org/breakingmathpodcast to learn neural networks, everyday physics, computer science fundamentals, the joy of problem solving, and many related topics in science, technology, engineering, and math.  Mathematics takes inspiration from all forms with which life ... Show More

When we think about machine learning today we often think in terms of immense scale — large language models that require huge amounts of computational power, for example. But one of the most interesting innovations in machine learning right now is actually happening on a really s ... Show More

In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the term Automated Machine Learning (AutoML), explain how this term relate to AI and why it’s important to know about them. Show Notes: FREE Intro to CPMAI mini course CPMAI Training and Certifi ... Show More

While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics," says AI professor Anima Anandkumar. She explains how her team developed neural operators — AI trained on the finest details of the real worl ... Show More

Catherine Nelson, author of the new O’Reilly book, Software Engineering for Data Scientists, discusses the collaboration between data scientists and software engineers -- an increasingly common pairing on machine learning and AI projects. Host Philip Winston speaks with Nelson ab ... Show More

What if AI could think and adapt like a real brain? TED Fellow and AI scientist Ramin Hasani shares how liquid neural networks — a new, more flexible AI technology inspired by physics and living brains — could transform how we solve complex problems. Hosted on Acast. See acast.co ... Show More

“While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics,” says AI professor Anima Anandkumar. She explains how her team developed neural operators — AI trained on the finest details of the real wor ... Show More