21min chapter

Machine Learning Street Talk (MLST) cover image

Want to Understand Neural Networks? Think Elastic Origami! - Prof. Randall Balestriero

Machine Learning Street Talk (MLST)

CHAPTER

Geometric Insights into Neural Network Robustness

This chapter explores the structural similarities between neural networks and geometric forms, emphasizing how these connections enhance decision-making processes. It discusses advanced concepts like grokking and adversarial robustness, revealing how prolonged training can lead to significant improvements in network performance and stability. Additionally, the narrative addresses innovative approaches to regularization and pruning, advocating for a geometric perspective to optimize neural network training and combat adversarial challenges.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode