London Futurists cover image

Don't try to make AI safe; instead, make safe AI, with Stuart Russell

London Futurists

00:00

Overcoming Challenges in Training Neural Networks and Debating General Intelligence

This chapter explores the challenges faced in training neural networks with multiple layers and discusses how stochastic gradient descent, relu units, resnets, and GPU scaling played a vital role in overcoming these challenges. The debate on whether current methods are sufficient for creating general intelligence and the mention of advancements outlined in 'Human compatible' and a textbook are also covered.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app