Machine Learning Street Talk (MLST) cover image

Prof. Chris Bishop's NEW Deep Learning Textbook!

Machine Learning Street Talk (MLST)

NOTE

Staying Focused on Neural Networks and the Power of Problem Theory

With the benefit of hindsight, focusing on neural networks early on would have been profitable as it has proven to be valuable technology. The speaker highlights the unifying idea of problem theory, giving an example of how two different technologies, hidden Markov models and common filters, are essentially the same algorithm derived from simple mathematical principles of probability and factorization. By understanding problem theory deeply, one can derive complex models like common filters and hidden Markov models effortlessly, making concepts like message passing algorithms and tree structures clear and elegant.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner