Machine Learning Street Talk (MLST)

Prof. Chris Bishop's NEW Deep Learning Textbook!

32 snips
Apr 10, 2024
Chris Bishop, Technical Fellow at Microsoft Research AI4Science and a leading figure in machine learning, discusses his newly co-authored textbook 'Deep Learning: Foundations and Concepts.' He delves into the evolution of deep learning, emphasizing the importance of a probabilistic approach. The conversation covers the nature of large models like GPT-4, AI's role in scientific discovery, and strategies for improving model training with geometric priors. Bishop also reflects on the paradox of deep learning effectiveness and the ethical considerations in AI development.
Ask episode
AI Snips
Chapters
Books
Transcript
Episode notes
ANECDOTE

Career Shift

  • Chris Bishop's career began in physics, inspired by AI in 2001: A Space Odyssey.
  • He transitioned to machine learning after encountering backpropagation, applying it to fusion data.
INSIGHT

Symbolic Reasoning in Neural Nets

  • Recent large language models like GPT-4 demonstrate symbolic reasoning capabilities.
  • This challenges prior beliefs about needing to combine connectionist and symbolic AI approaches.
INSIGHT

Book Motivations

  • Chris Bishop wrote Neural Networks for Pattern Recognition to learn the field.
  • PRML aimed to be a comprehensive textbook for the maturing field of machine learning.
Get the Snipd Podcast app to discover more snips from this episode
Get the app