Machine Learning Street Talk (MLST) avatar

Dexa/Machine Learning Street Talk (MLST)

Learn more

Generalization and Processing

Mohamed discusses how models can generalize during training and processing at test time, emphasizing the importance of system one and system two processing in understanding model behavior. He highlights the nature of perceptual tasks and the intriguing process of going from scratch to generalization, shedding light on optimizing for more effective generalization strategies.
  • In this clip

  • From this podcast

    Machine Learning Street Talk (MLST) avatar

    Machine Learning Street Talk (MLST)

    New 50% ARC result and current winners interviewed

  • Related Questions

    • How effective are current models in machine learning, as discussed in the episode "Long Context Language Models and their Biological Applications with Eric Nguyen - 690" and the clip "Generalizability in AI"?

    • Will large language models scale all the way to artificial general intelligence (AGI) as discussed in the episode Gary Marcus' keynote at AGI-24 and the clip Generalization Challenges? Additionally, what are the insights from the episode MEGATHREAT: The Dangers Of AI Are WEIRDER Than You Think! | Yoshua Bengio and the clip Neural Networks Explained?

    • Will large language models scale all the way to artificial general intelligence (AGI) as discussed in Gary Marcus' keynote at AGI-24 and the clip Generalization Challenges? Additionally, what are the insights from the episode MEGATHREAT: The Dangers Of AI Are WEIRDER Than You Think! | Yoshua Bengio and the clip Neural Networks Explained?

Built by
Charlie AI
© 2024 Machine Learning Street Talk (MLST)TermsPrivacySupport