Deconstructing Yourself cover image

Meditation and the Bayesian Brain with Shamil Chandaria

Deconstructing Yourself

CHAPTER

Neural Networks and Child Development

In the case of child development, these models are not just purely learning randomly. There's probably stages of development that will happen but these layers get learned sequentially which allows them to be learned in a more systematic way. Now how does this fit together with neural network type models? Right, so you know it's interesting because in artificial neural networks have to do the same Bayesian inference problem. They take data and in the early parts of the network, they extract the low level features and then later on the network, the midlevel features and then finally right at the top you get faces. This is Jack, this is Jill right at thetop. That stuff is pretty much hardwired,

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