AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
#82 - Dr. JOSCHA BACH - Digital Physics, DL and Consciousness [UNPLUGGED]
Machine Learning Street Talk (MLST)
The Language of Thought Hypothesis
Delhi 2 combines the language model and division model using embedding spaces. These embedding spaces basically project all the concepts into some high dimensional manifold. It's much easier to go the other way around, would you agree? The issues that language of thought is executable. So our language of thought can execute stuff. And it's not just a machine neural network that guesses what the outcome is going to be but gets pretty good at figuring this out. But there are probably ways in which we could make this happen much more elegantly and quickly - for instance, on models for arithmetic.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode