← neural networks
What podcasts say about neural networks
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about neural networks
5 statements · 4 positive · 1 neutral
Artificial networks require constraints to balance goal pursuit and exploration.
“You have to balance that and sometimes you have to impose constraints to make that happen in an artificial network.”
Open the episode · How Dopamine & Serotonin Shape Decisions, Motivation & Learning | Dr. Read MontagueListen at 47:19
Large neural networks trained on complex problems exhibit surprising emergent behaviors.
“you definitely do get very surprising emergent behaviors out of these neural nets when they're large enough and trained on complicated enough problems”
Open the episode · #333 – Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGIListen at 7:04
Neural networks can be made to reason.
“Yes.”
Open the episode · #333 – Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGIListen at 2:48:58
Current neural networks can generalize beyond explicit examples in their training data.
“You're able to remix the training set information into true generalization in some sense that doesn't appear.”
Open the episode · #333 – Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGIListen at 2:49:29
Neural networks already perform reasoning through information processing and generalization.
“I think the neural nets already do that today.”
Open the episode · #333 – Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGIListen at 2:49:59
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.