François Chollet
Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Co-founder @arcprize. Opinions are my own.
View on 𝕏Threads
Intelligence is the efficiency with which you operationalize past information in order to deal with the future. You can interpret it as a conversion ratio, and this ratio can be f...
Unfortunately , too few people understand the distinction between memorization and understanding. It's not some lofty question like "does the system have an internal world model?",...
KerasNLP also emphasizes in-graph computation for all workflows so that developers can expect easy productionization using the tools of the TensorFlow ecosystem. Get started with...
So far all evidence that LLMs can perform few-shot reasoning on novel problems seems to boil down to "LLMs store patterns they can reapply to new inputs", i.e. it works for problem...
"I have solved X in a dependable and generalizable way, I won't need to go back to that problem and add random hacks to my solution to address things I didn't see coming" is pure b...
The really hard part here is the "future" bit. You're optimizing for an unknown objective -- the end goal is to be able to operate in the situations you'll face *next*, which aren'...
Q: What should I do if I already bought a counterfeit copy? A: Ask for a refund. Maybe this will put pressure on Amazon to look into the issue?
Compilation thread of various Keras tips ⬇️⬇️⬇️