Two years later, deep learning is still faced with the same basic challenges (garymarcus.substack.com)

Screenshot of garymarcus.substack.com: Two years later, deep learning is still faced with the same basic challenges

First screen, captured 2 years ago.

Looks similar

Screenshot of lesswrong.com: Douglas Hofstadter changes his mind on Deep Learning and AI risk

Douglas Hofstadter changes his mind on Deep Learning and AI risk (lesswrong.com)

216 points by kfarr 3 years ago | 305 comments

Screenshot of people.idsia.ch: Who invented deep residual learning?

Who invented deep residual learning?(people.idsia.ch)

103 points by timlod 1 year ago | 34 comments

Screenshot of rachel.fast.ai: Deep learning gets the glory, deep fact checking gets ignored

Deep learning gets the glory, deep fact checking gets ignored (rachel.fast.ai)

549 points by chmaynard 1 year ago | 134 comments

Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.

deep-learning enzyme-function-prediction transformers scientific-errors

Screenshot of karpathy.github.io: Deep Neural Nets: 33 years ago and 33 years from now (2022)

Deep Neural Nets: 33 years ago and 33 years from now (2022)(karpathy.github.io)

248 points by gsky 3 years ago | 84 comments

Screenshot of hazyresearch.stanford.edu: From deep to long learning?

From deep to long learning?(hazyresearch.stanford.edu)

451 points by headalgorithm 3 years ago | 98 comments

Stanford Hazy Research blog post by Dan Fu, Michael Poli, and Chris Ré on their lab's work increasing sequence length in deep learning models.

long-context sequence-models state-space-models hyena

Screenshot of horace.io: Making deep learning go brrrr from first principles (2022)

Making deep learning go brrrr from first principles (2022)(horace.io)

81 points by jpdus 3 years ago | 18 comments