Re:Ask HN: Development/Engineering Epiphanies from your expe...
by alexmolas on Tuesday December 27, 2022 @09:57AM
(#34149191)
Deep learning is clever matrix multiplications with some clever loss functions.
When I first started learning theoretical deep learning I was afraid of it since it seemed so difficult. Then I realized that it's just doing matrix multiplication with some clever tricks to introduce inductive bias, and clever loss functions that teach you how to optimize the parameters of your matrices. And a lot of data.
When I first started learning theoretical deep learning I was afraid of it since it seemed so difficult. Then I realized that it's just doing matrix multiplication with some clever tricks to introduce inductive bias, and clever loss functions that teach you how to optimize the parameters of your matrices. And a lot of data.