Love the resident vs consultant analogy, makes it super clear. The part about neural nets figuring out features themselves is where things get wild compared to traditional ML that needs hand-engineered inputs. Would be cool to see how these models actually fail in practice when they run into edge cases docs would catch easily.
Love the resident vs consultant analogy, makes it super clear. The part about neural nets figuring out features themselves is where things get wild compared to traditional ML that needs hand-engineered inputs. Would be cool to see how these models actually fail in practice when they run into edge cases docs would catch easily.
Totally agree. Thanks for your comment. Will be unravelling these aspects soon