This could have easily been 3-4 landmark papers, but instead its packed into one cogent idea.
That common interview question about query autocomplete/sentence completion? Shannon solved it and demonstrates it in this paper, almost a decade before FORTRAN existed. New grads still struggle with that problem. PhD's still struggle with that problem.
Pretty much every machine learning classifier is using a loss function described in that paper.
That common interview question about query autocomplete/sentence completion? Shannon solved it and demonstrates it in this paper, almost a decade before FORTRAN existed. New grads still struggle with that problem. PhD's still struggle with that problem.
Pretty much every machine learning classifier is using a loss function described in that paper.