Someone should write the equivalent of TAOCP for machine learning.
(Ok, maybe not literally the equivalent. I mean Knuth is... Knuth. So it doesn't seem realistic to expect someone to do something as impressive as TAOCP. And yes, this is authority worship and I don't care. He's Knuth goddamn it.)
Specifically, a book where the theory/math's rigorous but the algorithms are described in their efficient forms. I haven't found this in the few ML books I've read parts of (Bishop's Pattern Recognition and Machine Learning, MacKay's Information Theory, and Tibrishani et Al's Elements of Statistical Learning), so if it's already out there, let me know.
Note that I don't mean that whoever does this should do the whole MMIX thing and write their own language and VM.
In light of reading Hazard's Shortform Feed -- which I really enjoy -- based on Raemon's Shortform feed, I'm making my own. There be thoughts here. Hopefully, this will also get me posting more.