News for hackers. Stuff that matters.
Re:Why deep learning works even though it shouldn’t by tbenst on Wednesday October 21, 2020 @11:24PM (#24854596)
How about 80% accuracy on CIFAR-10 with unsupervised training?

=> logistic regression + Kmeans

http://ai.stanford.edu/~acoates/papers/coatesleeng_aistats_2...

There are no comments on this comment yet.