News for hackers. Stuff that matters.
Re:How I trained an AI to detect satire in under an hour by latenightcoding on Friday April 20, 2018 @04:28PM (#16888220)
This is a thinly veiled "machinebox" ad. Thanks for teaching us how to overfit in under an hour OP.
Re:How I trained an AI to detect satire in under an hour by minimaxir on Friday April 20, 2018 @04:43PM (#16888313)
I suspect the OP cheated by only training on 1 epoch; otherwise, the overfit would become obvious as the validation accuracy craters.