Karl Higley
karlhigley
Counter-intuitively, if your recommender is trained on data collected from past interactions with recs, retraining new models regularly doesn’t resolve the issue of performance decaying over time and can actually
Read more
“Why Are Deep Learning Models Not Consistently Winning Recommender Systems Competitions Yet?“https://dl.acm.org/doi/abs/10.1145/3415959.3416001My take is that we haven’t had the right model architectures. Here’s why I think that...
Read more
So...lots on the value of soft skills today. It’s true: they are super-important!Bad news on the “just learn lol” front: there are lots of autistic people in tech and we
Read more