Everything in the Parilem archive, newest first.
Read · Compare · Go to the source
An assistant reading a company's own records is only as good as the pages it is handed. This study measures how a thirty-year-old word-matching method outran a neural one.
Teaching a neural network something new makes it erase what came before. This study shows that forgetting depends not only on the algorithm but on the order in which the tasks are shown.
Comparing quarantine and vaccination scenarios in an artificial town of a thousand gives a clear result: timing is as decisive as the type of intervention.
How a word spoken into a microphone becomes a sequence of numbers, and then a command. Speech recognition before deep learning is still worth understanding.
The method that reduces the link between shelf space and coffee sales to a single number is also the first step into machine learning.
