Beware of the man who won’t be bothered with details. — William Feather, Sr. Goal In this essay I want to shed some light on the details when dealing with large datasets (read: arrays), while working with Python and numerical code when datasets become increasingly large (or local memory being not enough or the overall computation being too slow using Python’s standard libraries). ...
Recently we have seen OpenAI, a company excessivly funded by Microsoft, trialing a Large Language Model (LLM) called chatGPT. Guess what? They are selling you, your own data. ...
In this article we have an illustrated annotated look at the Transformer published in “Attention is all you need” in 2017 by Vaswani, Shazeer, Parmer, et al. The Transformer architecture was groundbraking as it achieves 28.4 BLEU on the WMT 2014 English-to-German translation task with comparatively very little training. Even though it is eclipsed by the “Reformer: The Efficient Transformer” published by Nikita Kitaev, Łukasz Kaiser and Anselm Levskayain in this year/2020, it is still interesting to have a look at the fundamental idea of the comparatively “simple network architecture […] based solely on attention mechanisms”. ...
With voice assistants becoming ubiquitous we get used to things listening to us. In this article we explore how to get a headless RaspberryPi Zero W to be our offline voice assistant. ...
After reading up some nice stats on Google’s Coral Edge TPUs by Sam Sterckval at @RacoonsGroup, I got curious. Let’s see how this works. ...