model
This series covers a lot of fundamentals about the underlying BEAM VM and Erlang as consequence of covering Elixir fundamentals. A lot has been said about The A…
TLDR: the tricky part is “Large”. “Language” and “Model” seems manageable. But largeness has all sorts of trouble associated with it for mobile devices. Not ins…
What feels like forever ago but what was probably a year and a half I gave a talk about Lively LiveView with Membrane. Video is available for the curious. It wa…
(摘要暂无, 请查看原文)
(摘要暂无, 请查看原文)
(摘要暂无, 请查看原文)
CS231n notes on CNN training: normalization layers, dropout, activation functions, and architectures including AlexNet, VGG, and ResNet.
Natural Language Processing has undergone a massive evolution in recent years. To understand state-of-the-art models, we first need to look back at how we used …
GPUs Modern AI training is structured as a hierarchy: individual GP
With self-supervised learning, we can train neural networks without the need for manually labelled datasets.






