[HN Gopher] Explaining RNNs without neural networks ___________________________________________________________________ Explaining RNNs without neural networks Author : parrt Score : 45 points Date : 2020-07-10 19:00 UTC (4 hours ago) (HTM) web link (explained.ai) (TXT) w3m dump (explained.ai) | parrt wrote: | Vanilla recurrent neural networks (RNNs) form the basis of more | sophisticated models, such as LSTMs and GRUs. There are lots of | great articles, books, and videos that describe the | functionality, mathematics, and behavior of RNNs so, don't worry, | this isn't yet another rehash. (See below for a list of | resources.) My goal is to present an explanation that avoids the | neural network metaphor, stripping it down to its essence--a | series of vector transformations that result in embeddings for | variable-length input vectors. ___________________________________________________________________ (page generated 2020-07-10 23:00 UTC)