The fall of RNN / LSTM
It is the year 2014 and LSTM and RNN make a great come-back from the dead. We all read Colah’s blog and Karpathy’s ode to RNN. But we were all young and unexperienced.
For a few years this was the way to solve sequence learning, sequence translation (seq2seq), which also resulted in amazing results in speech to text comprehension and the raise of Siri, Cortana, Google voice assistant, Alexa. Also let us not forget machine translation, which resulted in the ability to translate documents into different languages or neural machine translation, but also translate images into text, text into images, and captioning video, and… well you got the idea. Then in the following years (2015–16) came ResNet and Attention.
One could then better understand that LSTM were a clever bypass technique. Also attention showed that MLP network could be replaced by averaging networks influenced by a context vector. But do not take our words for it, also see evidence that Attention based networks are used more and more by Google, Facebook, Salesforce, to name a few.
All these companies have replaced RNN and variants for attention based models, and it is just the beginning. RNN have the days counted in all applications, because they require more resources to train and run than attention-based models. See this post for more info.