Will transformers replace Recurrent Neural Networks and Convolutional Neural Networks?

I am in the process of studying Tensorflow, which is Python’s library that creates neural networks. So far, I have studied artificial neural networks (ANN), deep neural networks (DNN), convolutional neural networks (CNN), and recurrent neural networks (RNN). I am currently studying a course on Tensorflow that covers version 2 of the library.

Tensorflow version 2 is a library that provides a comprehensive ecosystem of tools for developers, researchers, and organisations who want to build scalable Machine Learning and Deep Learning applications. At the time of this writing, the most current version of Tensorflow is version 2.12.

I am on module 9 of the Tensorflow course that I am studying, and so far, there has been no mention of any transformers, so I believe that particular course is pre-transformers (most probably the reason why it is free on the Alison website). From what I have studied, computer vision uses CNN’s and natural language processing uses RNN’s.

What are transformers?

A transformer is a deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input (which includes the recursive output) data. It is used primarily in the fields of natural…