Explained | What is a transformer, the ML model that powers ChatGPT?

Machine learning, a subfield of artificial intelligence, teaches computers to solve tasks based on structured data, language, audio, or images, by providing examples of inputs and the desired outputs. ‘Attention Is All You Need’ In a pioneering paper entitled ‘Attention Is All You Need’ that appeared in 2017, a team at Google proposed transformers – a DNN architecture that has today gained popularity across all modalities: image, audio, and language. Transformers’ ability to ingest anything has been exploited to create joint vision-and-language models that allow users to search for an image, describe one, and even answer questions regarding the image. Instead, by training on several image-caption pairs with the word “bird”, it discovers common patterns in the image to associate the flying thing with “bird”. They feature several attention layers both within the encoder, to provide meaningful context across the input sentence or image, and from the decoder to the encoder when generating a translated sentence or describing an image.