Transformer (deep learning architecture)

For other uses, see Transformer (disambiguation).
Part of a series on
Machine learning
and data mining
Paradigms
Problems
Clustering
Dimensionality reduction
Structured prediction
Anomaly detection
Artificial neural network
Reinforcement learning
Learning with humans
Model diagnostics
Mathematical foundations
Journals and conferences
Related articles
A standard Transformer architecture, showing on the left an encoder, and on the right a decoder. Note: it uses the pre-LN convention, which is different from the post-LN convention used in the original 2017 Transformer.

A transformer is a deep learning architecture developed by researchers at Google and based on the multi-head attention mechanism, proposed in the 2017 paper "Attention Is All You Need".[1] Text is converted to numerical representations called tokens, and each token is converted into a vector via lookup from a word embedding table.[1] At each layer, each token is then contextualized within the scope of the context window with other (unmasked) tokens via a parallel multi-head attention mechanism, allowing the signal for key tokens to be amplified and less important tokens to be diminished.

Transformers have the advantage of having no recurrent units, therefore requiring less training time than earlier recurrent neural architectures (RNNs) such as long short-term memory (LSTM).[2] Later variations have been widely adopted for training large language models (LLM) on large (language) datasets, such as the Wikipedia corpus and Common Crawl.[3]

Transformers were first developed as an improvement over previous architectures for machine translation,[4][5] but have found many applications since. They are used in large-scale natural language processing, computer vision (vision transformers), reinforcement learning,[6][7] audio,[8] multimodal learning, robotics,[9] and even playing chess.[10] It has also led to the development of pre-trained systems, such as generative pre-trained transformers (GPTs)[11] and BERT[12] (bidirectional encoder representations from transformers).

  1. ^ a b Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N; Kaiser, Łukasz; Polosukhin, Illia (2017). "Attention is All you Need" (PDF). Advances in Neural Information Processing Systems. 30. Curran Associates, Inc.
  2. ^ Hochreiter, Sepp; Schmidhuber, Jürgen (1 November 1997). "Long Short-Term Memory". Neural Computation. 9 (8): 1735–1780. doi:10.1162/neco.1997.9.8.1735. ISSN 0899-7667. PMID 9377276. S2CID 1915014.
  3. ^ "Better Language Models and Their Implications". OpenAI. 2019-02-14. Archived from the original on 2020-12-19. Retrieved 2019-08-25.
  4. ^ Bahdanau; Cho, Kyunghyun; Bengio, Yoshua (September 1, 2014). "Neural Machine Translation by Jointly Learning to Align and Translate". arXiv:1409.0473 [cs.CL].
  5. ^ Luong, Minh-Thang; Pham, Hieu; Manning, Christopher D. (August 17, 2015). "Effective Approaches to Attention-based Neural Machine Translation". arXiv:1508.04025 [cs.CL].
  6. ^ Cite error: The named reference :10 was invoked but never defined (see the help page).
  7. ^ Parisotto, Emilio; Song, Francis; Rae, Jack; Pascanu, Razvan; Gulcehre, Caglar; Jayakumar, Siddhant; Jaderberg, Max; Kaufman, Raphaël Lopez; Clark, Aidan; Noury, Seb; Botvinick, Matthew; Heess, Nicolas; Hadsell, Raia (2020-11-21). "Stabilizing Transformers for Reinforcement Learning". Proceedings of the 37th International Conference on Machine Learning. PMLR: 7487–7498.
  8. ^ Radford, Alec; Jong Wook Kim; Xu, Tao; Brockman, Greg; McLeavey, Christine; Sutskever, Ilya (2022). "Robust Speech Recognition via Large-Scale Weak Supervision". arXiv:2212.04356 [eess.AS].
  9. ^ Monastirsky, Maxim; Azulay, Osher; Sintov, Avishai (February 2023). "Learning to Throw With a Handful of Samples Using Decision Transformers". IEEE Robotics and Automation Letters. 8 (2): 576–583. doi:10.1109/LRA.2022.3229266. ISSN 2377-3766.
  10. ^ Ruoss, Anian; Delétang, Grégoire; Medapati, Sourabh; Grau-Moya, Jordi; Wenliang, Li; Catt, Elliot; Reid, John; Genewein, Tim (2024-02-07). "Grandmaster-Level Chess Without Search". arXiv:2402.04494v1 [cs.LG].
  11. ^ Wolf, Thomas; Debut, Lysandre; Sanh, Victor; Chaumond, Julien; Delangue, Clement; Moi, Anthony; Cistac, Pierric; Rault, Tim; Louf, Remi; Funtowicz, Morgan; Davison, Joe; Shleifer, Sam; von Platen, Patrick; Ma, Clara; Jernite, Yacine; Plu, Julien; Xu, Canwen; Le Scao, Teven; Gugger, Sylvain; Drame, Mariama; Lhoest, Quentin; Rush, Alexander (2020). "Transformers: State-of-the-Art Natural Language Processing". Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pp. 38–45. doi:10.18653/v1/2020.emnlp-demos.6. S2CID 208117506.
  12. ^ "Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing". Google AI Blog. 2 November 2018. Archived from the original on 2021-01-13. Retrieved 2019-08-25.