transformer
Machine-learning model architecture first developed by Google Brain.
- Developer
- Google Brain, Ashish Vaswani, Noam Shazeer
- Follows
- recurrent neural network, long short-term memory
- Type of
- artificial neural network, deep learning model
- Instance of
- software architecture
Connected
Linked from
- bidirectional encoder representations from transformersdeep learning artificial neural network language model
- GPT-1original pretrained GPT language model released by OpenAI in 2018
- DeepSeek-R1large language model
- Llama 3.3 70B Instructtransformer large language model by Meta
- Llama 3.2 1Blarge language model by Meta
- Fluxsuite of text-to-image models
More concepts & methods
- supervised learningmachine learning task of learning a function that maps an input to an output based on example input-output pairs
- reinforcement learningtype of machine learning where an agent learns how to behave in an environment by performing actions and receiving rewards or penalties in return, aiming to maximize the cumulative reward over time
- linear regressionstatistical approach for modeling the relationship between a scalar dependent variable and one or more explanatory variables
- unsupervised learningmachine learning technique
- pattern recognitionbranch of machine learning
- generative adversarial networkdeep learning method in which two neural networks compete with each other in a game, learning to generate new data with the same statistics as the training set
Sources
- Wikidata Q85810444 (structured facts, CC0)
- Wikipedia