mixture of experts model
transformer-based model using a Mixture-of-Experts design, where only a subset of feed-forward ‘expert’ modules are activated per token
Press Enter · cited answer in seconds
0 sources
mixture of experts model
Summary
Key Facts
- mixture of experts model is credited with the discovery of Robert A. Jacobs[1].
- mixture of experts model is credited with the discovery of Michael I. Jordan[2].
- mixture of experts model is credited with the discovery of Steven J. Nowlan[3].
- mixture of experts model is credited with the discovery of Geoffrey Hinton[4].
- mixture of experts model's subclass of is recorded as transformer[5].
- mixture of experts model's subclass of is recorded as large language model[6].
- mixture of experts model's facet of is recorded as machine learning[7].
- mixture of experts model's facet of is recorded as ensemble learning[8].
- mixture of experts model's uses is recorded as mixture of experts[9].
- mixture of experts model's Google Knowledge Graph ID is recorded as /g/11dzt5tj98[10].
- mixture of experts model's Microsoft Academic ID is recorded as 2778025020[11].
Body
Works and Contributions
Credited discoveries include Robert A. Jacobs[1], a cognitive scientist[12]; Michael I. Jordan[2], a computer scientist[13], b. 1956[14], of United States[15], awarded the Rumelhart Prize[16], specialised in artificial intelligence[17]; Steven J. Nowlan[3], a computer scientist[18]; and Geoffrey Hinton[4], a computer scientist[19], b. 1947[20], of United Kingdom[21], awarded the Fellow of the Royal Society[22], specialised in deep learning[23].