20.5 C-Transformer: A 2.6-18.1μJ/Token Homogeneous DNN-Transformer/Spiking-Transformer Processor with Big-Little Network and Implicit Weight Generation for Large Language Models.
Sangyeob KimSangjin KimWooyoung JoSoyeon KimSeongyon HongHoi-Jun YooPublished in: ISSCC (2024)
Keyphrases
- language model
- distribution network
- fuzzy logic
- fault diagnosis
- language modeling
- statistical language models
- speech recognition
- probabilistic model
- information retrieval
- document retrieval
- spiking neural networks
- retrieval model
- document ranking
- test collection
- context sensitive
- n gram
- co occurrence
- ad hoc information retrieval
- language model for information retrieval