2 Matching Annotations
  1. Apr 2023
  2. arxiv.org arxiv.org
    [PDF] What Can Transformers Learn In-Context? A Case Study of Simple Function Classes | Semantic Scholar
    2
    1. mshook 01 Apr 2023
      We use a decoder-only Transformer architecture [Vaswani et al., 2017] from the GPT-2family
      gpt2 gpt transformer
    2. mshook 01 Apr 2023
      a random function f

      a random function not many or several

      icl transformer gpt2 gpt function
    Visit annotations in context

    Tags

    Annotators

    URL

    arxiv.org/pdf/2208.01066.pdf