BriefGPT.xyz
Jan, 2023
可编程计算机的环形变压器
Looped Transformers as Programmable Computers
HTML
PDF
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee...
TL;DR
本文提出了一种使用 transformer 网络作为通用计算机的框架,演示了一种将迭代算法映射为循环可执行程序的方法,并展示了注意力机制的多种用途。
Abstract
We present a framework for using
transformer networks
as
universal computers
by programming them with specific weights and placing them in a loop. Our input sequence acts as a punchcard, consisting of instruction
→