Lie access neural Turing machine

Greg Yang

Machine Learning mathscidoc:1912.43158

arXiv preprint arXiv:1602.08671, 2016.2
Following the recent trend in explicit neural memory structures, we present a new design of an external memory, wherein memories are stored in an Euclidean key space \mathbb R^ n . An LSTM controller performs read and write via specialized read and write heads. It can move a head by either providing a new address in the key space (aka random access) or moving from its previous position via a Lie group action (aka Lie access). In this way, the" L" and" R" instructions of a traditional Turing Machine are generalized to arbitrary elements of a fixed Lie group action. For this reason, we name this new model the Lie Access Neural Turing Machine, or LANTM.
No keywords uploaded!
[ Download ] [ 2019-12-21 11:26:33 uploaded by Greg_Yang ] [ 742 downloads ] [ 0 comments ]
@inproceedings{greg2016lie,
  title={Lie access neural Turing machine},
  author={Greg Yang},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221112633964564718},
  booktitle={arXiv preprint arXiv:1602.08671},
  year={2016},
}
Greg Yang. Lie access neural Turing machine. 2016. In arXiv preprint arXiv:1602.08671. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221112633964564718.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved