申请试用
HOT
登录
注册
 
Neural Random-Access Machines

Neural Random-Access Machines

Reboot
/
发布于
/
1898
人观看
In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure input-output examples using backpropagation. We evaluate the new model on a number of simple algorithmic tasks whose solutions require pointer manipulation and dereferencing. Our results show that the proposed model can learn to solve algorithmic tasks of such type and is capable of operating on simple data structures like linked-lists and binary trees. For easier tasks, the learned solutions generalize to sequences of arbitrary length. Moreover, memory access during inference can be done in a constant time under some assumptions.
3点赞
1收藏
0下载
相关推荐
确认
3秒后跳转登录页面
去登陆