Corpus ID: 2982122

Learning Simple Algorithms from Examples

@inproceedings{Zaremba2016LearningSA,
  title={Learning Simple Algorithms from Examples},
  author={Wojciech Zaremba and Tomas Mikolov and Armand Joulin and R. Fergus},
  booktitle={ICML},
  year={2016}
}
We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set of interfaces, accessed by a controller. Typical interfaces are 1-D tapes or 2-D grids that hold the input and output data. For the controller, we explore a range of neural network-based models which vary in their ability to abstract the underlying algorithm from training instances and generalize to test examples with… Expand
Towards Modular Algorithm Induction
Learning Numeracy: Binary Arithmetic with Neural Turing Machines
Sequential Coordination of Deep Models for Learning Visual Arithmetic
Common-Description Learning: A Framework for Learning Algorithms and Generating Subproblems from Few Examples
Learning Efficient Algorithms with Hierarchical Attentive Memory
Strong Generalization and Efficiency in Neural Programs
Making Neural Programming Architectures Generalize via Recursion
DeepCoder: Learning to Write Programs
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 32 REFERENCES
Reinforcement Learning Neural Turing Machines - Revised
Learning to Transduce with Unbounded Memory
End-To-End Memory Networks
Neural Turing Machines
Weakly Supervised Memory Networks
...
1
2
3
4
...