Corpus ID: 53065904

Symbolic Reasoning with Differentiable Neural Comput

@inproceedings{Graves2016SymbolicRW,
  title={Symbolic Reasoning with Differentiable Neural Comput},
  author={A. Graves and Greg Wayne and M. Reynolds and T. Harley and Ivo Danihelka and Grabska-Barwińska and S. G{\'o}mez and Edward Grefenstette and Tiago Ramalho and J. Agapiou and Adri{\`a} and P. Badia and K. Hermann and Yori Zwols and Georg Ostrovski and A. Cain and C. Summerfield and P. Blunsom and K. Kavukcuoglu and Demis Hassabis},
  year={2016}
}
  • A. Graves, Greg Wayne, +17 authors Demis Hassabis
  • Published 2016
  • Recent breakthroughs demonstrate that neural networks are remarkably adept at sensory 8 processing1 and sequence2, 3 and reinforcement learning4. However, cognitive scientists and 9 neuroscientists have argued that neural networks are limited in their ability to define vari10 ables and data structures5–9, store data over long time scales without interference10, 11, and 11 manipulate it to solve tasks. Conventional computers, on the other hand, can easily be pro12 grammed to store and process… CONTINUE READING

    References

    SHOWING 1-10 OF 15 REFERENCES
    Learning to Execute
    • 387
    • PDF
    Long Short-Term Memory
    • 32,848
    • Highly Influential
    • PDF
    Speech recognition with deep recurrent neural networks
    • 5,371
    • PDF
    End-To-End Memory Networks
    • 1,564
    • PDF
    Large Scale Distributed Deep Networks
    • 2,430
    • PDF
    Real-time reinforcement learning by sequential Actor-Critics and experience replay
    • 79
    • PDF
    Search-based structured prediction
    • 509
    • PDF