Neural Architecture Search with Reinforcement Learning

    Barret Zoph
    Barret Zoph

    international conference on learning representations, 2017.

    Cited by: 1400|Bibtex|Views134|Links
    EI

    Abstract:

    Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with rein...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments