Corpus ID: 212634211

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch

@article{Real2020AutoMLZeroEM,
  title={AutoML-Zero: Evolving Machine Learning Algorithms From Scratch},
  author={Esteban Real and Chen Liang and David R. So and Quoc V. Le},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.03384}
}
  • Esteban Real, Chen Liang, +1 author Quoc V. Le
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has also made significant progress. However, this progress has largely focused on the architecture of neural networks, where it has relied on sophisticated expert-designed layers as building blocks---or similarly restrictive search spaces. Our goal is to show that AutoML can go further: it is possible today to automatically discover… CONTINUE READING

    Citations

    Publications citing this paper.

    Evolving Normalization-Activation Layers

    VIEW 1 EXCERPT

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 104 REFERENCES

    Reading Digits in Natural Images with Unsupervised Feature Learning

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Rectified Linear Units Improve Restricted Boltzmann Machines

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Evolving Deep Convolutional Neural Networks for Image Classification

    ASAP: Architecture Search, Anneal and Prune

    VIEW 1 EXCERPT