Corpus ID: 208138361

ImmuNeCS: Neural Committee Search by an Artificial Immune System

@article{Frachon2019ImmuNeCSNC,
  title={ImmuNeCS: Neural Committee Search by an Artificial Immune System},
  author={Luc Frachon and Wei Pang and G. Coghill},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.07729}
}
  • Luc Frachon, Wei Pang, G. Coghill
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Current Neural Architecture Search techniques can suffer from a few shortcomings, including high computational cost, excessive bias from the search space, conceptual complexity or uncertain empirical benefits over random search. In this paper, we present ImmuNeCS, an attempt at addressing these issues with a method that offers a simple, flexible, and efficient way of building deep learning models automatically, and we demonstrate its effectiveness in the context of convolutional neural networks… CONTINUE READING
    2 Citations
    A Survey on Evolutionary Neural Architecture Search
    • 3
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 58 REFERENCES
    DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence
    • 11
    • PDF
    Auto-Keras: An Efficient Neural Architecture Search System
    • 162
    • PDF
    Multi-objective Architecture Search for CNNs
    • 48
    Evaluating the Search Phase of Neural Architecture Search
    • 139
    • PDF
    SNAS: Stochastic Neural Architecture Search
    • 349
    • PDF
    Learning Ensembles of Neural Networks by Means of a Bayesian Artificial Immune System
    • 29
    Efficient Architecture Search by Network Transformation
    • 292
    Regularized Evolution for Image Classifier Architecture Search
    • 982
    • Highly Influential
    • PDF
    Neural Architecture Search with Reinforcement Learning
    • 2,199
    • PDF
    Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution
    • 179
    • Highly Influential
    • PDF