Corpus ID: 219687843

Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms

@article{Dietz2020InteractionNU,
  title={Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms},
  author={F. Dietz},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.08457}
}
  • F. Dietz
  • Published 2020
  • Computer Science
  • ArXiv
  • The wiring of neurons in the brain is more flexible than the wiring of connections in contemporary artificial neural networks. It is possible that this extra flexibility is important for efficient problem solving and learning. This paper introduces the Interaction Network. Interaction Networks aim to capture some of this extra flexibility. An Interaction Network consists of a collection of conventional neural networks, a set of memory locations, and a DQN or other reinforcement learner. The… CONTINUE READING

    References

    SHOWING 1-10 OF 20 REFERENCES
    Hybrid computing using a neural network with dynamic external memory
    • 940
    • PDF
    Decoupled Neural Interfaces using Synthetic Gradients
    • 199
    • PDF
    The economy of brain network organization
    • 1,849
    • PDF
    Dynamic Routing Between Capsules
    • 1,883
    • Highly Influential
    • PDF
    An Overview of Multi-task Learning
    • 365
    • PDF
    An Overview of Multi-Task Learning in Deep Neural Networks
    • 987
    • PDF
    One Model To Learn Them All
    • 189
    • PDF
    Complexity and coherency: integrating information in the brain
    • 617
    • PDF