Corpus ID: 219721016

Neural Optimal Control for Representation Learning

@article{Chalvidal2020NeuralOC,
  title={Neural Optimal Control for Representation Learning},
  author={Mathieu Chalvidal and Matthew Ricci and R. VanRullen and Thomas Serre},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.09545}
}
The intriguing connections recently established between neural networks and dynamical systems have invited deep learning researchers to tap into the well-explored principles of differential calculus. Notably, the adjoint sensitivity method used in neural ordinary differential equations (Neural ODEs) has cast the training of neural networks as a control problem in which neural modules operate as continuous-time homeomorphic transformations of features. Typically, these methods optimize a single… Expand

References

SHOWING 1-10 OF 44 REFERENCES
A mean-field optimal control formulation of deep learning
Neural Ordinary Differential Equations
Stable Architectures for Deep Neural Networks
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
Maximum Principle Based Algorithms for Deep Learning
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
...
1
2
3
4
5
...