Mar 4, 2018 · Abstract:Deep learning is formulated as a discrete-time optimal control problem. This allows one to characterize necessary conditions for ...
The developed methods are applied to train, in a rather principled way, neural networks with weights that are constrained to take values in a discrete set. We ...
The discrete-time method of successive approximations (MSA), which is based on the Pontryagin's maximum principle, is introduced for training neural ...
Deep learning is formulated as a discrete-time optimal control problem. This allows one to characterize necessary conditions for optimality and develop ...
Jun 2, 2018 · Deep learning is formulated as a discrete-time optimal control problem. This allows one to char- acterize necessary conditions for ...
Paper: Qianxiao Li and Shuji Hao. "An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks". The 35th International ...
People also ask
What is the optimization method used in deep learning?
What is optimal control in machine learning?
What is the method used to optimize the complexity of a neural network?
Which algorithm is commonly used in the training of neural networks?
“An Optimal Control Approach to Deep Learning and. Applications to Discrete-Weight Neural Networks”. A Full Statement and Sketch of the Proof of Theorem 1. In ...
A mean-field optimal control formulation of deep learning ... An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks.
An optimal control approach to deep learning and applications to discrete-weight neural networks. In International Conference on Machine Learning, pages 2991–.