The Symplectic Adjoint Method: Memory-Efficient Backpropagation of Neural-Network-Based Differential Equations.
Takashi MatsubaraYuto MiyatakeTakaharu YaguchiPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- differential equations
- back propagation
- memory efficient
- neural network
- training algorithm
- pairwise
- dynamic programming
- numerical methods
- feed forward
- support vector machine
- artificial neural networks
- learning algorithm
- genetic algorithm
- mathematical model
- feed forward neural networks
- backpropagation neural network
- backpropagation neural networks
- pattern classification
- high order
- object recognition
- knowledge base
- machine learning