US Patent Application 18313291. TRAINING NEURAL NETWORKS USING SIGN AND MOMENTUM BASED OPTIMIZERS simplified abstract
Contents
TRAINING NEURAL NETWORKS USING SIGN AND MOMENTUM BASED OPTIMIZERS
Organization Name
Inventor(s)
Xiangning Chen of Los Angeles CA (US)
Chen Liang of Stanford CA (US)
Da Huang of Santa Clara CA (US)
Esteban Alberto Real of Sunnyvale CA (US)
Kaiyuan Wang of Newark CA (US)
Yifeng Lu of Palo Alto CA (US)
Quoc V. Le of Sunnyvale CA (US)
TRAINING NEURAL NETWORKS USING SIGN AND MOMENTUM BASED OPTIMIZERS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18313291 titled 'TRAINING NEURAL NETWORKS USING SIGN AND MOMENTUM BASED OPTIMIZERS
Simplified Explanation
The patent application describes a method, system, and apparatus for training a neural network using a specific type of optimizer called momentum and sign based optimizer.
- The patent application focuses on training a neural network to perform a machine learning task.
- The proposed method involves using a momentum and sign based optimizer to optimize the training process.
- The optimizer is designed to improve the efficiency and effectiveness of the neural network training.
- The method includes encoding computer programs on computer storage media to implement the optimizer.
- The invention aims to enhance the performance of machine learning tasks by utilizing this specific optimizer.
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform a machine learning task using a momentum and sign based optimizer.