QLAB: Quadratic Loss Approximation-Based Optimal Learning Rate for Deep Learning.
Minghan FuFang-Xiang WuPublished in: CoRR (2023)
Keyphrases
- learning rate
- deep learning
- convergence rate
- learning algorithm
- unsupervised learning
- unsupervised feature learning
- convergence speed
- hidden layer
- machine learning
- rapid convergence
- adaptive learning rate
- computer vision
- natural images
- evolutionary algorithm
- object recognition
- support vector
- feature extraction
- data mining