The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
–Neural Information Processing Systems
Deep learning succeeds by doing hierarchical feature learning, yet tuning hyper-parameters (HP) such as initialization scales, learning rates etc., only give indirect
Neural Information Processing Systems
Oct-11-2025, 00:27:05 GMT
- Country:
- Europe > Switzerland
- North America > United States (0.14)
- Genre:
- Research Report > Experimental Study (0.93)
- Technology: