AutoLR: an evolutionary approach to learning rate policies.
Pedro CarvalhoNuno LourençoFilipe AssunçãoPenousal MachadoPublished in: GECCO (2020)
Keyphrases
- learning rate
- learning algorithm
- convergence rate
- discount factor
- error function
- hidden layer
- adaptive learning rate
- convergence speed
- multilayer neural networks
- optimal policy
- weight vector
- convergence theorem
- delta bar delta
- rapid convergence
- training algorithm
- decision processes
- fitness function
- multi objective
- objective function