Efficient and sparse neural networks by pruning weights in a multiobjective learning approach.
Malena ReinersKathrin KlamrothFabian HeldmannMichael StiglmayrPublished in: Comput. Oper. Res. (2022)
Keyphrases
- multi objective
- neural network
- learning algorithm
- online learning
- prior knowledge
- connectionist systems
- error back propagation
- weight update
- learning process
- search space
- supervised learning
- learning systems
- neural nets
- reinforcement learning
- unsupervised learning
- back propagation
- learning tasks
- recurrent neural networks
- incremental learning
- tree construction
- artificial neural networks
- training data