Optimization-based Structural Pruning for Large Language Models without Back-Propagation.
Yuan GaoZujing LiuWeizhong ZhangBo DuGui-Song XiaPublished in: CoRR (2024)
Keyphrases
- language model
- back propagation
- artificial neural networks
- neural network
- language modeling
- feed forward
- training algorithm
- n gram
- bp algorithm
- feed forward neural networks
- document retrieval
- bp neural network
- speech recognition
- language modelling
- retrieval model
- information retrieval
- hidden layer
- multilayer perceptron
- learning algorithm
- probabilistic model
- query expansion
- test collection
- statistical language models
- fuzzy logic
- language models for information retrieval
- optimization algorithm
- smoothing methods
- context sensitive
- steepest descent method
- activation function
- bp network
- global optimization
- levenberg marquardt
- document ranking
- multi layer neural network
- cascade correlation
- data mining
- recurrent neural networks
- least squares
- multilayer neural network
- support vector machine
- evolutionary algorithm
- artificial intelligence