HIGHLIGHTS
SUMMARY
With the development of deep learning and high-performance GPU, plentiful neural_network models with more layers and more parameters are proposed. Namely, the neural_network structure parameters are trained in advance through a large amount of data, and then the trained neural_network is fine-tuned under the current specific task. As the authors know from the "Customer requirements classification" section, customer requirements actually involve multi-domain information and functional customer requirements represent customer intention maximally. With the development of deep learning and high-performance GPU, plentiful neural_network models with more layers and more parameters are . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.