Transfer learning is a machine learning method that takes a model developed for task A as a starting point and reuses it in developing a model for task B. In deep learning, it is a common method to use pre-trained models as the starting point of new models in computer vision tasks and natural language processing tasks. Usually, these pre-trained models have consumed huge time resources and resources when developing neural networks. Computational resources, transfer learning can transfer acquired powerful skills to related problems.
Chinese name: transfer learning
Foreign name: Transfer learning
Definition: use the model developed for task A as an initial point, and reuse it in the process of developing a model for task B
Common methods: methods of developing models, methods of pre-training models
Nature: A Machine Learning Method
