Transfer learning is a machine learning technique that involves using the knowledge acquired by a model trained on a specific task to improve the performance of another model on a related but different task.
In transfer learning, a pre-trained model, called a source model, which has learned to solve a specific task, is used to initialise the weights of the target model, which is used to solve a related but different task. The idea behind transfer learning is that the pre-trained model has already learned general and useful features of the source task domain, which may also be useful for the target task.
Transfer learning is commonly used in computer vision and natural language processing applications, where training data may be limited or expensive to obtain. It is also used in cases where the target task is sufficiently different from the source task to require model adaptation, but there are still some similarities that can be exploited.
The use of Artificial Intelligence in business is becoming more and more common and necessary for the optimization and evolution of processes. In one of our [...]
Read More »The content of this article synthesizes part of the chapter "Concept and brief history of Artificial Intelligence" of the thesis Generation of Artificial [...]
Read More »Natural Language Processing or NLP analyzes how machines understand, interpret and process human language.
Read More »The commercial optimization software based on artificial intelligence must have feedback of the commercial actions carried out, of the nu [...]
Read More »
