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.
Artificial intelligence (AI) and machine learning (ML) are two of the most popular technologies used to build intelligent systems for the [...]
Read More »The acquisition of new potential customers is one of the most important and difficult processes for a company. Traditionally, it has been necessary to [...]
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 »Data Mining is a process of exploration and analysis of large amounts of data, with the objective of discovering patterns, relationships and trends that can be [...]
Read More »