PhD student at the Halmstad University
Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experiences. While this concept is inherent in the human learning ability, current machine learning-based methods struggle with this as they are highly prone to forget past experiences and they are usually not trained to accelerate future learning. Meta-learning, or learning how to learn, has shown promise in addressing these challenges. In this project, we propose to apply meta-learning to solve CL problems by meta-learning the weights and the hyperparameters of a neural network. We will also introduce a novel metric to evaluate the transferability of prior knowledge on the current task, determining the degree of model update at each iteration. We will evaluate our approach on four benchmarks, including Split MNIST, Permuted MNIST, NEVIS’22, and Meta-Album. Expected results will show that fine-tuning the model to the current task, before making the final prediction, is beneficial for the learning process and allows it to outperform state-of-the-art methods with few examples.
Visit to: Automated Machine Learning group at TU/e University (Eindhoven, Netherlands). Collaborator at the host institution: Joaquin Vanschoren, Associate Professor, Department of Mathematics and Computer Science, Eindhoven University of Technology, The Netherlands.