The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Cross-entropy loss and focal loss are the most common choices when training deep neural
networks for classification problems. Generally speaking, however, a good loss function can …

Abstract Model-agnostic meta learning (MAML) is currently one of the dominating
approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML …

Although deep learning has made great progress in recent years, the exploding economic
and environmental costs of training neural networks are becoming unsustainable. To …

We propose a meta-learning technique for offline discovery of physics-informed neural
network (PINN) loss functions. We extend earlier works on meta-learning, and develop a …

Automated construction of deep neural networks (DNNs) has become a research hot spot
nowadays because DNN's performance is heavily influenced by its architecture and …

Generalising robustly to distribution shift is a major challenge that is pervasive across most
real-world applications of machine learning. A recent study highlighted that many advanced …

Few-shot object detection, the problem of modelling novel object detection categories with
few training instances, is an emerging topic in the area of few-shot learning and object …

The choice of activation function can have a large effect on the performance of a neural
network. While there have been some attempts to hand-engineer novel activation functions …

Recent studies have shown that the choice of activation function can significantly affect the
performance of deep learning networks. However, the benefits of novel activation functions …