No abstract

The formations of different types of laser-induced periodic surface structures (LIPSS) on the surface of GaP crystals with different laser fluence are researched in experiments. The transition from the high spatial frequency LIPSS (HSFL) to the low spatial frequency LIPSS (LSFL) occurred as the number of the irradiated laser pulse increased. The finite difference time domain method combined with the holographic ablation model is used to simulate the LIPSS formation under the irradiation of multiple pulses. Different types of ripples are predicted by the electromagnetic approach. Results demonstrate that the electromagnetic origins of HSFL and LSFL are due to the interference of incident field and the scattering field under the multi-pulse irradiation.

Meta-Learning, or so-called Learning to learn, has become another important research branch in Machine Learning. Different from traditional deep learning, meta-learning can be used to solve one-to-many problems and has a better performance in few-shot learning which only few samples are available in each class. In these tasks, meta-learning is designed to quickly form a relatively reliable model through very limited samples. In this paper, we propose a modified LSTM-based meta-learning model, which can initialize and update the parameters of classifier (learner) considering both short-term knowledge of one task and long-term knowledge across multiple tasks. We reconstruct a Compound loss function to make up for the deficiency caused by the separate one in original model aiming for a quick start and better stability, without taking expensive operation. Our modification enables meta-learner to perform better under few-updates. Experiments conducted on the Mini-ImageNet demonstrate the improved accuracies.

No abstract