Articles proposes a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. The model achieves 28.4 BLEU on the WMT 2014 English- to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. The Transformer also generalizes well to other tasks.
Continue ReadingLearning to Compare: Relation Network for Few-Shot Learning
A general framework for few-shot learning. The method, called the Relation Network (RN), is trained end-to-end from scratch. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning.
Continue ReadingThe interactive whiteboard in primary school science and interaction
Teaching using an Interactive Whiteboard does not indicate dialogic interaction, according to the current study. The questions about the place and role of the IWB are asked. The answer would seem to lie in the teachers’ perceptional change in respect of interaction and learning.
Continue Reading