Outperforms State-of-the-art Algorithms In Deep Learning Tasks

A research team has proposed a novel meta-learning based semi-supervised learning algorithm called Meta-Semi, which requires tuning only one additional hyper-parameter and outperforms existing state-of-the-art semi-supervised learning algorithms. This algorithm has the potential to be used in real semi-supervised learning scenarios such as medical image processing, hyper-spectral image classification, network traffic recognition, and document recognition. The team published their work in the journal CAAI Artificial Intelligence Research on March 10.