A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or ...

Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to ...

Keywords: active learning, contrastive learning, clustering, semi-supervised learning, human-in-the-loop Citation: Roda H and Geva AB (2024) Semi-supervised active learning using convolutional ...

For action inference, we use the common protocol of unsupervised feature learning, i.e., linear evaluation (Zheng et al., 2018), such that the latent features learned without supervision are given to ...

Trans-encoder is a completely unsupervised sentence-pair model developed by Amazon Research experts. The corresponding research paper was also presented at this year’s International Conference on ...