54 citations · 66 across the 4 of their papers we have counts for
4 papers
Few-Shot Learning with Per-Sample Rich Supervision
Roman Visotsky, Yuval Atzmon, Gal Chechik
Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting…
Learning to generalize to new compositions in image understanding
Yuval Atzmon, Jonathan Berant, Vahid Kezami +2
Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scene…
Gradual training of deep denoising auto encoders
Alexander Kalmanovich, Gal Chechik
Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We inve…
Adaptive Regularization for Weight Matrices
Koby Crammer, Gal Chechik
Algorithms for learning distributions over weight-vectors, such as AROW were recently shown empirically to achieve state-of-the-art performance at various problems, with strong the…