A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. ... It seems handy to include an additional skip connection in the search space to make depths variable. ... Informally, ELS plays an important role in rectifying the features' phase gap between skip connections and other homogeneous choices. ...arXiv:1908.06022v6 fatcat:hilaqbep6vhibj6x3xaqvoy2za
In order to overcome some shortcomings of manually designed CNN, neural architecture search (NAS) technology has become an important research direction of deep learning. ... However, the architectures of these CNNs have mostly been developed manually by human experts, which is a time-consuming and error-prone process. ... By forcing all sub-models to share weights, the shortcomings of Chu et al.  Bridging the gap between stability and scalability in weight-sharing neural architecture search Nayman et al. ...doi:10.1007/s11633-021-1292-1 fatcat:ki4as3yt3rgvbe5ytenhpelpr4