Deep Supervised Learning Using Local Errors
Sign Up to like & getrecommendations! Published in 2018 at "Frontiers in Neuroscience"
DOI: 10.3389/fnins.2018.00608
Abstract: Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from higher layers.… read more here.
Keywords: local errors; mechanism; layer; deep supervised ... See more keywords
The Mirage of Progress? A Longitudinal Study of Japanese Students’ L2 Oral Grammar
Sign Up to like & getrecommendations! Published in 2021 at "Language Teaching"
DOI: 10.37546/jalttlt45.2-2
Abstract: This study examines the grammatical errors in Japanese university students’ dialogues over an academic year. The L2 interactions of 15 Japanese speakers were taken from the JUSFC2018 corpus (April/May 2018) and the JUSFC2019 corpus (January/February… read more here.
Keywords: mirage progress; progress longitudinal; study; 100 words ... See more keywords