DRTP trains hidden layers using only fixed random projections of the one-hot label, removing feedback pathways and update locking at a modest accuracy cost versus backpropagation.
Rosenblatt, Principles of neurodynamics: Perceptrons and the theory of brain mechanisms, Sparta, NJ, USA: Spartan Books, 1961
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks
DRTP trains hidden layers using only fixed random projections of the one-hot label, removing feedback pathways and update locking at a modest accuracy cost versus backpropagation.