FTP trains neural networks using only forward passes, propagating random-projection target signals through the network, and achieves near-backpropagation accuracy on small shallow benchmarks.
Rumelhart, Geoffrey E
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
FTP trains neural networks using only forward passes, propagating random-projection target signals through the network, and achieves near-backpropagation accuracy on small shallow benchmarks.