Backpropagation Paper Published in Nature
Rumelhart, Hinton, and Williams publish "Learning representations by back-propagating errors" in Nature (vol. 323, pp. 533-536), demonstrating that multi-layer neural networks can learn useful internal representations by propagating error gradients backward through hidden layers — overcoming the limitations of single-layer perceptrons identified by Minsky and Papert in 1969 and reigniting the connectionist revolution that would eventually produce modern deep learning
Key Figures
Causal neighbors · 337 linked moments
1969
· thematic
I
2009
· thematic
I
2009
· follows
1958
· thematic
1958
· influences
1969
· influences
1948
· thematic
1948
· influences
2006
· same figure
2006
· thematic
1950
· thematic
1950
· influences
2006
· follows
2017
· thematic
2017
· caused by
2012
· same figure
2012
· thematic
2016
· thematic
1997
· thematic
1956
· thematic
2012
· caused by
R
1986
· same era
S
1986
· same era
S
1986
· precedes
S
1986
· precedes
R
1986
· precedes
S
1988
· same era
S
1988
· follows
S
1986
· same era
S
1986
· precedes
E
1986
· same era
E
1986
· precedes
S
1988
· same era
S
1988
· follows
S
1986
· same era
S
1981
· same era