Loading timeline…
19861980s
Backpropagation Revival
Practical implementation of the backpropagation algorithm for multi-layer neural networks.
Why It Was Important
David Rumelhart, Geoffrey Hinton, and Ronald Williams demonstrated that backpropagation could successfully train deep, multi-layer neural networks to learn internal representations of data. This solved the XOR problem that had stalled neural network research since 1969, sparking a major connectionist revival.
Who Invented It
David Rumelhart, Geoffrey Hinton, Ronald Williams
The 'Parallel Distributed Processing' (PDP) research group.
Applications
- Deep Learning
- Pattern Recognition
- Weight Optimization
Key Papers
- Learning Representations by Back-Propagating Errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986
Videos
What is Back Propagation
IBM Technology