Original Contribution: A learning algorithm for multilayered neural networks based on linear least squares problems

By F. Biegler-König, F. Bärmann. 1993

Citations in the corpus

• Deep learning in neural networks: An overview (2014, neutral): “BP can be treated as a linear least-squares problem (Biegler-König & Bärmann, 1993), where second-order gradient information is passed back to preceding layers.”