Many people, including Geoffrey Hinton, have raised concerns about the back-propagation algorithm and the fact that it’s likely not a promising way to achieve Artificial Intelligence (see this Axios blog post).
Alternative mechanisms for learning have been and are currently studied to try and approach the learning problem in a more effective way.
Direct feedback alignment
The theory is sometimes summarized as “Cells that fire together wire together.”.
- Millidge, Beren, Alexander Tschantz, and Christopher L. Buckley. October 5, 2020. "Predictive Coding Approximates Backprop along Arbitrary Computation Graphs". arXiv:2006.04182 [Cs]. http://arxiv.org/abs/2006.04182.
- Whittington, James C. R., and Rafal Bogacz. May 2017. “An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity”. Neural Computation 29 (5):1229–62. DOI.
- Nøkland, Arild. December 21, 2016. “Direct Feedback Alignment Provides Learning in Deep Neural Networks”. arXiv:1609.01596 [Cs, Stat]. http://arxiv.org/abs/1609.01596.