# Front Contribution instead of Back Propagation

arXiv: https://arxiv.org/abs/2106.05569 · HTML: https://mlsanity.com/paper/2106.05569/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Training Neural Networks with Local Error Signals](https://mlsanity.com/paper/1901.06656/) (2019)
- [Greedy Layerwise Learning Can Scale to ImageNet](https://mlsanity.com/paper/1812.11446/) (2018)
- [Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures](https://mlsanity.com/paper/1807.04587/) (2018)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [Memory-Efficient Backpropagation Through Time](https://mlsanity.com/paper/1606.03401/) (2016)
- [The HSIC Bottleneck: Deep Learning without Back-Propagation](https://mlsanity.com/paper/1908.01580/) (2019)
- [Biologically Motivated Algorithms for Propagating Local Target Representations](https://mlsanity.com/paper/1805.11703/) (2018)
- [Deep supervised learning using local errors](https://mlsanity.com/paper/1711.06756/) (2017)
- [Decoupled Parallel Backpropagation with Convergence Guarantee](https://mlsanity.com/paper/1804.10574/) (2018)
- [Understanding Synthetic Gradients and Decoupled Neural Interfaces](https://mlsanity.com/paper/1703.00522/) (2017)
- [Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input](https://mlsanity.com/paper/1905.13633/) (2019)
- [Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks](https://mlsanity.com/paper/1908.06378/) (2019)
- [Learning to solve the credit assignment problem](https://mlsanity.com/paper/1906.00889/) (2019)
- [Beyond Backprop: Online Alternating Minimization with Auxiliary Variables](https://mlsanity.com/paper/1806.09077/) (2018)
- [Conducting Credit Assignment by Aligning Local Representations](https://mlsanity.com/paper/1803.01834/) (2018)
- [A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation](https://mlsanity.com/paper/1905.11722/) (2019)
- [Learning in the Machine: Random Backpropagation and the Deep Learning Channel](https://mlsanity.com/paper/1612.02734/) (2016)
- [Breaking the Activation Function Bottleneck through Adaptive Parameterization](https://mlsanity.com/paper/1805.08574/) (2018)
- [Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs](https://mlsanity.com/paper/1807.09511/) (2018)
- [Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment](https://mlsanity.com/paper/2002.03911/) (2020)

## Abstract (arXiv)

Deep Learning's outstanding track record across several domains has stemmed from the use of error backpropagation (BP). Several studies, however, have shown that it is impossible to execute BP in a real brain. Also, BP still serves as an important and unsolved bottleneck for memory usage and speed. We propose a simple, novel algorithm, the Front-Contribution algorithm, as a compact alternative to BP. The contributions of all weights with respect to the final layer weights are calculated before training commences and all the contributions are appended to weights of the final layer, i.e., the effective final layer weights are a non-linear function of themselves. Our algorithm then essentially collapses the network, precluding the necessity for weight updation of all weights not in the final layer. This reduction in parameters results in lower memory usage and higher training speed. We show that our algorithm produces the exact same output as BP, in contrast to several recently proposed algorithms approximating BP. Our preliminary experiments demonstrate the efficacy of the proposed algorithm. Our work provides a foundation to effectively utilize these presently under-explored "front contributions", and serves to inspire the next generation of training algorithms.