# Are skip connections necessary for biologically plausible learning rules?

arXiv: https://arxiv.org/abs/2001.01647 · HTML: https://mlsanity.com/paper/2001.01647/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2019.

## Built on by (most cited first, 1 of 1)

- [Functional Connectome: Approximating Brain Networks with Artificial Neural Networks](https://mlsanity.com/paper/2211.12935/) (2022)

## Abstract (arXiv)

Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation. None of these methods have produced a competitive performance against backpropagation. In this paper, we show that biologically-motivated learning rules with skip connections between intermediate layers can perform as well as backpropagation on the MNIST dataset and are robust to various sets of hyper-parameters.