# Conducting Credit Assignment by Aligning Local Representations

arXiv: https://arxiv.org/abs/1803.01834 · HTML: https://mlsanity.com/paper/1803.01834/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2018.

## Built on by (most cited first, 12 of 12)

- [Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment](https://mlsanity.com/paper/2312.09257/) (2023)
- [BayesPCN: A Continually Learnable Predictive Coding Associative Memory](https://mlsanity.com/paper/2205.09930/) (2022)
- [How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective](https://mlsanity.com/paper/2106.08453/) (2021)
- [Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning](https://mlsanity.com/paper/2106.06401/) (2021)
- [Fixed-Weight Difference Target Propagation](https://mlsanity.com/paper/2212.10352/) (2022)
- [Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning](https://mlsanity.com/paper/2409.19841/) (2024)
- [InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem](https://mlsanity.com/paper/2105.00568/) (2021)
- [A Robust Backpropagation-Free Framework for Images](https://mlsanity.com/paper/2206.01820/) (2022)
- [Forward Learning of Graph Neural Networks](https://mlsanity.com/paper/2403.11004/) (2024)
- [Front Contribution instead of Back Propagation](https://mlsanity.com/paper/2106.05569/) (2021)
- [Feature Alignment as a Generative Process](https://mlsanity.com/paper/2106.12562/) (2021)
- [Can Local Representation Alignment RNNs Solve Temporal Tasks?](https://mlsanity.com/paper/2504.13531/) (2025)

## Abstract (arXiv)

Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Here, we present Local Representation Alignment (LRA), a training procedure that is much less sensitive to bad initializations, does not require modifications to the network architecture, and can be adapted to networks with highly nonlinear and discrete-valued activation functions. Furthermore, we show that one variation of LRA can start with a null initialization of network weights and still successfully train networks with a wide variety of nonlinearities, including tanh, ReLU-6, softplus, signum and others that may draw their inspiration from biology. A comprehensive set of experiments on MNIST and the much harder Fashion MNIST data sets show that LRA can be used to train networks robustly and effectively, succeeding even when back-propagation fails and outperforming other alternative learning algorithms, such as target propagation and feedback alignment.