# Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network

arXiv: https://arxiv.org/abs/2208.01416 · HTML: https://mlsanity.com/paper/2208.01416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 1 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation](https://mlsanity.com/paper/1602.05179/) (2016)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Putting An End to End-to-End: Gradient-Isolated Learning of Representations](https://mlsanity.com/paper/1905.11786/) (2019)
- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization](https://mlsanity.com/paper/1908.09375/) (2019)
- [Towards Biologically Plausible Deep Learning](https://mlsanity.com/paper/1502.04156/) (2015)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [How Important is Weight Symmetry in Backpropagation?](https://mlsanity.com/paper/1510.05067/) (2015)
- [Understanding Synthetic Gradients and Decoupled Neural Interfaces](https://mlsanity.com/paper/1703.00522/) (2017)
- [Credit Assignment in Neural Networks through Deep Feedback Control](https://mlsanity.com/paper/2106.07887/) (2021)
- [On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent](https://mlsanity.com/paper/1712.06564/) (2017)
- [Learning in the Machine: the Symmetries of the Deep Learning Channel](https://mlsanity.com/paper/1712.08608/) (2017)
- [Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks](https://mlsanity.com/paper/1909.01311/) (2019)

## Abstract (arXiv)

Despite the widespread adoption of Backpropagation algorithm-based Deep Neural Networks, the biological infeasibility of the BP algorithm could potentially limit the evolution of new DNN models. To find a biologically plausible algorithm to replace BP, we focus on the top-down mechanism inherent in the biological brain. Although top-down connections in the biological brain play crucial roles in high-level cognitive functions, their application to neural network learning remains unclear. This study proposes a two-level training framework designed to train a bottom-up network using a Top-Down Credit Assignment Network (TDCA-network). The TDCA-network serves as a substitute for the conventional loss function and the back-propagation algorithm, widely used in neural network training. We further introduce a brain-inspired credit diffusion mechanism, significantly reducing the TDCA-network's parameter complexity, thereby greatly accelerating training without compromising the network's performance.Our experiments involving non-convex function optimization, supervised learning, and reinforcement learning reveal that a well-trained TDCA-network outperforms back-propagation across various settings. The visualization of the update trajectories in the loss landscape indicates the TDCA-network's ability to bypass local minima where BP-based trajectories typically become trapped. The TDCA-network also excels in multi-task optimization, demonstrating robust generalizability across different datasets in supervised learning and unseen task settings in reinforcement learning. Moreover, the results indicate that the TDCA-network holds promising potential to train neural networks across diverse architectures.