# Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets

arXiv: https://arxiv.org/abs/1901.09049 · HTML: https://mlsanity.com/paper/1901.09049/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2019.

## Built on by (most cited first, 20 of 20)

- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Learning What and Where: Disentangling Location and Identity Tracking Without Supervision](https://mlsanity.com/paper/2205.13349/) (2022)
- [Exploring the Promise and Limits of Real-Time Recurrent Learning](https://mlsanity.com/paper/2305.19044/) (2023)
- [Convergence and Alignment of Gradient Descent with Random Backpropagation Weights](https://mlsanity.com/paper/2106.06044/) (2021)
- [Meta-learning Spiking Neural Networks with Surrogate Gradient Descent](https://mlsanity.com/paper/2201.10777/) (2022)
- [Encoding Event-Based Data With a Hybrid SNN Guided Variational Auto-encoder in Neuromorphic Hardware](https://mlsanity.com/paper/2104.00165/) (2021)
- [Noise-Aware Training of Neuromorphic Dynamic Device Networks](https://mlsanity.com/paper/2401.07387/) (2024)
- [Cortico-cerebellar networks as decoupling neural interfaces](https://mlsanity.com/paper/2110.11501/) (2021)
- [Learning Object Permanence from Videos via Latent Imaginations](https://mlsanity.com/paper/2310.10372/) (2023)
- [Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networks](https://mlsanity.com/paper/2306.01906/) (2023)
- [Three-Factor Learning in Spiking Neural Networks: An Overview of Methods and Trends from a Machine Learning Perspective](https://mlsanity.com/paper/2504.05341/) (2025)
- [Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks](https://mlsanity.com/paper/2206.12520/) (2022)
- [A Taxonomy of Recurrent Learning Rules](https://mlsanity.com/paper/2207.11439/) (2022)
- [Including STDP to eligibility propagation in multi-layer recurrent spiking neural networks](https://mlsanity.com/paper/2201.07602/) (2022)
- [Efficient LSTM Training with Eligibility Traces](https://mlsanity.com/paper/2209.15502/) (2022)
- [RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers](https://mlsanity.com/paper/2601.00426/) (2026)
- [Emergent organization of receptive fields in networks of excitatory and inhibitory neurons](https://mlsanity.com/paper/2205.13614/) (2022)
- [Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing](https://mlsanity.com/paper/2405.05141/) (2024)
- [Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing](https://mlsanity.com/paper/2408.15800/) (2024)
- [Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency](https://mlsanity.com/paper/2605.27946/) (2026)

## Abstract (arXiv)

The way how recurrently connected networks of spiking neurons in the brain acquire powerful information processing capabilities through learning has remained a mystery. This lack of understanding is linked to a lack of learning algorithms for recurrent networks of spiking neurons (RSNNs) that are both functionally powerful and can be implemented by known biological mechanisms. Since RSNNs are simultaneously a primary target for implementations of brain-inspired circuits in neuromorphic hardware, this lack of algorithmic insight also hinders technological progress in that area. The gold standard for learning in recurrent neural networks in machine learning is back-propagation through time (BPTT), which implements stochastic gradient descent with regard to a given loss function. But BPTT is unrealistic from a biological perspective, since it requires a transmission of error signals backwards in time and in space, i.e., from post- to presynaptic neurons. We show that an online merging of locally available information during a computation with suitable top-down learning signals in real-time provides highly capable approximations to BPTT. For tasks where information on errors arises only late during a network computation, we enrich locally available information through feedforward eligibility traces of synapses that can easily be computed in an online manner. The resulting new generation of learning algorithms for recurrent neural networks provides a new understanding of network learning in the brain that can be tested experimentally. In addition, these algorithms provide efficient methods for on-chip training of RSNNs in neuromorphic hardware.